Cleanup for 0.5.0 alpha release

Signed-off-by: Justin Georgi <justin.georgi@gmail.com>

.gitea/workflows/dev-build.yaml

@@ -0,0 +1,32 @@
+name: Build Dev PWA
+run-name: ${{ gitea.actor }} is building new dev pwa version
+on:
+  push:
+    branches:
+      - main 
+
+jobs:
+  Build-PWA:
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+      - name: Install node modules
+        run: npm install
+      - name: Build pwa
+        run: npm run build
+      - name: Replace previous dev pwa
+        env:
+          DEV_HOST: ${{ secrets.DEV_HOST }}
+          DEV_KEY: ${{ secrets.DEV_KEY }}
+          DEV_FP: ${{ secrets.DEV_FINGERPRINT }}
+        run: |
+          echo "$DEV_KEY" > ~/.ssh/id_rsa
+          chmod 600 ~/.ssh/id_rsa
+          echo "$DEV_FP" > ~/.ssh/known_hosts
+          chmod 600 ~/.ssh/known_hosts
+          ssh root@$DEV_HOST "rm -R /var/www/html/alvinn-dev/*"
+          echo "Old files removed"
+          scp -r ${{ gitea.workspace }}/www/* root@$DEV_HOST:/var/www/html/alvinn-dev
+          ssh root@$DEV_HOST "chown -R www-data:www-data /var/www/html/alvinn-dev/*"
+          echo "New files copied"

README.md

@@ -1,6 +1,6 @@
 # ALVINN
 
-Anatomy Lab Visual Identification Neural Net (A.L.V.I.N.N) is a f7 based app for using a computer vision neural net model to identify anatomical structures in photographic imagery.
+Anatomy Lab Visual Identification Neural Net (A.L.V.I.N.N.) is a f7 based app for using a computer vision neural net model to identify anatomical structures in photographic imagery.
 
 ## Install
 * **Android:** Download the latest Android apk in [packages](https://gitea.azgeorgis.net/Georgi_Lab/ALVINN_f7/packages) and open the downloaded file to install.
@@ -9,16 +9,26 @@ Anatomy Lab Visual Identification Neural Net (A.L.V.I.N.N) is a f7 based app for
 * **Run from source:** Clone this repository and in the root directory run `npm install` followed by `npm start`.  For more information see [f7 info](f7_info.md).
 
 ## Quick Start
-1. From the main screen of the app, select the menu icon in the upper left corner and go to `Settings`.
+1. Select the region of the body you want to identify structures from. The regions are:
-1. Make sure that `Use external server` option is selected and fill in address and port parameters to connect to a back end serving the ALVINN models (Doods2 is the default backend).
+    * Thorax and back
-1. Save the settings and return to the main screen.
+    * Abdomen and pelvis
-1. Select the region of the body you want to identify structures from.
+    * Limbs
-1. In the region page, click on the camera icon to take a new picture or load a picture from storage. When the picture load, any identifiable structures will be listed as tags below the image.
+    * Head and neck
-1. Click on each tag to see the structure highlighted in the image.
+1. Load an image in one of the following ways:
+    * Click on the camera icon to take a new picture.
+      * ALVINN will highlight areas with potential structures as you aim the camera.
+      * Press Capture to use the current camera view.
+    * Click on the image file icon to load a picture from the device storage.
+    * If demo mode is turned on, you can click on the marked image icon to load an ALVINN sample image.
+1. When the picture is captured or loaded, any identifiable structures will be listed as tags below the image:
+    * Click on each tag to see the structure highlighted in the image or click on the image to see the tag for that structure (additional clicks to the same area will select overlapping structres).
+    * Tag color and proportion filled indicate ALVINN's level of confidence in the identification.
+    * An incorrect tag can be deleted by clicking on the tag's X button.
 
 ## Advanced Features
 ### Detection Parameters
-After an image has been loaded and structure detection has been performed, the detection parameters can be adjusted using the third detection menu button (eye).
+If there are potential structures that do not satisfy the current detection settings, a badge on the detection menu icon will indicate the number of un-displayed structures.
+Clicking on the detection menu icon will open a menu of tools to adjust the detection settings.
 This button will make three tools available:
 1. Confidence slider: You can use the slider to change the confidence threshold for identifying structures.
 The default threshold is 50% confidence.
@@ -28,4 +38,35 @@ The default threshold is 50% confidence.
 ### Submitting Images
 If all of the detection tags that are currently visible have been viewed, then the final button (cloud upload) on the detection menu will be enabled.
 This button will cause the image and the verified structures to be uploaded to the ALVINN project servers where that data will be available for further training of the neural net.
-If after the image has been uploaded, the available detection tags change, then the option to re-upload the image will be available if all the new tags have been viewed and verified.
+If after the image has been uploaded, the available detection tags change, then the option to re-upload the image will be available if all the new tags have been viewed and verified.
+
+## Configuration
+Configuring aspects of the hosted ALVINN PWA is done through the `conf.yaml` file in the `conf` folder.
+### Site settings
+The following site settings are avaible:
+| name | description | values | default |
+| --- | --- | --- | --- |
+| `agreeExpire` | number of months before users are shown the site agreement dialog again<br />set to 0 to display dialog on every reload | integer >= 0 | 3 |
+| `demo` | set to **true** to enable demo mode by default | boolean | false
+| `regions` | array of regions names to enable | thorax, abdomen, limbs, head | [thorax, abdomen, limbs, head] |
+| `useExternal` | detemines the ability to use an external detection server:<br />**none** - external server cannot be configured<br />**optional** - external server can be configured in the app's settings page<br />**list** - external server can be selected in the app's settings page but only the configured server(s) may be selected<br />**required** - external server settings from conf file will be used by default and disable server options in the settings page | none, optional, list, required | **optional** |
+| `external` | properties of the external server(s) ALVINN may connect to<br />This setting must be a single element array if **useExternal** is set to **required**.<br />This setting must be an array of one or more elements if **useExternal** is set to **list** | external server settings array | []|
+| `infoUrl` | root url for links to information about identified structures<br />Structure labels with spaces replaced by underscores will be appended to this value for full information links (*e.g.,* Abdominal_diapragm) | string | info link not shown |
+
+### External server settings
+ALVINN can use an external object detection server instead of the built in models; settings for that external server are configured here. These settings must be configured if **site - useExternal** is set to **list** or **required**.
+| name | description | default |
+| --- | --- | --- |
+| `name` | identifier for external server | *none* |
+| `address` | ip or url of external server | *none* |
+| `port` | port to access on external server | 9001 |
+
+The external server's response must be json with a `detections` key that contains an array of the detected structure labels, bounding box data, and confidence values.
+```
+{
+  "detections": [
+    {"top": 0.1, "left": 0.1, "bottom": 0.9, "right": 0.9, "label": "Aorta", "confidence": 90.0 }
+    ...
+  ],
+}
+```

cordova/config.xml

@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<widget id="edu.midwestern.alvinn" version="0.5.0-rc" xmlns="http://www.w3.org/ns/widgets" xmlns:cdv="http://cordova.apache.org/ns/1.0" xmlns:android="http://schemas.android.com/apk/res/android">
+<widget id="edu.midwestern.alvinn" version="0.5.0-alpha" xmlns="http://www.w3.org/ns/widgets" xmlns:cdv="http://cordova.apache.org/ns/1.0" xmlns:android="http://schemas.android.com/apk/res/android">
     <name>ALVINN</name>
     <description>Anatomy Lab Visual Identification Neural Network.</description>
     <author email="jgeorg@midwestern.edu" href="https://midwestern.edu">

cordova/package.json

@@ -1,7 +1,7 @@
 {
   "name": "edu.midwestern.alvinn",
   "displayName": "ALVINN",
-  "version": "0.5.0-rc",
+  "version": "0.5.0-alpha",
   "description": "Anatomy Lab Visual Identification Neural Network.",
   "main": "index.js",
   "scripts": {

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "alvinn",
-  "version": "0.4.0",
+  "version": "0.5.0-rc",
   "lockfileVersion": 2,
   "requires": true,
   "packages": {
     "": {
       "name": "alvinn",
-      "version": "0.4.0",
+      "version": "0.5.0-rc",
       "hasInstallScript": true,
       "license": "UNLICENSED",
       "dependencies": {
@@ -17,7 +17,8 @@
         "framework7-vue": "^8.3.0",
         "skeleton-elements": "^4.0.1",
         "swiper": "^11.0.3",
-        "vue": "^3.3.8"
+        "vue": "^3.3.8",
+        "yaml": "^2.4.1"
       },
       "devDependencies": {
         "@vitejs/plugin-vue": "^4.4.1",
@@ -9844,6 +9845,17 @@
       "integrity": "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==",
       "dev": true
     },
+    "node_modules/yaml": {
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.4.1.tgz",
+      "integrity": "sha512-pIXzoImaqmfOrL7teGUBt/T7ZDnyeGBWyXQBvOVhLkWLN37GXv8NMLK406UY6dS51JfcQHsmcW5cJ441bHg6Lg==",
+      "bin": {
+        "yaml": "bin.mjs"
+      },
+      "engines": {
+        "node": ">= 14"
+      }
+    },
     "node_modules/yargs": {
       "version": "16.2.0",
       "resolved": "https://registry.npmjs.org/yargs/-/yargs-16.2.0.tgz",
@@ -16397,6 +16409,11 @@
       "integrity": "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==",
       "dev": true
     },
+    "yaml": {
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.4.1.tgz",
+      "integrity": "sha512-pIXzoImaqmfOrL7teGUBt/T7ZDnyeGBWyXQBvOVhLkWLN37GXv8NMLK406UY6dS51JfcQHsmcW5cJ441bHg6Lg=="
+    },
     "yargs": {
       "version": "16.2.0",
       "resolved": "https://registry.npmjs.org/yargs/-/yargs-16.2.0.tgz",

package.json

@@ -1,7 +1,7 @@
 {
   "name": "alvinn",
   "private": true,
-  "version": "0.5.0-rc",
+  "version": "0.5.0-alpha",
   "description": "ALVINN",
   "repository": "",
   "license": "UNLICENSED",
@@ -14,7 +14,8 @@
     "cordova-ios": "cross-env TARGET=cordova cross-env NODE_ENV=production vite build && node ./build/build-cordova.js && cd cordova && cordova run ios",
     "build-cordova-android": "cross-env TARGET=cordova cross-env NODE_ENV=production vite build && node ./build/build-cordova.js && cd cordova && cordova build android",
     "cordova-android": "cross-env TARGET=cordova cross-env NODE_ENV=production vite build && node ./build/build-cordova.js && cd cordova && cordova run android",
-    "postinstall": "cpy --flat ./node_modules/framework7-icons/fonts/*.* ./src/fonts/"
+    "postinstall": "cpy --flat ./node_modules/framework7-icons/fonts/*.* ./src/fonts/",
+    "preview": "vite preview"
   },
   "browserslist": [
     "IOS >= 15",
@@ -30,7 +31,8 @@
     "framework7-vue": "^8.3.0",
     "skeleton-elements": "^4.0.1",
     "swiper": "^11.0.3",
-    "vue": "^3.3.8"
+    "vue": "^3.3.8",
+    "yaml": "^2.4.1"
   },
   "devDependencies": {
     "@vitejs/plugin-vue": "^4.4.1",

public/conf/conf.yaml

@@ -0,0 +1,16 @@
+demo: true
+agreeExpire: 3
+regions:
+  - thorax
+  - abdomen
+  - limbs
+  - head
+useExternal: none
+external:
+  - name: Mserver
+    address: "192.169.1.105"
+    port: 9001
+  - name: Georgi lab server
+    address: "10.188.0.98"
+    port: 9001
+infoUrl: http://anatlabwiki.midwestern.edu/vetlab/index.php/

public/models/abdomen-mini/descript.json

@@ -1,11 +1,10 @@
 {
-  "version": "0.0.0-n1",
+  "version": "0.1.0-n4",
-  "region": "Coco",
+  "region": "Thorax",
   "size": 640,
   "epochs": 1000,
-  "name": "coco128 test",
+  "name": "nano4",
   "yolo-version": "8.1.20 docker",
-  "date": "2024-03-12",
+  "date": "2024-03-08",
-  "export": "coco128.yaml"
+  "export": "0.1.0-th"
 }
-

public/models/abdomen-mini/metadata.yaml

@@ -1,7 +1,7 @@
-description: Ultralytics best model trained on /usr/src/ultralytics/ultralytics/cfg/datasets/coco128.yaml
+description: Ultralytics best model trained on /data/ALVINN/Thorax/Thorax 0.1.0/thorax.yaml
 author: Ultralytics
 license: AGPL-3.0 https://ultralytics.com/license
-date: '2024-03-12T16:25:00.089873'
+date: '2024-03-08T20:14:34.118186'
 version: 8.1.20
 stride: 32
 task: detect
@@ -10,83 +10,44 @@ imgsz:
 - 640
 - 640
 names:
-  0: person
+  0: Abdominal diaphragm
-  1: bicycle
+  1: Aorta
-  2: car
+  2: Azygous vein
-  3: motorcycle
+  3: Brachiocephalic trunk
-  4: airplane
+  4: Caudal vena cava
-  5: bus
+  5: Cranial vena cava
-  6: train
+  6: Esophagus
-  7: truck
+  7: External abdominal oblique
-  8: boat
+  8: Iliocostalis
-  9: traffic light
+  9: Latissimus dorsi
-  10: fire hydrant
+  10: Left atrium
-  11: stop sign
+  11: Left auricle
-  12: parking meter
+  12: Left lung
-  13: bench
+  13: Left subclavian artery
-  14: bird
+  14: Left ventricle
-  15: cat
+  15: Longissimus
-  16: dog
+  16: Pectoralis profundus
-  17: horse
+  17: Pectoralis superficialis
-  18: sheep
+  18: Pericardium
-  19: cow
+  19: Phrenic nerve
-  20: elephant
+  20: Primary bronchus
-  21: bear
+  21: Pulmonary artery
-  22: zebra
+  22: Pulmonary trunk
-  23: giraffe
+  23: Pulmonary vein
-  24: backpack
+  24: Rectus abdominis
-  25: umbrella
+  25: Rectus thoracis
-  26: handbag
+  26: Recurrent laryngeal nerve
-  27: tie
+  27: Rhomboideus
-  28: suitcase
+  28: Right atrium
-  29: frisbee
+  29: Right auricle
-  30: skis
+  30: Right lung
-  31: snowboard
+  31: Right ventricle
-  32: sports ball
+  32: Scalenus
-  33: kite
+  33: Serratus dorsalis caudalis
-  34: baseball bat
+  34: Serratus dorsalis cranialis
-  35: baseball glove
+  35: Serratus ventralis
-  36: skateboard
+  36: Spinalis
-  37: surfboard
+  37: Sympathetic chain
-  38: tennis racket
+  38: Trachea
-  39: bottle
+  39: Trapezius
-  40: wine glass
+  40: Vagus nerve
-  41: cup
-  42: fork
-  43: knife
-  44: spoon
-  45: bowl
-  46: banana
-  47: apple
-  48: sandwich
-  49: orange
-  50: broccoli
-  51: carrot
-  52: hot dog
-  53: pizza
-  54: donut
-  55: cake
-  56: chair
-  57: couch
-  58: potted plant
-  59: bed
-  60: dining table
-  61: toilet
-  62: tv
-  63: laptop
-  64: mouse
-  65: remote
-  66: keyboard
-  67: cell phone
-  68: microwave
-  69: oven
-  70: toaster
-  71: sink
-  72: refrigerator
-  73: book
-  74: clock
-  75: vase
-  76: scissors
-  77: teddy bear
-  78: hair drier
-  79: toothbrush

public/models/abdomen/classes.json

@@ -1,82 +1,43 @@
 [
-  "person",
+  "Abdominal diaphragm",
-  "bicycle",
+  "Aorta",
-  "car",
+  "Azygous vein",
-  "motorcycle",
+  "Brachiocephalic trunk",
-  "airplane",
+  "Caudal vena cava",
-  "bus",
+  "Cranial vena cava",
-  "train",
+  "Esophagus",
-  "truck",
+  "External abdominal oblique",
-  "boat",
+  "Iliocostalis",
-  "traffic light",
+  "Latissimus dorsi",
-  "fire hydrant",
+  "Left atrium",
-  "stop sign",
+  "Left auricle",
-  "parking meter",
+  "Left lung",
-  "bench",
+  "Left subclavian artery",
-  "bird",
+  "Left ventricle",
-  "cat",
+  "Longissimus",
-  "dog",
+  "Pectoralis profundus",
-  "horse",
+  "Pectoralis superficialis",
-  "sheep",
+  "Pericardium",
-  "cow",
+  "Phrenic nerve",
-  "elephant",
+  "Primary bronchus",
-  "bear",
+  "Pulmonary artery",
-  "zebra",
+  "Pulmonary trunk",
-  "giraffe",
+  "Pulmonary vein",
-  "backpack",
+  "Rectus abdominis",
-  "umbrella",
+  "Rectus thoracis",
-  "handbag",
+  "Recurrent laryngeal nerve",
-  "tie",
+  "Rhomboideus",
-  "suitcase",
+  "Right atrium",
-  "frisbee",
+  "Right auricle",
-  "skis",
+  "Right lung",
-  "snowboard",
+  "Right ventricle",
-  "sports ball",
+  "Scalenus",
-  "kite",
+  "Serratus dorsalis caudalis",
-  "baseball bat",
+  "Serratus dorsalis cranialis",
-  "baseball glove",
+  "Serratus ventralis",
-  "skateboard",
+  "Spinalis",
-  "surfboard",
+  "Sympathetic chain",
-  "tennis racket",
+  "Trachea",
-  "bottle",
+  "Trapezius",
-  "wine glass",
+  "Vagus nerve"
-  "cup",
-  "fork",
-  "knife",
-  "spoon",
-  "bowl",
-  "banana",
-  "apple",
-  "sandwich",
-  "orange",
-  "broccoli",
-  "carrot",
-  "hot dog",
-  "pizza",
-  "donut",
-  "cake",
-  "chair",
-  "couch",
-  "potted plant",
-  "bed",
-  "dining table",
-  "toilet",
-  "tv",
-  "laptop",
-  "mouse",
-  "remote",
-  "keyboard",
-  "cell phone",
-  "microwave",
-  "oven",
-  "toaster",
-  "sink",
-  "refrigerator",
-  "book",
-  "clock",
-  "vase",
-  "scissors",
-  "teddy bear",
-  "hair drier",
-  "toothbrush"
 ]

public/models/abdomen/descript.json

@@ -1,11 +1,10 @@
 {
-  "version": "0.0.0-n1",
+  "version": "0.1.0-n4",
-  "region": "Coco",
+  "region": "Thorax",
   "size": 640,
   "epochs": 1000,
-  "name": "coco128 test",
+  "name": "nano4",
   "yolo-version": "8.1.20 docker",
-  "date": "2024-03-12",
+  "date": "2024-03-08",
-  "export": "coco128.yaml"
+  "export": "0.1.0-th"
 }
-

public/models/abdomen/metadata.yaml

@@ -1,7 +1,7 @@
-description: Ultralytics best model trained on /usr/src/ultralytics/ultralytics/cfg/datasets/coco128.yaml
+description: Ultralytics best model trained on /data/ALVINN/Thorax/Thorax 0.1.0/thorax.yaml
 author: Ultralytics
 license: AGPL-3.0 https://ultralytics.com/license
-date: '2024-03-12T16:25:00.089873'
+date: '2024-03-08T20:14:34.118186'
 version: 8.1.20
 stride: 32
 task: detect
@@ -10,83 +10,44 @@ imgsz:
 - 640
 - 640
 names:
-  0: person
+  0: Abdominal diaphragm
-  1: bicycle
+  1: Aorta
-  2: car
+  2: Azygous vein
-  3: motorcycle
+  3: Brachiocephalic trunk
-  4: airplane
+  4: Caudal vena cava
-  5: bus
+  5: Cranial vena cava
-  6: train
+  6: Esophagus
-  7: truck
+  7: External abdominal oblique
-  8: boat
+  8: Iliocostalis
-  9: traffic light
+  9: Latissimus dorsi
-  10: fire hydrant
+  10: Left atrium
-  11: stop sign
+  11: Left auricle
-  12: parking meter
+  12: Left lung
-  13: bench
+  13: Left subclavian artery
-  14: bird
+  14: Left ventricle
-  15: cat
+  15: Longissimus
-  16: dog
+  16: Pectoralis profundus
-  17: horse
+  17: Pectoralis superficialis
-  18: sheep
+  18: Pericardium
-  19: cow
+  19: Phrenic nerve
-  20: elephant
+  20: Primary bronchus
-  21: bear
+  21: Pulmonary artery
-  22: zebra
+  22: Pulmonary trunk
-  23: giraffe
+  23: Pulmonary vein
-  24: backpack
+  24: Rectus abdominis
-  25: umbrella
+  25: Rectus thoracis
-  26: handbag
+  26: Recurrent laryngeal nerve
-  27: tie
+  27: Rhomboideus
-  28: suitcase
+  28: Right atrium
-  29: frisbee
+  29: Right auricle
-  30: skis
+  30: Right lung
-  31: snowboard
+  31: Right ventricle
-  32: sports ball
+  32: Scalenus
-  33: kite
+  33: Serratus dorsalis caudalis
-  34: baseball bat
+  34: Serratus dorsalis cranialis
-  35: baseball glove
+  35: Serratus ventralis
-  36: skateboard
+  36: Spinalis
-  37: surfboard
+  37: Sympathetic chain
-  38: tennis racket
+  38: Trachea
-  39: bottle
+  39: Trapezius
-  40: wine glass
+  40: Vagus nerve
-  41: cup
-  42: fork
-  43: knife
-  44: spoon
-  45: bowl
-  46: banana
-  47: apple
-  48: sandwich
-  49: orange
-  50: broccoli
-  51: carrot
-  52: hot dog
-  53: pizza
-  54: donut
-  55: cake
-  56: chair
-  57: couch
-  58: potted plant
-  59: bed
-  60: dining table
-  61: toilet
-  62: tv
-  63: laptop
-  64: mouse
-  65: remote
-  66: keyboard
-  67: cell phone
-  68: microwave
-  69: oven
-  70: toaster
-  71: sink
-  72: refrigerator
-  73: book
-  74: clock
-  75: vase
-  76: scissors
-  77: teddy bear
-  78: hair drier
-  79: toothbrush

public/models/head-mini/descript.json

@@ -0,0 +1,10 @@
+{
+  "version": "0.1.0-n4",
+  "region": "Thorax",
+  "size": 640,
+  "epochs": 1000,
+  "name": "nano4",
+  "yolo-version": "8.1.20 docker",
+  "date": "2024-03-08",
+  "export": "0.1.0-th"
+}

public/models/head-mini/metadata.yaml

@@ -0,0 +1,53 @@
+description: Ultralytics best model trained on /data/ALVINN/Thorax/Thorax 0.1.0/thorax.yaml
+author: Ultralytics
+license: AGPL-3.0 https://ultralytics.com/license
+date: '2024-03-08T20:14:34.118186'
+version: 8.1.20
+stride: 32
+task: detect
+batch: 1
+imgsz:
+- 640
+- 640
+names:
+  0: Abdominal diaphragm
+  1: Aorta
+  2: Azygous vein
+  3: Brachiocephalic trunk
+  4: Caudal vena cava
+  5: Cranial vena cava
+  6: Esophagus
+  7: External abdominal oblique
+  8: Iliocostalis
+  9: Latissimus dorsi
+  10: Left atrium
+  11: Left auricle
+  12: Left lung
+  13: Left subclavian artery
+  14: Left ventricle
+  15: Longissimus
+  16: Pectoralis profundus
+  17: Pectoralis superficialis
+  18: Pericardium
+  19: Phrenic nerve
+  20: Primary bronchus
+  21: Pulmonary artery
+  22: Pulmonary trunk
+  23: Pulmonary vein
+  24: Rectus abdominis
+  25: Rectus thoracis
+  26: Recurrent laryngeal nerve
+  27: Rhomboideus
+  28: Right atrium
+  29: Right auricle
+  30: Right lung
+  31: Right ventricle
+  32: Scalenus
+  33: Serratus dorsalis caudalis
+  34: Serratus dorsalis cranialis
+  35: Serratus ventralis
+  36: Spinalis
+  37: Sympathetic chain
+  38: Trachea
+  39: Trapezius
+  40: Vagus nerve

public/models/head/classes.json

@@ -0,0 +1,43 @@
+[
+  "Abdominal diaphragm",
+  "Aorta",
+  "Azygous vein",
+  "Brachiocephalic trunk",
+  "Caudal vena cava",
+  "Cranial vena cava",
+  "Esophagus",
+  "External abdominal oblique",
+  "Iliocostalis",
+  "Latissimus dorsi",
+  "Left atrium",
+  "Left auricle",
+  "Left lung",
+  "Left subclavian artery",
+  "Left ventricle",
+  "Longissimus",
+  "Pectoralis profundus",
+  "Pectoralis superficialis",
+  "Pericardium",
+  "Phrenic nerve",
+  "Primary bronchus",
+  "Pulmonary artery",
+  "Pulmonary trunk",
+  "Pulmonary vein",
+  "Rectus abdominis",
+  "Rectus thoracis",
+  "Recurrent laryngeal nerve",
+  "Rhomboideus",
+  "Right atrium",
+  "Right auricle",
+  "Right lung",
+  "Right ventricle",
+  "Scalenus",
+  "Serratus dorsalis caudalis",
+  "Serratus dorsalis cranialis",
+  "Serratus ventralis",
+  "Spinalis",
+  "Sympathetic chain",
+  "Trachea",
+  "Trapezius",
+  "Vagus nerve"
+]

public/models/head/descript.json

@@ -0,0 +1,12 @@
+{
+  "version": "0.3.1-s1",
+  "region": "Thorax",
+  "size": 960,
+  "epochs": 2000,
+  "epochsFinal:": 1656,
+  "name": "small1",
+  "yolo-version": "8.2.16 docker",
+  "date": "2024-06-05",
+  "export": "0.3.0-th",
+  "grayscale": true
+}

public/models/head/metadata.yaml

@@ -0,0 +1,53 @@
+description: Ultralytics best model trained on /data/ALVINN/Thorax/Thorax 0.3.0/thorax_g.yaml
+author: Ultralytics
+license: AGPL-3.0 https://ultralytics.com/license
+date: '2024-06-05T22:55:38.088791'
+version: 8.1.20
+stride: 32
+task: detect
+batch: 1
+imgsz:
+- 960
+- 960
+names:
+  0: Abdominal diaphragm
+  1: Aorta
+  2: Azygous vein
+  3: Brachiocephalic trunk
+  4: Caudal vena cava
+  5: Cranial vena cava
+  6: Esophagus
+  7: External abdominal oblique
+  8: Iliocostalis
+  9: Latissimus dorsi
+  10: Left atrium
+  11: Left auricle
+  12: Left lung
+  13: Left subclavian artery
+  14: Left ventricle
+  15: Longissimus
+  16: Pectoralis profundus
+  17: Pectoralis superficialis
+  18: Pericardium
+  19: Phrenic nerve
+  20: Primary bronchus
+  21: Pulmonary artery
+  22: Pulmonary trunk
+  23: Pulmonary vein
+  24: Rectus abdominis
+  25: Rectus thoracis
+  26: Recurrent laryngeal nerve
+  27: Rhomboideus
+  28: Right atrium
+  29: Right auricle
+  30: Right lung
+  31: Right ventricle
+  32: Scalenus
+  33: Serratus dorsalis caudalis
+  34: Serratus dorsalis cranialis
+  35: Serratus ventralis
+  36: Spinalis
+  37: Sympathetic chain
+  38: Trachea
+  39: Trapezius
+  40: Vagus nerve

public/models/thorax-mini/descript.json

@@ -1,10 +1,12 @@
 {
-  "version": "0.1.0-n4",
+  "version": "0.2.1-n3",
   "region": "Thorax",
   "size": 640,
-  "epochs": 1000,
+  "epochs": 1500,
-  "name": "nano4",
+  "name": "nano3",
-  "yolo-version": "8.1.20 docker",
+  "yolo-version": "8.2.16 docker",
-  "date": "2024-03-08",
+  "date": "2024-06-17",
-  "export": "0.1.0-th"
+  "export": "0.2.1-th",
-}
+  "grayscale": true,
+  "background": 35
+}

public/models/thorax-mini/metadata.yaml

@@ -1,8 +1,9 @@
-description: Ultralytics best model trained on /data/ALVINN/Thorax/Thorax 0.1.0/thorax.yaml
+description: Ultralytics best model trained on /data/ALVINN/Thorax 0.2.1/thorax_g.yaml
 author: Ultralytics
-license: AGPL-3.0 https://ultralytics.com/license
+date: '2024-06-17T22:40:05.967309'
-date: '2024-03-08T20:14:34.118186'
+version: 8.2.16
-version: 8.1.20
+license: AGPL-3.0 License (https://ultralytics.com/license)
+docs: https://docs.ultralytics.com
 stride: 32
 task: detect
 batch: 1

public/models/thorax/descript.json

@@ -1,10 +1,12 @@
 {
-  "version": "0.1.0-s1",
+  "version": "0.2.1-s1",
   "region": "Thorax",
-  "size": 640,
+  "size": 1080,
-  "epochs": 1000,
+  "epochs": 1399,
   "name": "small1",
-  "yolo-version": "8.1.20 docker",
+  "yolo-version": "8.2.16 docker",
-  "date": "2024-03-07",
+  "date": "2024-06-18",
-  "export": "0.1.0-th"
+  "export": "0.2.1-th",
+  "grayscale": true,
+  "background": 35
 }

public/models/thorax/metadata.yaml

@@ -1,14 +1,15 @@
-description: Ultralytics best model trained on /data/ALVINN/Thorax/Thorax 0.1.0/thorax.yaml
+description: Ultralytics best model trained on /data/ALVINN/Thorax 0.2.1/thorax_g.yaml
 author: Ultralytics
-license: AGPL-3.0 https://ultralytics.com/license
+date: '2024-06-18T23:10:47.568324'
-date: '2024-03-07T16:03:03.296997'
+version: 8.2.16
-version: 8.1.20
+license: AGPL-3.0 License (https://ultralytics.com/license)
+docs: https://docs.ultralytics.com
 stride: 32
 task: detect
 batch: 1
 imgsz:
-- 640
+- 1088
-- 640
+- 1088
 names:
   0: Abdominal diaphragm
   1: Aorta

src/assets/detect-worker.js

@@ -0,0 +1,176 @@
+import * as tf  from '@tensorflow/tfjs'
+
+let model = null
+
+onmessage = function (e) {
+  switch (e.data.call) {
+    case 'loadModel':
+      loadModel(e.data.weights,e.data.preload).then(() => {
+        postMessage({success: 'model'})
+      }).catch((err) => {
+        postMessage({error: true, message: err.message})
+      })
+      break
+    case 'localDetect':
+      localDetect(e.data.image).then((dets) => {
+        postMessage({success: 'detection', detections: dets})
+      }).catch((err) => {
+        //throw (err)
+        postMessage({error: true, message: err.message})
+      })
+      e.data.image.close()
+      break
+    case 'videoFrame':
+      videoFrame(e.data.image).then((frameDet) =>{
+        postMessage({succes: 'frame', coords: frameDet.cds, modelWidth: frameDet.mW, modelHeight: frameDet.mH})
+      }).catch((err) => {
+        postMessage({error: true, message: err.message})
+      })
+      e.data.image.close()
+      break
+    default:
+      console.log('Worker message incoming:')
+      console.log(e)
+      postMessage({result1: 'First result', result2: 'Second result'})
+      break
+  }
+}
+
+async function loadModel(weights, preload) {
+  if (model && model.modelURL == weights) {
+    return model
+  } else if (model) {
+    tf.dispose(model)
+  }
+  model = await tf.loadGraphModel(weights)
+  const [modelWidth, modelHeight] = model.inputs[0].shape.slice(1, 3)
+  /*****************
+   * If preloading then run model
+   * once on fake data to preload
+   * weights for a faster response
+   *****************/
+  if (preload) {
+    const dummyT = tf.ones([1,modelWidth,modelHeight,3])
+    model.predict(dummyT)
+  }
+  return model
+}
+
+async function localDetect(imageData) {
+  console.time('sw: pre-process')
+  const [modelWidth, modelHeight] = model.inputs[0].shape.slice(1, 3)
+  let gTense = null
+  const input = tf.tidy(() => {
+    gTense = tf.image.rgbToGrayscale(tf.image.resizeBilinear(tf.browser.fromPixels(imageData), [modelWidth, modelHeight])).div(255.0).expandDims(0)
+    return tf.concat([gTense,gTense,gTense],3)
+  })
+  tf.dispose(gTense)
+  console.timeEnd('sw: pre-process')
+
+  console.time('sw: run prediction')
+  const res = model.predict(input)
+  const tRes = tf.transpose(res,[0,2,1])
+  const rawRes = tRes.arraySync()[0]
+  console.timeEnd('sw: run prediction')
+
+  console.time('sw: post-process')
+  const outputSize = res.shape[1]
+  let rawBoxes = []
+  let rawScores = []
+
+  for (var i = 0; i < rawRes.length; i++) {
+    var getScores = rawRes[i].slice(4)
+    if (getScores.every( s => s < .05)) { continue }
+    var getBox = rawRes[i].slice(0,4)
+    var boxCalc = [
+      (getBox[0] - (getBox[2] / 2)) / modelWidth,
+      (getBox[1] - (getBox[3] / 2)) / modelHeight,
+      (getBox[0] + (getBox[2] / 2)) / modelWidth,
+      (getBox[1] + (getBox[3] / 2)) / modelHeight,
+    ]
+    rawBoxes.push(boxCalc)
+    rawScores.push(getScores)
+  }
+
+  if (rawBoxes.length > 0) {
+    const tBoxes = tf.tensor2d(rawBoxes)
+    let tScores = null
+    let resBoxes = null
+    let validBoxes = []
+    let structureScores = null
+    let boxes_data = []
+    let scores_data = []
+    let classes_data = []
+    for (var c = 0; c < outputSize - 4; c++) {
+      structureScores = rawScores.map(x => x[c])
+      tScores = tf.tensor1d(structureScores)
+      resBoxes = await tf.image.nonMaxSuppressionAsync(tBoxes,tScores,10,0.5,.05)
+      validBoxes = resBoxes.dataSync()
+      tf.dispose(resBoxes)
+      if (validBoxes) {
+        boxes_data.push(...rawBoxes.filter( (_, idx) => validBoxes.includes(idx)))
+        var outputScores = structureScores.filter( (_, idx) => validBoxes.includes(idx))
+        scores_data.push(...outputScores)
+        classes_data.push(...outputScores.fill(c))
+      }
+    }
+
+    validBoxes = []
+    tf.dispose(tBoxes)
+    tf.dispose(tScores)
+    tf.dispose(tRes)
+    const valid_detections_data = classes_data.length
+    var output = {
+      detections: []
+    }
+    for (var i =0; i < valid_detections_data; i++) {
+      var [dLeft, dTop, dRight, dBottom] = boxes_data[i]
+      output.detections.push({
+        "top": dTop,
+        "left": dLeft,
+        "bottom": dBottom,
+        "right": dRight,
+//        "label": this.detectorLabels[classes_data[i]].name,
+        "label": classes_data[i],
+        "confidence": scores_data[i] * 100
+      })
+    }
+  }
+  tf.dispose(res)
+  tf.dispose(input)
+  console.timeEnd('sw: post-process')
+
+  return output || { detections: [] }
+}
+
+async function videoFrame (vidData) {
+  const [modelWidth, modelHeight] = model.inputs[0].shape.slice(1, 3)
+  console.time('sw: frame-process')
+  let rawCoords = []
+  try {
+    const input = tf.tidy(() => {
+      return tf.image.resizeBilinear(tf.browser.fromPixels(vidData), [modelWidth, modelHeight]).div(255.0).expandDims(0)
+    })
+    const res = model.predict(input)
+    const rawRes = tf.transpose(res,[0,2,1]).arraySync()[0]
+
+    if (rawRes) {
+      for (var i = 0; i < rawRes.length; i++) {
+        let getScores = rawRes[i].slice(4) 
+        if (getScores.some( s => s > .5)) {
+          let foundTarget = rawRes[i].slice(0,2)
+          foundTarget.push(Math.max(...getScores))
+          rawCoords.push(foundTarget)
+        }
+      }
+
+    }
+    tf.dispose(input)
+    tf.dispose(res)
+    tf.dispose(rawRes)
+  } catch (e) {
+    console.log(e)
+  }
+  console.timeEnd('sw: frame-process')
+  return {cds: rawCoords, mW: modelWidth, mH: modelHeight}
+}

src/components/app.vue

@@ -33,7 +33,7 @@
           ALVINN is for educational purposes only. It may not be used for medical diagnosis, intervention, or treatment.
         </h3>
         <div style="display: flex; justify-content: space-around; flex-direction: row; align-items: center;">
-          <span style="height: min-content;">
+          <span v-if="!siteConf || !siteConf.agreeExpire == 0" style="height: min-content;">
             <f7-checkbox v-model:checked="rememberAgreement"/> Don't show again
           </span>
           <f7-button text="I agree" fill @click="setAgreement" />
@@ -52,13 +52,15 @@
 </style>
 
 <script>
-  import { ref, onMounted } from 'vue';
+  import { ref, onMounted } from 'vue'
-  import { f7, f7ready } from 'framework7-vue';
+  import { f7, f7ready } from 'framework7-vue'
-  import { getDevice }  from 'framework7/lite-bundle';
+  import { getDevice }  from 'framework7/lite-bundle'
-  import cordovaApp from '../js/cordova-app.js';
+  import cordovaApp from '../js/cordova-app.js'
 
-  import routes from '../js/routes.js';
+  import YAML from 'yaml'
-  import store from '../js/store';
+
+  import routes from '../js/routes.js'
+  import store from '../js/store'
 
   export default {
     data () {
@@ -66,27 +68,53 @@
         rememberAgreement: false,
         siteAgreement: false,
         dateAgreement: null,
-        showDisclaimer: true,
+        showDisclaimer: false,
-        alvinnVersion: store().getVersion
+        alvinnVersion: store().getVersion,
+        siteConf: {}
       }
     },
-    created () {
+    async created () {
-      var loadSiteSettings = localStorage.getItem('siteSettings')
+      if (!window.cordova) {
+        const confText = await fetch('./conf/conf.yaml')
+          .then((mod) => { return mod.text() })
+        this.siteConf = YAML.parse(confText)
+      }
+      if (window.safari !== undefined) {store().safariDetected()}
+      const loadSiteSettings = localStorage.getItem('siteSettings')
       if (loadSiteSettings) {
-        var loadedSettings = JSON.parse(loadSiteSettings)
+        let loadedSettings = JSON.parse(loadSiteSettings)
         this.siteAgreement = loadedSettings.siteAgreement
         this.rememberAgreement = loadedSettings.rememberAgreement
         this.dateAgreement = loadedSettings.dateAgreement && new Date(loadedSettings.dateAgreement)
       }
-      var curDate = new Date ()
+      const curDate = new Date ()
-      var agreeStillValid = this.dateAgreement && (curDate < this.dateAgreement.setMonth(this.dateAgreement.getMonth() + 3)) 
+      const expireMonth = (this.dateAgreement?.getMonth() || 0) + (this.siteConf?.agreeExpire || 3)
-      if (this.siteAgreement && this.rememberAgreement && agreeStillValid) {
+      const agreeStillValid = this.dateAgreement && (curDate < this.dateAgreement.setMonth(expireMonth))
-        this.showDisclaimer = false
+      if (this.siteAgreement && this.rememberAgreement && agreeStillValid && !this.siteConf?.agreeExpire == 0) {
         store().agree()
+      } else {
+        this.showDisclaimer = true        
       }
-      var loadServerSettings = localStorage.getItem('serverSettings')
+      store().set('enabledRegions',this.siteConf?.regions)
-      if (!loadServerSettings) {
+      store().set('siteDemo',this.siteConf?.demo)
+      store().set('infoUrl',this.siteConf?.infoUrl)
+      const loadServerSettings = localStorage.getItem('serverSettings')
+      if (this.siteConf?.useExternal) {
+        if (!['none','list','optional','required'].includes(this.siteConf.useExternal)) {
+          console.warn(`'${this.siteConf.useExternal}' is not a valid value for useExternal configuration: using 'optional'`)
+        } else {
+          store().set('useExternal',this.siteConf.useExternal)
+          if (this.siteConf.external) {
+            store().set('externalServerList',this.siteConf.external)
+          }
+        }
+      }
+      if (this.siteConf.useExternal == 'none') {
+        localStorage.setItem('serverSettings','{"use":false}')
+      } else if (!loadServerSettings && !this.siteConf.external) {
         localStorage.setItem('serverSettings','{"use":false,"address":"10.188.0.98","port":"9001","previous":{"10.188.0.98":"9001"}}')
+      } else if (this.siteConf.useExternal == 'required') {
+        localStorage.setItem('serverSettings',`{"use":true,"address":"${this.siteConf.external[0].address}","port":${this.siteConf.external[0].port}}`)
       }
     },
     methods: {
@@ -113,7 +141,7 @@
             this.showDisclaimer = false
           },
           () => {
-            var toast = f7.toast.create({
+            const toast = f7.toast.create({
               text: 'ERROR: No settings saved',
               closeTimeout: 2000
             })
@@ -125,13 +153,11 @@
     setup() {
       const device = getDevice();
       // Framework7 Parameters
-      var loadThemeSettings = localStorage.getItem('themeSettings')
+      const loadThemeSettings = localStorage.getItem('themeSettings')
-      if (loadThemeSettings) var themeSettings = JSON.parse(loadThemeSettings)
+      let themeSettings = {}
-      try {
+      let darkTheme = 'auto'
-        if (themeSettings.darkMode.toString()) var darkTheme = themeSettings.darkMode
+      if (loadThemeSettings) { themeSettings = JSON.parse(loadThemeSettings) }
-      } catch {
+      if (themeSettings?.darkMode) darkTheme = themeSettings.darkMode
-        var darkTheme = 'auto'
-      }
       const f7params = {
         name: 'ALVINN', // App name
         theme: 'auto', // Automatic theme detection

src/components/region-icon.vue

@@ -1,14 +1,25 @@
 <template>
-  <svg width="100%" height="100%" version="1.1" viewBox="0 0 26.458333 26.458333" xmlns="http://www.w3.org/2000/svg">
+  <svg width="100%" height="100%" version="1.1" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
-    <g stroke="none" :fill="fillColor" >
+    <g v-if="iconSet == 1" stroke="none" :fill="fillColor" >
-      <path d="m25.402178 7.8631343c-0.487907-0.3670601-0.811572-0.7261214-1.573424-1.106523-0.006122-0.1598737 0.053853-0.2411643-0.072374-0.5438299-0.239221-0.3572156-1.352454-0.987126-2.19723-0.8590224-1.567124 0.9252583-1.879175 1.9380345-3.311246 2.9148849-0.987966 0.103956-2.015535 0.3206455-3.091153 0.6741123-10.556415-1.8721062-8.2481554 5.9196998-14.460584 1.7189868 0 0-0.24989902 0.06545-0.28777276 0.170279-0.0360567 0.0998 0.10708587 0.299783 0.10708587 0.299783 2.0948939 1.933517 4.742145 1.74421 6.6624536-0.07316 0.096935 0.768305 0.3887649 1.92789 0.8180324 3.363404-0.035692 1.245357-1.2923422 2.350278-1.3169003 2.801484-0.013354 0.24535 0.5120291 3.6149 0.7015429 3.650219l0.7793046 0.145235c0.8989154 0.167526 0.7195768-0.420583 0.3224789-0.780361-0.2085791-0.188976-0.3404558-0.252396-0.3637846-0.441707-0.3810495-3.092169 2.1284358-4.423261 2.4023638-6.742929 2.453391 0.120243 3.974486 1.282365 6.721539 1.403033 0.136906 1.035362-0.177341 4.099457-0.120257 4.484465 0.04824 0.325337 0.511082 0.918401 0.497537 1.876854-3e-3 0.211416 0.410117 0.159484 0.619918 0.185743 0.799059 0.09999 1.033405-0.329373 0.42557-0.75884-0.132327-0.0935-0.456134-0.264276-0.476806-0.424973-0.251045-1.951541 1.103782-4.917365 1.103782-4.917365 0.355435-0.554509 0.707693-1.135262 1.002776-2.188396 0.160636-0.543413 0.157772-1.012576 0.119972-1.465872 1.541867-1.5721797 1.123352-2.3466703 2.548492-2.7336036 0.65786 0.059985 1.147615 0.1738285 1.444935 0.3493259 0.420933-0.188852 0.760222-0.5096057 0.993749-1.001227z" style="opacity: .25;"/>
+      <path d="M22,8.25 20.75,7.5 20.25,6.5 19,6 V5 L18.25,6 16,7.75 13.5,8.75 H8.5 L7,9 6,9.75 5,11 L4.25,12.5 3.5,14 2.5,15 2,15.5 2.5,15.75 3.5,15.5 4.5,14.25 5.5,12.25 6.75,10.75 7,12 7.25,13.25 6.5,15.5 7,19 H8 V 18.5 L7.5,18.25 7.75,15.75 9.75,12.25 12,13 15.25,13.5 15.5,17.25 16,19 H17 V18.5 L16.5,18.25 V15.5 L17,13 17.75,10.75 19,8.75 H20 L21.25,9 Z" style="opacity: .4;"/>
-      <path v-if="region == 0" d="m 18.247904,8.2686439 c -0.987966,0.103956 -3.091153,0.6741123 -3.091153,0.6741123 -1.652395,2.7995828 -2.226698,3.8098238 -2.580037,4.4476078 0,0 2.617397,0.984666 4.665796,1.066659 -0.003,0.01385 2.049744,0.445884 2.049744,0.445884 0,0 0.707693,-1.135262 1.002776,-2.188396 0.160636,-0.543413 0.157772,-1.012576 0.119972,-1.465872 -0.291029,-0.377705 -1.38593,-1.9038754 -2.167098,-2.9799951 z" fill-rule="evenodd" :fill="fillColor" />
+      <path v-if="region == 0" d="M16,7.75 13.5,8.75 12,13 15.25,13.5 17,13 17.75,10.75 Z" fill-rule="evenodd" :fill="fillColor" />
-      <path v-else-if="region ==1" d="m15.156751 8.9427562c-10.556415-1.8721062-8.2481554 5.9196998-14.460584 1.7189868 0 0-0.24989902 0.06545-0.28777276 0.170279-0.0360567 0.0998 0.10708587 0.299783 0.10708587 0.299783 2.0948939 1.933517 4.742145 1.74421 6.6624536-0.07316 0.048468 0.384152 0.1456587 0.866125 0.2843915 1.431499 0.7210773 0.130029 2.5390772 0.501293 3.0586462 0.563846 0.613348 0.03006 1.528237 0.20676 2.05877 0.334503 0.563462-1.044613 0.536275-0.982536 2.57701-4.4457368z" :fill="fillColor" fill-rule="evenodd"/>
+      <path v-else-if="region ==1" d="M13.5,8.75 H8.5 L7,9 6,9.75 5,11 4.25,12.5 3.5,14 2.5,15 2,15.5 2.5,15.75 3.5,15.5 4.5,14.25 5.5,12.25 6.75,10.75 7,12 9.75,12.25 12,13 Z" :fill="fillColor" fill-rule="evenodd"/>
-      <g v-else-if="region == 2" :fill="fillColor" fill-rule="evenodd">
+      <path v-else-if="region == 2" d="M15,8.5 C14,8.5 13.25,9.25 13.25,10.25 C13.25,10.75 13.5,11.25 13.75,11.5 L15.25,13.5 15.5,17.25 16,19 H17 V18.5 L16.5,18.25 V15.5 L17,13 17.75,10.75 16.25,9 C16,8.75 15.5,8.5 15,8.5 Z M8.5,9 C7.5,9 6.75,9.75 6.75,10.75 L7,12 7.25,13.25 6.5,15.5 7,19 H8 V18.5 L7.5,18.25 7.75,15.75 9.75,12.25 10.25,10.75 C10.25,9.75 9.5,9 8.5,9 Z" :fill="fillColor" fill-rule="evenodd"/>
-        <path d="m17.24251 14.457023c0.136906 1.035362-0.177341 4.099457-0.120257 4.484465 0.04824 0.325337 0.511082 0.918401 0.497537 1.876854-3e-3 0.211416 0.410117 0.159484 0.619918 0.185743 0.799059 0.09999 1.033405-0.329373 0.42557-0.75884-0.132327-0.0935-0.456134-0.264276-0.476806-0.424973-0.251045-1.951541 1.103782-4.917365 1.103782-4.917365 0.355435-0.554509 0.707693-1.135262 1.002776-2.188396 0.160636-0.543413 0.157772-1.012576 0.119972-1.465872-3.100189-4.8581326-4.866767-0.394712-3.172492 3.208384z" />
+      <path v-else-if="region == 3" d="M22,8.25 20.75,7.5 20.25,6.5 19,6 V5 L18.25,6 16,7.75 17.75,10.75 19,8.75 H20 L21.25,9 Z" :fill="fillColor" fill-rule="evenodd"/>
-        <path d="m7.1779333 11.058645c0.096935 0.768305 0.3887649 1.92789 0.8180324 3.363404-0.035692 1.245357-1.2923422 2.350278-1.3169003 2.801484-0.013354 0.24535 0.5120291 3.6149 0.7015429 3.650219l0.7793046 0.145235c0.8989154 0.167526 0.7195768-0.420583 0.3224789-0.780361-0.2085791-0.188976-0.3404558-0.252396-0.3637846-0.441707-0.3810495-3.092169 2.1284358-4.423261 2.4023638-6.742929 2.1562-5.4517681-2.8350883-3.4878487-3.3430377-1.995345z" />
+    </g>
-      </g>
+    <g v-else-if="iconSet == 2" stroke="none" :fill="fillColor" >
-      <path v-else-if="region == 3" d="m25.402178 7.8631343c-0.487907-0.3670601-0.811572-0.7261214-1.573424-1.106523-0.006122-0.1598737 0.053853-0.2411643-0.072374-0.5438299-0.239221-0.3572156-1.352454-0.987126-2.19723-0.8590224-1.567124 0.9252583-1.879175 1.9380345-3.311246 2.9148849 0.566485 0.8398567 1.254642 1.7575311 2.167098 2.9799951 1.541867-1.5721797 1.123352-2.3466703 2.548492-2.7336036 0.65786 0.059985 1.147615 0.1738285 1.444935 0.3493259 0.420933-0.188852 0.760222-0.5096057 0.993749-1.001227z" :fill="fillColor" fill-rule="evenodd"/>
+      <path d="M22,9.5 20.5,8.5 19.75,7.25 18.25,6.75 V 5 L 17,6.75 15,8.25 12,9.5 H 5.75 L 2.75,10 2,12 2.5,15.75 3.25,16 4,19 H 5.5 V 18.25 L 5,18 5.25,16.25 6,15.25 H 10 L 13.75,16 14.75,19 H 16.25 V 18.25 L 15.75,18 V 16 L 17,15.25 17.5,12 18.25,10.25 H 19.5 L 21,10.5 Z" style="opacity: .4;"/>
+      <path v-if="region == 0" d="M12,9.5 H 11 L 10,15.25 13.75,16 H 15.75 L 17,15.25 17.5,12 Z" fill-rule="evenodd" :fill="fillColor" />
+      <path v-else-if="region ==1" d="M 11,9.5 H 5.75 L 2.75,10 2,12 2.5,15.75 3.25,16 6,15.25 H 10 Z" :fill="fillColor" fill-rule="evenodd"/>
+      <path v-else-if="region == 2" d="M11.25,10.25 C 10.25,11.25 10.25,12.75 11.25,13.75 L 13.75,16 14.75,19 H 16.25 V 18.25 L 15.75,18 V 16 L 16,12 14.75,10.25 C 13.75,9.25 12.25,9.25 11.25,10.25 Z M 3,11 2,12 2.5,15.75 3.25,16 4,19 H 5.5 V 18.25 L 5,18 5.25,16.25 6,15.25 6.5,14.5 C 7.5,13.5 7.5,12 6.5,11 C 5.5,10 4,10 3,11 Z" :fill="fillColor" fill-rule="evenodd"/>
+      <path v-else-if="region == 3" d="M 22,9.5 20.5,8.5 19.75,7.25 18.25,6.75 V 5 L 17,6.75 15,8.25 12,9.5 17.5,12 18.25,10.25 H 19.5 L 21,10.5 Z" :fill="fillColor" fill-rule="evenodd"/>
+    </g>
+    <g v-else-if="iconSet == 3" stroke="none" :fill="fillColor" >
+      <path d="M22,6.25 L21,6 V5 L19.5,4.5 V3 L18.25,4.5 16,6.5 12.5,8 6,8.25 4,8.5 2.5,9.75 2,10.5 2.75,10.75 3.5,10.25 V11 L4,12.5 4.25,14 3.25,16.5 4,21 H5.25 V20.25 L4.75,20 5,16.75 7.75,13 10.5,14.5 15,15.25 15.25,18.75 16,21 H17.25 V20.25 L16.75,20 V16.5 L17.75,13.75 18.5,10.5 19.5,8.25 H20.5 L21.5,8.75 22,7.75 Z" style="opacity: .4;"/>
+      <path v-if="region == 0" d="M16,6.5 L12.5,8 10.5,14.5 15,15.25 17.75,13.75 18.5,10.5 Z" fill-rule="evenodd" :fill="fillColor" />
+      <path v-else-if="region ==1" d="M12.5,8 L6,8.25 4,8.5 2.5,9.75 2,10.5 2.75,10.75 3.5,10.25 V11 L4,12.5 7.75,13 10.5,14.5 Z" :fill="fillColor" fill-rule="evenodd"/>
+      <path v-else-if="region == 2" d="M12.75,8.25 C11.75,9.25 11.75,10.75 12.75,11.75 L15,15.25 15.25,18.75 16,21 H17.25 V20.25 L16.75,20 V16.5 L17.75,13.75 18.5,10.5 16.25,8.25 C15.25,7.25 13.75,7.25 12.75,8.25 Z M6,8.5 C4.75,8.5 3.5,9.75 3.5,11 L4,12.5 4.25,14 3.25,16.5 4,21 H5.25 V20.25 L4.75,20 5,16.75 7.75,13 8.5,11 C8.5,9.75 7.25,8.5 6,8.5 Z" :fill="fillColor" fill-rule="evenodd"/>
+      <path v-else-if="region == 3" d="M22,6.25 L21,6 V5 L19.5,4.5 V3 L18.25,4.5 L16,6.5 18.5,10.5 19.5,8.25 H20.5 L21.5,8.75 22,7.75 Z" :fill="fillColor" fill-rule="evenodd"/>
     </g>
   </svg>
 </template>
@@ -26,6 +37,13 @@
       fillColor: {
         type: String,
         default: "var(--avn-theme-color)"
+      },
+      iconSet: {
+        type: Number,
+        default: 1,
+        validator(value) {
+          return value >= 1 && value <= 3
+        }
       }
     }
   }

src/components/svg-icon.vue

@@ -16,6 +16,7 @@
     <path v-else-if="icon == 'limbs'" d="M540-440q17 0 28.5-11.5T580-480q0-7-1.5-12.5T574-503q11-4 18.5-14t7.5-23q0-17-11.5-28.5T560-580q-13 0-23 7t-14 19l-146-70q2-4 2.5-8t.5-8q0-17-11.5-28.5T340-680q-17 0-28.5 11.5T300-640q0 6 2 11.5t5 10.5q-11 4-19 14t-8 24q0 17 11.5 28.5T320-540q14 0 24-7.5t14-19.5l146 70-4 17q0 17 11.5 28.5T540-440ZM394-80q-16-47-24-92.5t-10-86q-2-40.5-.5-74.5t4.5-58q-1 0 0 0-22-5-50.5-12.5t-61-20.5Q220-437 186-455.5T119-500l50-70q39 35 81.5 55.5t78.5 32q36 11.5 60 15l24 3.5q18 1 28.5 15t7.5 32l-4.5 33.5q-4.5 33.5-5 83.5t7.5 109q8 59 33 111h-86Zm366 0h-80v-423q0-48-25.5-87T586-649L313-772l49-67 257 117q64 29 102.5 88T760-503v423Zm-280 0q-25-52-33-111t-7.5-109q.5-50 5-83.5L449-417q3-18-7.5-32T413-464l-24-3.5q-24-3.5-60-15t-78.5-32Q208-535 169-570q39 35 81.5 55.5t78.5 32q36 11.5 60 15l24 3.5q18 1 28.5 15t7.5 32l-4.5 33.5q-4.5 33.5-5 83.5t7.5 109q8 59 33 111Z"/>
     <path v-else-if="icon == 'head'" d="M194-80v-395h80v315h280v-193l105-105q29-29 45-65t16-77q0-40-16.5-76T659-741l-25-26-127 127H347l-43 43-57-56 67-67h160l160-160 82 82q40 40 62 90.5T800-600q0 57-22 107.5T716-402l-82 82v240H194Zm197-187L183-475q-11-11-17-26t-6-31q0-16 6-30.5t17-25.5l84-85 124 123q28 28 43.5 64.5T450-409q0 40-15 76.5T391-267Z"/>
     <path v-else-if="icon == 'photo_sample'" d="M240-80q-33 0-56.5-23.5T160-160v-640q0-33 23.5-56.5T240-880h480q33 0 56.5 23.5T800-800v640q0 33-23.5 56.5T720-80H240Zm0-80h480v-640h-80v280l-100-60-100 60v-280H240v640Zm40-80h400L545-420 440-280l-65-87-95 127Zm-40 80v-640 640Zm200-360 100-60 100 60-100-60-100 60Z"/>
+    <path v-else-if="icon == 'reset_slide'" d="M520-330v-60h160v60H520Zm60 210v-50h-60v-60h60v-50h60v160h-60Zm100-50v-60h160v60H680Zm40-110v-160h60v50h60v60h-60v50h-60Zm111-280h-83q-26-88-99-144t-169-56q-117 0-198.5 81.5T200-480q0 72 32.5 132t87.5 98v-110h80v240H160v-80h94q-62-50-98-122.5T120-480q0-75 28.5-140.5t77-114q48.5-48.5 114-77T480-840q129 0 226.5 79.5T831-560Z"/>
   </svg>
 </template>
   
@@ -42,7 +43,8 @@
             'abdomen',
             'limbs',
             'head',
-            'photo_sample'
+            'photo_sample',
+            'reset_slide'
           ]
           return iconList.includes(value)
         }

src/css/detect.css

@@ -43,6 +43,12 @@
   background: var(--chip-media-gradient) !important;
 }
 
+.chip-label {
+  pointer-events: none;
+  user-select: none;
+  -webkit-user-select: none;
+}
+
 .chip-results {
   display: flex;
   flex-wrap: wrap;
@@ -83,6 +89,26 @@
   display: none;
 }
 
+.level-slide-marker {
+  border: var(--avn-slide-marker-border);
+  position: absolute;
+  top: 0%;
+  height: 100%;
+  left: var(--avn-slide-marker-position);
+}
+
+.range-bar {
+  background: var(--avn-theme-color);
+}
+
+.range-bar-active {
+  background: rgba(255,255,255,.8);
+}
+
+.dark .range-bar-active {
+  background: rgba(0,0,0,.8);
+}
+
 .image-menu {
   grid-area: menu-view;
   margin: 5px;
@@ -121,6 +147,14 @@
   align-self: center;
 }
 
+.structure-info {
+  position: absolute;
+  z-index: 3;
+  color: rgb(15, 32, 108);
+  background: yellow;
+  border-radius: 100%;
+}
+
 /*Additional styles for small format landscape orientation*/
 @media (max-height: 450px) and (orientation: landscape) {
   .detect-grid {
@@ -156,6 +190,12 @@
     display: block;
   }
 
+  .level-slide-marker {
+    top: calc(100% - var(--avn-slide-marker-position));
+    height: auto;
+    width: 100%;
+    left: 0%;
+  }
 
   .image-container {
     flex-direction: column;

src/js/store.js

@@ -2,17 +2,63 @@ import { reactive, computed } from 'vue';
 
 const state = reactive({
     disclaimerAgreement: false,
-    enabledRegions: ['thorax','abdomen','limbs'],
+    enabledRegions: ['thorax','abdomen','limbs','head'],
-    version: '0.5.0-rc'
+    regionIconSet: Math.floor(Math.random() * 3) + 1,
+    version: '0.5.0-alpha',
+    fullscreen: false,
+    useExternal: 'optional',
+    siteDemo: false,
+    externalServerList: [],
+    infoUrl: false,
+    safariBrowser: false
   })
 
+const set = (config, confObj) => {
+  if (confObj === undefined) { return }
+  state[config] = confObj
+}
+
 const agree = () => {
   state.disclaimerAgreement = true
 }
 
+const safariDetected = () => {
+  state.safariBrowser = true
+}
+
+const getServerList = () => {
+  if (state.useExternal == 'required') {
+    return state.externalServerList[0]
+  } else {
+    return state.externalServerList
+  }
+}
+
+const toggleFullscreen = () => {
+  if (document.fullscreenElement) {
+    document.exitFullscreen().then( () => {
+      state.fullscreen = false
+    })
+  } else {
+    app.requestFullscreen().then( () => {
+      state.fullscreen = true
+    })
+  }
+}
+
 export default () => ({
   isAgreed: computed(() => state.disclaimerAgreement),
+  isFullscreen: computed(() => state.fullscreen),
+  demoMode: computed(() => state.siteDemo),
+  externalType: computed(() => state.useExternal),
   getRegions: computed(() => state.enabledRegions),
   getVersion: computed(() => state.version),
-  agree
+  getIconSet: computed(() => state.regionIconSet),
+  getInfoUrl: computed(() => state.infoUrl),
+  isSafari: computed(() => state.safariBrowser),
+  set,
+  agree,
+  safariDetected,
+  getServerList,
+  toggleFullscreen
 })

src/pages/camera-mixin.js

@@ -1,3 +1,5 @@
+import { f7 } from 'framework7-vue'
+
 export default {
   methods: {
     async openCamera(imContain) {
@@ -25,17 +27,67 @@ export default {
     },
     closeCamera () {
       this.cameraStream.getTracks().forEach( t => t.stop())
+      this.cameraStream = null
       this.videoAvailable = false
     },
     captureVidFrame() {
       const vidViewer = this.$refs.vid_viewer
       vidViewer.pause()
       let tempCVS = document.createElement('canvas')
+      tempCVS.id = 'temp-video-canvas'
       tempCVS.height = vidViewer.videoHeight || parseInt(vidViewer.style.height)
       tempCVS.width = vidViewer.videoWidth || parseInt(vidViewer.style.width)
       const tempCtx = tempCVS.getContext('2d')
       tempCtx.drawImage(vidViewer, 0, 0)
       this.getImage(tempCVS.toDataURL())
+    },
+    async videoFrameDetectWorker (vidData) {
+      const startDetection = () => {
+        createImageBitmap(vidData).then(imVideoFrame => {
+          this.vidWorker.postMessage({call: 'videoFrame', image: imVideoFrame}, [imVideoFrame])
+        })
+      }
+      vidData.addEventListener('resize',startDetection,{once: true})
+      this.vidWorker.onmessage = (eVid) => {
+        if (eVid.data.error) {
+          console.log(eVid.data.message)
+          f7.dialog.alert(`ALVINN AI model error: ${eVid.data.message}`)
+        } else if (this.videoAvailable) {
+          createImageBitmap(vidData).then(imVideoFrame => {
+            this.vidWorker.postMessage({call: 'videoFrame', image: imVideoFrame}, [imVideoFrame])
+          })
+          if (eVid.data.coords) {
+            imageCtx.clearRect(0,0,imCanvas.width,imCanvas.height)
+            for (var coord of eVid.data.coords) {
+              let pointX = (imCanvas.width - imgWidth) / 2 + (coord[0] / eVid.data.modelWidth) * imgWidth - 10
+              let pointY = (imCanvas.height - imgHeight) / 2 + (coord[1] / eVid.data.modelHeight) * imgHeight - 10
+              console.debug(`cx: ${pointX}, cy: ${pointY}`)
+              imageCtx.globalAlpha = coord[2]
+              imageCtx.drawImage(target, pointX, pointY, 20, 20)
+            }
+          }
+        }
+      }
+
+      const imCanvas = this.$refs.image_cvs
+      const imageCtx = imCanvas.getContext("2d")
+      const target = this.$refs.target_image
+      var imgWidth
+      var imgHeight
+      f7.utils.nextFrame(() => {
+        imCanvas.width = imCanvas.clientWidth
+        imCanvas.height = imCanvas.clientHeight
+        imageCtx.clearRect(0,0,imCanvas.width,imCanvas.height)
+        const imgAspect = vidData.width / vidData.height
+        const rendAspect = imCanvas.width / imCanvas.height
+        if (imgAspect >= rendAspect) {
+          imgWidth = imCanvas.width
+          imgHeight = imCanvas.width / imgAspect
+        } else {
+          imgWidth = imCanvas.height * imgAspect
+          imgHeight = imCanvas.height
+        }
+      })
     }
   }
 }

src/pages/detect.vue

@@ -10,16 +10,26 @@
     </f7-navbar>
     <f7-block class="detect-grid">
       <div class="image-container" ref="image_container">
-        <SvgIcon v-if="!imageView && !videoAvailable" :icon="f7route.params.region" fill-color="var(--avn-theme-color)" @click="selectImage" />
+        <SvgIcon v-if="!imageView.src && !videoAvailable" :icon="f7route.params.region" fill-color="var(--avn-theme-color)"/>
         <div class="vid-container" :style="`display: ${videoAvailable ? 'block' : 'none'}; position: absolute; width: 100%; height: 100%;`">
           <video id="vid-view" ref="vid_viewer" :srcObject="cameraStream" :autoPlay="true" style="width: 100%; height: 100%"></video>
           <f7-button @click="captureVidFrame()" style="position: absolute; bottom: 32px; left: 50%; transform: translateX(-50%); z-index: 3;" fill large>Capture</f7-button>
         </div>
         <canvas id="im-draw" ref="image_cvs" @click="structureClick" :style="`display: ${(imageLoaded || videoAvailable) ? 'block' : 'none'}; flex: 1 1 0%; max-width: 100%; max-height: 100%; min-width: 0; min-height: 0; background-size: contain; background-position: center; background-repeat: no-repeat; z-index: 2;`" />
+        <f7-link v-if="getInfoUrl && (selectedChip > -1)"
+          :style="`left: ${infoLinkPos.x}px; top: ${infoLinkPos.y}px; transform: translate(calc(-50% - ${infoLinkPos.adj}px),calc(-50% - ${infoLinkPos.adj}px));`"
+          class="structure-info"
+          :icon-only="true"
+          icon-f7="info"
+          target="_blank"
+          :external="true"
+          :href="infoLinkTarget"
+        />
       </div>
-      <div class="chip-results" style="grid-area: result-view; flex: 0 0 auto; align-self: center;">
+      <div class="chip-results" style="grid-area: result-view; flex: 0 0 auto; align-self: center; max-height: 450px;">
         <f7-chip v-for="result in showResults.filter( r => { return r.aboveThreshold && r.isSearched && !r.isDeleted })"
           :class="(result.resultIndex == selectedChip) ? 'selected-chip' : ''"
+          :id="(result.resultIndex == selectedChip) ? 'selected_chip' : ''"
           :text="result.label"
           media=" "
           :tooltip="result.confidence.toFixed(1)"
@@ -32,8 +42,17 @@
         <f7-progressbar v-if="(detecting || modelLoading)" style="width: 100%;" :infinite="true" />
       </div>
       <div v-if="showDetectSettings" class="detect-inputs" style="grid-area: detect-settings;">
-        <f7-range class="level-slide-horz" :min="0" :max="100" :step="1" @range:change="onLevelChange" v-model:value="detectorLevel" type="range" style="flex: 1 1 100%"/>
+        <f7-button @click="this.detectorLevel > 0 ? this.detectorLevel = 0 : this.detectorLevel = 50" style="flex: 0 1 20%">
-        <f7-range class="level-slide-vert" vertical :min="0" :max="100" :step="1" @range:change="onLevelChange" v-model:value="detectorLevel" type="range" style="flex: 1 1 100%"/>
+          <SvgIcon :icon="this.detectorLevel > 0 ? 'visibility' : 'reset_slide'"/>
+        </f7-button>
+        <div style="position: relative; flex: 1 1 100%">
+          <f7-range class="level-slide-horz" :min="0" :max="100" :step="1" @range:change="onLevelChange" v-model:value="detectorLevel" type="range"/>
+          <f7-range class="level-slide-vert" vertical :min="0" :max="100" :step="1" @range:change="onLevelChange" v-model:value="detectorLevel" type="range"/>
+          <div v-for="result in showResults.filter( r => { return r.isSearched && !r.isDeleted })"
+            class="level-slide-marker"
+            :style="`--avn-slide-marker-border: solid hsla(${result.confidence * 1.2}deg, 100%, 50%, .33) 1px; --avn-slide-marker-position: ${result.confidence.toFixed(1)}%`"
+          ></div>
+        </div>
         <f7-button @click="() => detectPanel = !detectPanel" :panel-open="!detectPanel && `#${detectorName}-settings`" :panel-close="detectPanel && `#${detectorName}-settings`" style="flex: 0 1 20%">
           <SvgIcon icon="check_list"/>
         </f7-button>
@@ -43,7 +62,7 @@
       </div>
       <f7-segmented class="image-menu" raised>
         <f7-button popover-open="#region-popover">
-          <RegionIcon :region="activeRegion" />
+          <RegionIcon :region="activeRegion" :iconSet="getIconSet" />
         </f7-button>
         <f7-button v-if="!videoAvailable" :class="(!modelLoading) ? '' : 'disabled'" popover-open="#capture-popover">
           <SvgIcon icon="camera_add"/>
@@ -77,16 +96,16 @@
     <f7-popover id="region-popover" class="popover-button-menu">
       <f7-segmented raised class="segment-button-menu">
         <f7-button :class="(getRegions.includes('thorax')) ? '' : ' disabled'" style="height: auto; width: auto;" href="/detect/thorax/" popover-close="#region-popover">
-          <RegionIcon :region="0" />
+          <RegionIcon :region="0" :iconSet="getIconSet" />
         </f7-button>
         <f7-button :class="(getRegions.includes('abdomen')) ? '' : ' disabled'" style="height: auto; width: auto;" href="/detect/abdomen/" popover-close="#region-popover">
-          <RegionIcon :region="1" />
+          <RegionIcon :region="1" :iconSet="getIconSet" />
         </f7-button>
         <f7-button :class="(getRegions.includes('limbs')) ? '' : ' disabled'" style="height: auto; width: auto;" href="/detect/limbs/" popover-close="#region-popover">
-          <RegionIcon :region="2" />
+          <RegionIcon :region="2" :iconSet="getIconSet" />
         </f7-button>
         <f7-button :class="(getRegions.includes('head')) ? '' : ' disabled'" style="height: auto; width: auto;" href="/detect/head/" popover-close="#region-popover">
-          <RegionIcon :region="3" />
+          <RegionIcon :region="3" :iconSet="getIconSet" />
         </f7-button>
       </f7-segmented>
     </f7-popover>
@@ -99,7 +118,7 @@
         <f7-button style="height: auto; width: auto;" popover-close="#capture-popover" @click="selectImage('file')">
           <SvgIcon icon="photo_library" />
         </f7-button>
-        <f7-button v-if="otherSettings.demo" style="height: auto; width: auto;" popover-close="#capture-popover" @click="selectImage('sample')">
+        <f7-button v-if="demoEnabled" style="height: auto; width: auto;" popover-close="#capture-popover" @click="selectImage('sample')">
           <SvgIcon icon="photo_sample"/>
         </f7-button>
       </f7-segmented>
@@ -121,6 +140,8 @@
   import detectionMixin from './detection-mixin'
   import cameraMixin from './camera-mixin'
 
+  import detectionWorker from '@/assets/detect-worker.js?worker&inline'
+
   export default {
     mixins: [submitMixin, detectionMixin, cameraMixin],
     props: {
@@ -138,7 +159,7 @@
         activeRegion: 4,
         classesList: [],
         imageLoaded: false,
-        imageView: null,
+        imageView: new Image(),
         imageLoadMode: "environment",
         detecting: false,
         detectPanel: false,
@@ -149,7 +170,6 @@
         serverSettings: {},
         otherSettings: {},
         isCordova: !!window.cordova,
-        isFullscreen: false,
         uploadUid: null,
         uploadDirty: false,
         modelLocation: '',
@@ -158,7 +178,10 @@
         reloadModel: false,
         videoDeviceAvailable: false,
         videoAvailable: false,
-        cameraStream: null
+        cameraStream: null,
+        infoLinkPos: {},
+        detectWorker: null,
+        vidWorker: null
       }
     },
     setup() {
@@ -167,7 +190,6 @@
     created () {
       let loadOtherSettings = localStorage.getItem('otherSettings')
       if (loadOtherSettings) this.otherSettings = JSON.parse(loadOtherSettings)
-      let modelRoot = this.isCordova ? 'https://localhost' : '.'
       this.detectorName = this.f7route.params.region
       switch (this.detectorName) {
         case 'thorax':
@@ -183,9 +205,9 @@
           this.activeRegion = 3
           break;
       }
-      this.modelLocation = `${modelRoot}/models/${this.detectorName}${this.otherSettings.mini ? '-mini' : ''}/model.json`
+      this.modelLocation = URL.parse(`../models/${this.detectorName}${this.otherSettings.mini ? '-mini' : ''}/model.json`,import.meta.url).href
-      this.miniLocation = `${modelRoot}/models/${this.detectorName}-mini/model.json`
+      this.miniLocation = URL.parse(`../models/${this.detectorName}-mini/model.json`,import.meta.url).href
-      fetch(`${this.isCordova ? 'https://localhost' : '.'}/models/${this.detectorName}/classes.json`)
+      fetch(URL.parse(`../models/${this.detectorName}/classes.json`,import.meta.url).href)
         .then((mod) => { return mod.json() })
         .then((classes) => {
           this.classesList = classes
@@ -195,20 +217,43 @@
       if (loadServerSettings) this.serverSettings = JSON.parse(loadServerSettings)
     },
     mounted () {
+      this.detectWorker = new detectionWorker()
+      this.detectWorker.onmessage = (eMount) => {
+        self = this
+        if (eMount.data.error) {
+          console.log(eMount.data.message)
+          f7.dialog.alert(`ALVINN AI model error: ${eMount.data.message}`)
+        }
+        self.modelLoading = false
+      }
+      this.vidWorker = new detectionWorker()
+      this.vidWorker.onmessage = (eMount) => {
+        self = this
+        if (eMount.data.error) {
+          console.log(eMount.data.message)
+          f7.dialog.alert(`ALVINN AI nano model error: ${eMount.data.message}`)
+        }
+      }
+
       if (this.serverSettings && this.serverSettings.use) {
         this.getRemoteLabels()
         this.modelLoading = false
       } else {
         this.modelLoading = true
-        this.loadModel(this.modelLocation, true).then(() => {
+        if (this.isSafari) {
-          this.modelLoading = false
+          this.loadModel(this.modelLocation, true).then(() => {
-        }).catch((e) => {
+            this.modelLoading = false
-          console.log(e.message)
+          }).catch((e) => {
-          f7.dialog.alert(`ALVINN AI model error: ${e.message}`)
+            console.log(e.message)
-          this.modelLoading = false
+            f7.dialog.alert(`ALVINN AI model error: ${e.message}`)
-        })
+            this.modelLoading = false
+          })
+        } else {
+          this.detectWorker.postMessage({call: 'loadModel', weights: this.modelLocation, preload: true})
+          this.vidWorker.postMessage({call: 'loadModel', weights: this.miniLocation, preload: true})
+        }
       }
-      window.onresize = (e) => { this.selectChip('redraw') }
+      window.onresize = (e) => { if (this.$refs.image_cvs) this.selectChip('redraw') }
     },
     computed: {
       message () {
@@ -252,6 +297,14 @@
         } else {
           return false
         }
+      },
+      demoEnabled () {
+        return this.otherSettings.demo || this.demoMode
+      },
+      infoLinkTarget () {
+        if (!this.getInfoUrl) return ''
+        let structure = this.showResults.find( r => r.resultIndex == this.selectedChip)
+        return structure ? this.getInfoUrl + structure.label.replaceAll(' ','_') : ''
       }
     },
     methods: {
@@ -260,12 +313,50 @@
         return `--chip-media-gradient: conic-gradient(from ${270 - (confFactor * 360 / 2)}deg, hsl(${confFactor * 120}deg, 100%, 50%) ${confFactor}turn, hsl(${confFactor * 120}deg, 50%, 66%) ${confFactor}turn)`
       },
       async setData () {
-        if (this.reloadModel) {
+        this.detectWorker.onmessage = (eDetect) => {
-          await this.loadModel(this.modelLocation)
+          self = this
-          this.reloadModel = false
+          if (eDetect.data.error) {
+            self.detecting = false
+            self.resultData = {}
+            loadFailure()
+            f7.dialog.alert(`ALVINN structure finding error: ${eDetect.data.message}`)
+          } else if (eDetect.data.success == 'detection') {
+            self.detecting = false
+            self.resultData = eDetect.data.detections
+            if (self.resultData) {
+              self.resultData.detections.map(d => {d.label = self.detectorLabels[d.label].name})
+            }
+            self.uploadDirty = true
+          } else if (eDetect.data.success == 'model') {
+            self.reloadModel = false
+            loadSuccess()
+          }
         }
+
+        let loadSuccess = null
+        let loadFailure = null
+        let modelReloading = null
+        if (this.isSafari && this.reloadModel) {
+          await this.loadModel(this.modelLocation)
+          this.reloadModel = false          
+        } else {
+          modelReloading = new Promise((res, rej) => {
+            loadSuccess = res
+            loadFailure = rej
+            if (this.reloadModel) {
+              this.detectWorker.postMessage({call: 'loadModel', weights: this.modelLocation})
+            } else {
+              loadSuccess()
+            }
+          })
+        }
+
         if (this.serverSettings && this.serverSettings.use) {
           this.remoteDetect()
+        } else if (!this.isSafari) {
+          Promise.all([modelReloading,createImageBitmap(this.imageView)]).then(res => {
+            this.detectWorker.postMessage({call: 'localDetect', image: res[1]}, [res[1]])
+          })
         } else {
           this.localDetect(this.imageView).then(dets => {
             this.detecting = false
@@ -292,19 +383,22 @@
           navigator.camera.getPicture(this.getImage, this.onFail, { quality: 50, destinationType: Camera.DestinationType.DATA_URL, correctOrientation: true });
           return
         }
-        if (mode == "camera") {
+        if (mode == "camera" && !this.otherSettings.disableVideo) {
           this.videoAvailable = await this.openCamera(this.$refs.image_container)
           if (this.videoAvailable) {
+            this.selectedChip = -1
             this.imageLoaded = false
-            this.imageView = null
+            this.imageView.src = null
             this.$refs.image_cvs.style['background-image'] = 'none'
             this.resultData = {}
             var trackDetails = this.cameraStream.getVideoTracks()[0].getSettings()
             var vidElement = this.$refs.vid_viewer
             vidElement.width = trackDetails.width
             vidElement.height = trackDetails.height
-            if (!this.otherSettings.disableVideo) {
+            if (this.isSafari) {
               this.videoFrameDetect(vidElement)
+            } else {
+              this.videoFrameDetectWorker(vidElement)
             }
             return
           }
@@ -342,13 +436,22 @@
 
         const boxCoords = this.box2cvs(this.resultData.detections[iChip])[0]
 
-        var boxLeft = boxCoords.cvsLeft
+        let boxLeft = boxCoords.cvsLeft
-        var boxTop = boxCoords.cvsTop
+        let boxTop = boxCoords.cvsTop
-        var boxWidth = boxCoords.cvsRight - boxCoords.cvsLeft
+        let boxWidth = boxCoords.cvsRight - boxCoords.cvsLeft
-        var boxHeight = boxCoords.cvsBottom - boxCoords.cvsTop
+        let boxHeight = boxCoords.cvsBottom - boxCoords.cvsTop
-        imageCtx.strokeRect(boxLeft,boxTop,boxWidth,boxHeight)
+        this.infoLinkPos.x = boxCoords.cvsLeft
+        this.infoLinkPos.y = boxCoords.cvsTop
+        let boxMin = Math.min(boxHeight, boxWidth)
+        this.infoLinkPos.adj = (boxMin >= 50) ? 0 : Math.min(10, 50 - boxMin)
+
+        imageCtx.strokeRect(boxLeft, boxTop, boxWidth, boxHeight)
         this.selectedChip = iChip
         this.resultData.detections[iChip].beenViewed = true
+
+        this.$nextTick( () => {
+          document.getElementById('selected_chip').scrollIntoView({behavior: 'smooth', block: 'nearest'})
+        })
       },
       deleteChip ( iChip ) {
         f7.dialog.confirm(`${this.resultData.detections[iChip].label} is identified with ${this.resultData.detections[iChip].confidence.toFixed(1)}% confidence. Are you sure you want to delete it?`, () => {
@@ -364,6 +467,7 @@
         imCanvas.width = imCanvas.clientWidth
         imCanvas.height = imCanvas.clientHeight
         imageCtx.clearRect(0,0,imCanvas.width,imCanvas.height)
+        imageCtx.globalAlpha = 1
         imageCtx.strokeStyle = 'yellow'
         imageCtx.lineWidth = 3
         return [imCanvas, imageCtx]
@@ -379,11 +483,11 @@
             this.detecting = true
             resolve('data:image/jpg;base64,' + searchImage)
           }
-          var reader = new FileReader()
+          const reader = new FileReader()
           reader.addEventListener("load", () => {
             this.detecting = true
             resolve(reader.result)
-          })
+          },{once: true})
           if (this.imageLoadMode == 'sample') {
             fetch(`${this.isCordova ? 'https://localhost' : '.'}/samples/${this.detectorName}-${searchImage}.jpeg`).then( resp => {
               return resp.blob()
@@ -403,19 +507,14 @@
           this.imageLoaded = true
           this.resultData = {}
           this.selectedChip = -1
-          this.imageView = new Image()
           this.imageView.src = imgData
           return(this.imageView.decode())
         }).then( () => {
           const [imCanvas, _]  = this.resetView()
           imCanvas.style['background-image'] = `url(${this.imageView.src})`
-          /******
+          f7.utils.nextFrame(() => {
-           * setTimeout is not a good solution, but it's the only way
-           * I can find to not cut off drawing of the canvas background
-           ******/
-          setTimeout(() => {
             this.setData()
-          }, 1)
+          })
         }).catch((e) => {
           console.log(e.message)
           f7.dialog.alert(`Error loading image: ${e.message}`)
@@ -468,17 +567,6 @@
           }
         })
         return cvsCoords
-      },
-      toggleFullscreen() {
-        if (document.fullscreenElement) {
-          document.exitFullscreen().then( () => {
-            this.isFullscreen = false
-          })
-        } else {
-          app.requestFullscreen().then( () => {
-            this.isFullscreen = true
-          })
-        }
       }
     }
   }

src/pages/detection-mixin.js

@@ -1,7 +1,7 @@
 import * as tf  from '@tensorflow/tfjs'
 import { f7 } from 'framework7-vue'
 
-var model = null
+let model = null
 
 export default {
   methods: {
@@ -9,7 +9,7 @@ export default {
       if (model && model.modelURL == weights) {
         return model
       } else if (model) {
-        model.dispose()
+        tf.dispose(model)
       }
       model = await tf.loadGraphModel(weights)
       const [modelWidth, modelHeight] = model.inputs[0].shape.slice(1, 3)
@@ -25,19 +25,23 @@ export default {
       return model
     },
     async localDetect(imageData) {
-      console.time('pre-process')
+      console.time('mx: pre-process')
       const [modelWidth, modelHeight] = model.inputs[0].shape.slice(1, 3)
+      let gTense = null
       const input = tf.tidy(() => {
-        return tf.image.resizeBilinear(tf.browser.fromPixels(imageData), [modelWidth, modelHeight]).div(255.0).expandDims(0)
+        gTense = tf.image.rgbToGrayscale(tf.image.resizeBilinear(tf.browser.fromPixels(imageData), [modelWidth, modelHeight])).div(255.0).expandDims(0)
+        return tf.concat([gTense,gTense,gTense],3)
       })
-      console.timeEnd('pre-process')
+      tf.dispose(gTense)
+      console.timeEnd('mx: pre-process')
 
-      console.time('run prediction')
+      console.time('mx: run prediction')
       const res = model.predict(input)
-      const rawRes = tf.transpose(res,[0,2,1]).arraySync()[0]
+      const tRes = tf.transpose(res,[0,2,1])
-      console.timeEnd('run prediction')
+      const rawRes = tRes.arraySync()[0]
+      console.timeEnd('mx: run prediction')
 
-      console.time('post-process')
+      console.time('mx: post-process')
       const outputSize = res.shape[1]
       let rawBoxes = []
       let rawScores = []
@@ -59,6 +63,8 @@ export default {
       if (rawBoxes.length > 0) {
         const tBoxes = tf.tensor2d(rawBoxes)
         let tScores = null
+        let resBoxes = null
+        let validBoxes = []
         let structureScores = null
         let boxes_data = []
         let scores_data = []
@@ -66,8 +72,9 @@ export default {
         for (var c = 0; c < outputSize - 4; c++) {
           structureScores = rawScores.map(x => x[c])
           tScores = tf.tensor1d(structureScores)
-          var validBoxes = await tf.image.nonMaxSuppressionAsync(tBoxes,tScores,10,0.5,.05)
+          resBoxes = await tf.image.nonMaxSuppressionAsync(tBoxes,tScores,10,0.5,.05)
-          validBoxes = validBoxes.dataSync()
+          validBoxes = resBoxes.dataSync()
+          tf.dispose(resBoxes)
           if (validBoxes) {
             boxes_data.push(...rawBoxes.filter( (_, idx) => validBoxes.includes(idx)))
             var outputScores = structureScores.filter( (_, idx) => validBoxes.includes(idx))
@@ -76,8 +83,10 @@ export default {
           }
         }
 
+        validBoxes = []
         tf.dispose(tBoxes)
         tf.dispose(tScores)
+        tf.dispose(tRes)
         const valid_detections_data = classes_data.length
         var output = {
           detections: []
@@ -96,7 +105,7 @@ export default {
       }
       tf.dispose(res)
       tf.dispose(input)
-      console.timeEnd('post-process')
+      console.timeEnd('mx: post-process')
 
       return output || { detections: [] }
     },
@@ -185,7 +194,7 @@ export default {
         imgHeight = imCanvas.height
       }
       while (this.videoAvailable) {
-        console.time('frame-process')
+        console.time('mx: frame-process')
         try {
           const input = tf.tidy(() => {
             return tf.image.resizeBilinear(tf.browser.fromPixels(vidData), [modelWidth, modelHeight]).div(255.0).expandDims(0)
@@ -196,9 +205,11 @@ export default {
           let rawCoords = []
           if (rawRes) {
             for (var i = 0; i < rawRes.length; i++) {
-              var getScores = rawRes[i].slice(4)
+              let getScores = rawRes[i].slice(4) 
               if (getScores.some( s => s > .5)) {
-                rawCoords.push(rawRes[i].slice(0,2))
+                let foundTarget = rawRes[i].slice(0,2)
+                foundTarget.push(Math.max(...getScores))
+                rawCoords.push(foundTarget)
               }
             }
 
@@ -207,13 +218,17 @@ export default {
               console.log(`x: ${coord[0]}, y: ${coord[1]}`)
               let pointX = (imCanvas.width - imgWidth) / 2 + (coord[0] / modelWidth) * imgWidth -5
               let pointY = (imCanvas.height - imgHeight) / 2 + (coord[1] / modelHeight) * imgHeight -5
+              imageCtx.globalAlpha = coord[2]
               imageCtx.drawImage(target, pointX, pointY, 20, 20)
             }
           }
+          tf.dispose(input)
+          tf.dispose(res)
+          tf.dispose(rawRes)
         } catch (e) {
           console.log(e)
         }
-        console.timeEnd('frame-process')
+        console.timeEnd('mx: frame-process')
         await tf.nextFrame();
       }
     }

src/pages/help.vue

@@ -4,7 +4,14 @@
     <f7-block>
       <h2>Quick Start</h2>
       <ol>
-        <li>Select the region of the body you want to identify structures from.</li>
+        <li>Select the region of the body you want to identify structures from. The regions are:
+          <ul>
+            <li><RegionIcon :region="0" class="list-region"/>Thorax and back</li>
+            <li><RegionIcon :region="1" class="list-region"/>Abdomen and pelvis</li>
+            <li><RegionIcon :region="2" class="list-region"/>Limbs</li>
+            <li><RegionIcon :region="3" class="list-region"/>Head and neck</li>
+          </ul>
+        </li>
         <li>Load an image:
           <ul>
             <li>Click on the camera icon <SvgIcon icon="photo_camera" class="list-svg"/> to take a new picture.
@@ -18,29 +25,32 @@
           </ul>
         </li>
         <li>When the picture is captured or loaded, any identifiable structures will be listed as tags below the image:
-          <f7-chip text="Structure name" media=" " class="demo-chip"/>
+          <f7-chip text="Structure name" media=" " class="demo-chip" deleteable/>
           <ul>
-            <li>Click on each tag to see the structure highlighted in the image.</li>
+            <li>Click on each tag to see the structure highlighted in the image or click on the image to see the tag for that structure (additional clicks to the same area will select overlapping structres).</li>
             <li>Tag color and proportion filled indicate ALVINN's level of confidence in the identification.</li>
-            <li>If there are potential structures that do not satisfy the current detection threshold, a badge on the detection menu icon <SvgIcon icon="visibility" class="list-svg"/> will indicate the number of un-displayed structures.</li>
+            <li>An incorrect tag can be deleted by clicking on the tag's <f7-icon icon="chip-delete" style="margin-right: 1px;"></f7-icon> button.</li>
           </ul>
         </li>
       </ol>
     <h2>Advanced Features</h2>
     <h3>Detection Parameters</h3>
       <p>
-        After an image has been loaded and structure detection has been performed, the detection parameters can be adjusted using the detection menu icon <SvgIcon icon="visibility" class="list-svg"/>.
+        If there are potential structures that do not satisfy the current detection settings, a badge on the detection menu icon <SvgIcon icon="visibility" class="list-svg"/> will indicate the number of un-displayed structures.
+        Clicking on the detection menu icon will open a menu of tools to adjust the detection settings.
         This button will make three tools available:
       </p>
       <ol>
-        <li>Confidence slider: You can use the slider to change the confidence threshold for identifying structures. The default threshold is 50% confidence.</li>
+        <li>Confidence filter <SvgIcon icon="visibility" class="list-svg"/> or <SvgIcon icon="reset_slide" class="list-svg"/>: You can press this button to show all structures or return the confidence slider to the default value (50%).</li>
-        <li>Refresh detections <SvgIcon icon="refresh_search" class="list-svg"/>: If there has been a permanent change to the structures detections, such as deleting a tag, the detection list can be reset to its original state.</li>
+        <li>Confidence slider: You can use the slider to change the confidence threshold for identifying structures.</li>
+        <li>Refresh detections <SvgIcon icon="refresh_search" class="list-svg"/>: If there has been a permanent change to the structure detection list, such as deleting a tag, the detection list can be reset to its original state.</li>
         <li>Structure list <SvgIcon icon="check_list" class="list-svg"/>: you can view a list of all the structures available for detection in that region and select/deselect individual structures for detection.</li>
       </ol>
     <h3>Submitting Images</h3>
       <p>
-        If all of the detection tags that are currently visible have been viewed, then the cloud upload button <SvgIcon icon="cloud_upload" class="list-svg"/> on the detection menu will be enabled.
+        If all of the detection tags that are currently visible have been clicked on and viewed, then the cloud upload button <SvgIcon icon="cloud_upload" class="list-svg"/> on the detection menu will be enabled.
-        This button will cause the image and the verified structures to be uploaded to the ALVINN project servers where that data will be available for further training of the neural net. If after the image has been uploaded, the available detection tags change, then the option to re-upload the image will be available if all the new tags have been viewed and verified.
+        This button will cause the image and the verified structures to be uploaded to the ALVINN project servers where that data will become available for further training of the neural net.
+        If after the image has been uploaded, the available detection tags are changed via deletion or the detection settings options, then the option to re-upload the image will be available if all the new tags have been viewed and verified.
       </p>
     </f7-block>
   </f7-page>
@@ -57,6 +67,13 @@
     top: .5em;
   }
 
+  .list-region {
+    width: 3em;
+    position:relative;
+    top: 1em;
+    margin-right: .5em;
+  }
+
   .cap-button {
     background-color: var(--f7-theme-color);
     color: white;
@@ -80,10 +97,12 @@
 
 <script>
   import SvgIcon from '../components/svg-icon.vue'
+  import RegionIcon from '../components/region-icon.vue'
 
   export default {
     components: {
-      SvgIcon
+      SvgIcon,
+      RegionIcon
     }
   }
 </script>

src/pages/home.vue

@@ -6,6 +6,10 @@
         <f7-link icon-ios="f7:bars" icon-md="f7:bars" panel-open="left"></f7-link>
       </f7-nav-left>
       <f7-nav-title sliding>A.L.V.I.N.N.</f7-nav-title>
+      <f7-nav-right>
+        <f7-link v-if="!isCordova" :icon-only="true" tooltip="Fullscreen" :icon-f7="isFullscreen ? 'viewfinder_circle_fill' : 'viewfinder'" @click="toggleFullscreen"></f7-link>
+        <f7-link :icon-only="true" tooltip="ALVINN help" icon-f7="question_circle_fill" href="/help/"></f7-link>
+      </f7-nav-right>
     </f7-navbar>
     <!-- Page content-->
     <div style="display: grid; grid-template-columns: 100%; grid-template-rows: min-content min-content min-content 1fr; align-content: stretch; gap: 15px; min-height: 0px; max-height: calc(100vh - (var(--f7-navbar-height) + var(--f7-safe-area-top))); height: calc(100vh - (var(--f7-navbar-height) + var(--f7-safe-area-top)));">
@@ -20,16 +24,16 @@
       <p style="text-align: center; margin: 0;">Select a region to begin.</p>
       <div class="region-grid">
         <f7-button :class="`region-button thorax${isAgreed && getRegions.includes('thorax') ? '' : ' disabled'}`" :href="isAgreed && getRegions.includes('thorax') && '/detect/thorax/'">
-          <RegionIcon class="region-image" :region="0" />
+          <RegionIcon class="region-image" :region="0" :iconSet="getIconSet" />
         </f7-button>
         <f7-button :class="`region-button abdomen${isAgreed && getRegions.includes('abdomen') ? '' : ' disabled'}`" :href="isAgreed && getRegions.includes('abdomen') && '/detect/abdomen/'">
-          <RegionIcon class="region-image" :region="1" />
+          <RegionIcon class="region-image" :region="1" :iconSet="getIconSet" />
         </f7-button>
         <f7-button :class="`region-button limbs${isAgreed && getRegions.includes('limbs') ? '' : ' disabled'}`" :href="isAgreed && getRegions.includes('limbs') && '/detect/limbs/'">
-          <RegionIcon class="region-image" :region="2" />
+          <RegionIcon class="region-image" :region="2" :iconSet="getIconSet" />
         </f7-button>
         <f7-button :class="`region-button headneck${isAgreed && getRegions.includes('head') ? '' : ' disabled'}`" :href="isAgreed && getRegions.includes('head') && '/detect/head/'">
-          <RegionIcon class="region-image" :region="3" />
+          <RegionIcon class="region-image" :region="3" :iconSet="getIconSet" />
         </f7-button>
       </div>
     </div>
@@ -93,7 +97,8 @@
 </style>
 
 <script>
-  import RegionIcon from '../components/region-icon.vue'
+  import { touchstart } from 'dom7'
+import RegionIcon from '../components/region-icon.vue'
   import store from '../js/store'
   import { f7 } from 'framework7-vue'
 
@@ -103,6 +108,7 @@
     },
     data () {
       return {
+        isCordova: !!window.cordova,
         alphaCheck: false
       }
     },

src/pages/settings.vue

@@ -31,19 +31,22 @@
             <span style="margin-left: 16px;">Disable video estimates<f7-icon size="16" style="padding-left: 5px;" f7="question_diamond_fill" tooltip="faster: recommended for slower devices" /></span>
             <f7-toggle v-model:checked="otherSettings.disableVideo" style="margin-right: 16px;" />
           </div>
-          <div style="display:flex; justify-content:space-between; width: 100%">
+          <div  v-if="serverToggle">
-            <span style="margin-left: 16px;">Use external server</span>
+            <div style="display:flex; justify-content:space-between; width: 100%">
-            <f7-toggle v-model:checked="serverSettings.use" style="margin-right: 16px;" @change="setDirty()" />
+              <span style="margin-left: 16px;">Use external server</span>
+              <f7-toggle v-model:checked="serverSettings.use" style="margin-right: 16px;" @change="setDirty()" />
+            </div>
+            <f7-list >
+              <f7-list-input :disabled="!serverSettings.use || serverList" v-model:value="serverSettings.address" label="Server address" type="text" placeholder="127.0.0.1" />
+              <f7-list-input :disabled="!serverSettings.use || serverList" v-model:value="serverSettings.port" label="Server port" type="text" placeholder="9001" />
+            </f7-list>
+            <span>Other servers</span>
+            <f7-list :dividers="true" :outline="true" :strong="true" :inset="true" style="width: calc(100% - 32px); margin-top: 0;">
+              <f7-list-item v-for="(addObj) in externalIp" :disabled="!serverSettings.use" :title="addObj.name" @click="setServerProps(addObj.address, addObj.port)"></f7-list-item>
+              <f7-list-item v-if="!serverList" v-for="(port, add) in otherIp" :disabled="!serverSettings.use" :title="add" @click="setServerProps(add, port)">{{ port }}</f7-list-item>
+              <f7-list-item v-if="Object.keys(otherIp).length == 0 && externalIp.length == 0" title="No previous server settings"></f7-list-item>
+            </f7-list>
           </div>
-          <f7-list>
-            <f7-list-input :disabled="!serverSettings.use" v-model:value="serverSettings.address" label="Server address" type="text" placeholder="127.0.0.1" />
-            <f7-list-input :disabled="!serverSettings.use" v-model:value="serverSettings.port" label="Server port" type="text" placeholder="9001" />
-          </f7-list>
-          <span>Other servers</span>
-          <f7-list :dividers="true" :outline="true" :strong="true" :inset="true" style="width: calc(100% - 32px); margin-top: 0;">
-            <f7-list-item v-for="(port, add) in otherIp" :disabled="!serverSettings.use" :title="add" @click="setServerProps(add, port)">{{ port }}</f7-list-item>
-            <f7-list-item v-if="Object.keys(otherIp).length == 0" title="No previous server settings"></f7-list-item>
-          </f7-list>
         </div>
         <f7-button fill @click="saveAllSettings">SAVE</f7-button>
       </div>
@@ -61,6 +64,7 @@
 
 <script>
   import { f7 } from 'framework7-vue'
+  import store from '../js/store'
 
   export default {
     data () {
@@ -72,8 +76,8 @@
         },
         serverSettings: {
           use: false,
-          address: '10.170.64.22',
+          address: '127.0.0.1',
-          port: '9001',
+          port: '9000',
           previous: {}
         },
         themeSettings: {
@@ -81,6 +85,9 @@
         }
       }
     },
+    setup() {
+      return store()
+    },
     computed: {
       otherIp () {
         let filteredIps = {}
@@ -90,6 +97,15 @@
           }
         }
         return filteredIps
+      },
+      serverToggle () {
+        return ['optional','list'].includes(this.externalType)
+      },
+      serverList () {
+        return this.externalType == 'list'
+      },
+      externalIp () {
+        return this.getServerList()
       }
     },
     created () {
@@ -106,7 +122,7 @@
         let saveSetting = new Promise(
           (saved,failed) => {
             try {
-              if (this.serverSettings.use) {
+              if (this.serverSettings.use && !this.externalIp.some( (srv) => srv.address == this.serverSettings.address)) {
                 this.serverSettings.previous[this.serverSettings.address] = this.serverSettings.port
               }
               localStorage.setItem('serverSettings',JSON.stringify(this.serverSettings))
@@ -151,7 +167,8 @@
       },
       toggleSettingsView () {
         this.showAdvanced = !this.showAdvanced
-        this.$refs.advancedSettings.style.maxHeight = `${this.showAdvanced ? this.$refs.advancedSettings.scrollHeight : 0}px`
+        //this.$refs.advancedSettings.style.maxHeight = `${this.showAdvanced ? this.$refs.advancedSettings.scrollHeight : 0}px`
+        this.$refs.advancedSettings.style.maxHeight = this.showAdvanced ? '100%' : '0px'
       },
       confirmBack () {
         if (this.isDirty) {

src/pages/specs.vue

@@ -8,6 +8,7 @@
         <f7-block-title medium>Details</f7-block-title>
         <f7-list>
           <f7-list-item title="Version" :after="alvinnVersion"></f7-list-item>
+          <f7-list-item v-if="isSafari" title="Safari" after="Workers disabled"></f7-list-item>
         </f7-list>
         <f7-block-title medium>Models</f7-block-title>
         <f7-list style="width: 100%;">
@@ -15,8 +16,10 @@
           <f7-list-item title="Thorax-m" :after="miniThoraxDetails.version"></f7-list-item>
           <f7-list-item :class="otherSettings.mini ? 'unused-model' : ''" title="Abdomen/Pelvis" :after="abdomenDetails.version"></f7-list-item>
           <f7-list-item title="Abd/Pel-m" :after="miniAbdomenDetails.version"></f7-list-item>
-          <f7-list-item title="Limbs" :after="limbsDetails.version"></f7-list-item>
+          <f7-list-item :class="otherSettings.mini ? 'unused-model' : ''" title="Limbs" :after="limbsDetails.version"></f7-list-item>
-          <f7-list-item title="Head/Neck" :after="headneckDetails.version"></f7-list-item>
+          <f7-list-item title="Limbs-m" :after="miniLimbsDetails.version"></f7-list-item>
+          <f7-list-item :class="otherSettings.mini ? 'unused-model' : ''" title="Head/Neck" :after="headneckDetails.version"></f7-list-item>
+          <f7-list-item title="Head-m" :after="miniHeadneckDetails.version"></f7-list-item>
         </f7-list>
       </div>
     </f7-block>
@@ -42,10 +45,15 @@
         miniThoraxDetails: {},
         abdomenDetails: {},
         miniAbdomenDetails: {},
-        limbsDetails: { "version": "N/A" },
+        //limbsDetails: { "version": "N/A" },
-        headneckDetails: { "version": "N/A" },
+        //headneckDetails: { "version": "N/A" },
+        limbsDetails: {},
+        miniLimbsDetails: {},
+        headneckDetails: {},
+        miniHeadneckDetails: {},
         alvinnVersion: store().getVersion,
         isCordova: !!window.cordova,
+        isSafari: store().isSafari,
         otherSettings: {}
       }
     },
@@ -67,6 +75,18 @@
         fetch(`${this.isCordova ? 'https://localhost' : '.'}/models/abdomen-mini/descript.json`)
           .then((mod) => { return mod.json() })
           .then((desc) => { this.miniAbdomenDetails = desc })
+        fetch(`${this.isCordova ? 'https://localhost' : '.'}/models/limbs/descript.json`)
+          .then((mod) => { return mod.json() })
+          .then((desc) => { this.limbsDetails = desc })
+        fetch(`${this.isCordova ? 'https://localhost' : '.'}/models/limbs-mini/descript.json`)
+          .then((mod) => { return mod.json() })
+          .then((desc) => { this.miniLimbsDetails = desc })
+        fetch(`${this.isCordova ? 'https://localhost' : '.'}/models/head/descript.json`)
+          .then((mod) => { return mod.json() })
+          .then((desc) => { this.headneckDetails = desc })
+        fetch(`${this.isCordova ? 'https://localhost' : '.'}/models/head-mini/descript.json`)
+          .then((mod) => { return mod.json() })
+          .then((desc) => { this.miniHeadneckDetails = desc })
     },
     methods: {
     }