Notebook For ER Prediction Using SlideGraph Pipeline

examples/full-pipelines/slide-graph.ipynb

@@ -41,7 +41,17 @@
     "- Patch extraction\n",
     "- Stain normalization\n",
     "- Cell segmentation & classification\n",
-    "- Extraction of deep features"
+    "- Extraction of deep features\n",
+    "\n",
+    "> **Note**: Although the original paper was evaluated for HER2. The method itself\n",
+    "> can be applicable for other mutation prediction. We provide a pretrained model\n",
+    "> for predicting [ER (Estrogen receptor)](https://en.wikipedia.org/wiki/Estrogen_receptor)\n",
+    "> status [here (model weights)](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/model.weights.pth)\n",
+    "> and [here (model auxiliary)](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/model.aux.dat).\n",
+    "> You can get the pre-generated graphs [here](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/graphs.zip)\n",
+    "> and its node preprocessing model [here](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/node_scaler.dat).\n",
+    "> For predicting ER status, we use deep features coming from ResNet50 rather than\n",
+    "> the cellular composition.\n"
    ]
   },
   {

examples/inference-pipelines/slide-graph.ipynb

@@ -68,7 +68,17 @@
     "- Cell segmentation & classification\n",
     "- Extraction of deep features\n",
     "- Graph Construction\n",
-    "- Graph Plotting"
+    "- Graph Plotting\n",
+    "\n",
+    "> **Note**: Although the original paper was evaluated for HER2. The method itself\n",
+    "> can be applicable for other mutation prediction. We provide a pretrained model\n",
+    "> for predicting [ER (Estrogen receptor)](https://en.wikipedia.org/wiki/Estrogen_receptor)\n",
+    "> status [here (model weights)](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/model.weights.pth)\n",
+    "> and [here (model auxiliary)](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/model.aux.dat).\n",
+    "> You can get the pre-generated graphs [here](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/graphs.zip)\n",
+    "> and its node preprocessing model [here](https://tiatoolbox.dcs.warwick.ac.uk/models/slide_graph/deep-features/node_scaler.dat).\n",
+    "> For predicting ER status, we use deep features coming from ResNet50 rather than\n",
+    "> the cellular composition.\n"
    ]
   },
   {