monai-test
/

pathology_nuclei_segmentation_classification

monai

medical

Model card Files Files and versions Community

katielink commited on Aug 16, 2023

Commit

268d2cb

1 Parent(s): 23f4506

Update README Formatting

Browse files

Files changed (3) hide show

README.md +2 -5
configs/metadata.json +2 -1
docs/README.md +2 -5

README.md CHANGED Viewed

@@ -8,10 +8,8 @@ license: apache-2.0
 # Model Overview
 A pre-trained model for simultaneous segmentation and classification of nuclei within multi-tissue histology images based on CoNSeP data. The details of the model can be found in [1].
-## Workflow
 The model is trained to simultaneously segment and classify nuclei. Training is done via a two-stage approach. First initialized the model with pre-trained weights on the [ImageNet dataset](https://ieeexplore.ieee.org/document/5206848), trained only the decoders for the first 50 epochs, and then fine-tuned all layers for another 50 epochs. There are two training modes in total. If "original" mode is specified, [270, 270] and [80, 80] are used for `patch_size` and `out_size` respectively. If "fast" mode is specified, [256, 256] and [164, 164] are used for `patch_size` and `out_size` respectively. The results shown below are based on the "fast" mode.
-### Pre-trained weights
 The first stage is trained with pre-trained weights from some internal data.The [original author's repo](https://github.com/vqdang/hover_net#data-format) also provides pre-trained weights but for non-commercial use.
 Each user is responsible for checking the content of models/datasets and the applicable licenses and determining if suitable for the intended use.
@@ -29,6 +27,8 @@ The training data is from <https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet
 The provided labelled data was partitioned, based on the original split, into training (27 tiles) and testing (14 tiles) datasets.
 After download the datasets, please run `scripts/prepare_patches.py` to prepare patches from tiles. Prepared patches are saved in `your-concep-dataset-path`/Prepared. The implementation is referring to <https://github.com/vqdang/hover_net/blob/master/extract_patches.py>. The command is like:
 ```
@@ -125,9 +125,6 @@ python -m monai.bundle run --config_file "['configs/train.json','configs/evaluat
 python -m monai.bundle run --config_file configs/inference.json
 ```
-# Disclaimer
-This is an example, not to be used for diagnostic purposes.
 # References
 [1] Simon Graham, Quoc Dang Vu, Shan E Ahmed Raza, Ayesha Azam, Yee Wah Tsang, Jin Tae Kwak, Nasir Rajpoot, Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images, Medical Image Analysis, 2019 https://doi.org/10.1016/j.media.2019.101563

 # Model Overview
 A pre-trained model for simultaneous segmentation and classification of nuclei within multi-tissue histology images based on CoNSeP data. The details of the model can be found in [1].
 The model is trained to simultaneously segment and classify nuclei. Training is done via a two-stage approach. First initialized the model with pre-trained weights on the [ImageNet dataset](https://ieeexplore.ieee.org/document/5206848), trained only the decoders for the first 50 epochs, and then fine-tuned all layers for another 50 epochs. There are two training modes in total. If "original" mode is specified, [270, 270] and [80, 80] are used for `patch_size` and `out_size` respectively. If "fast" mode is specified, [256, 256] and [164, 164] are used for `patch_size` and `out_size` respectively. The results shown below are based on the "fast" mode.
 The first stage is trained with pre-trained weights from some internal data.The [original author's repo](https://github.com/vqdang/hover_net#data-format) also provides pre-trained weights but for non-commercial use.
 Each user is responsible for checking the content of models/datasets and the applicable licenses and determining if suitable for the intended use.
 The provided labelled data was partitioned, based on the original split, into training (27 tiles) and testing (14 tiles) datasets.
+### Preprocessing
 After download the datasets, please run `scripts/prepare_patches.py` to prepare patches from tiles. Prepared patches are saved in `your-concep-dataset-path`/Prepared. The implementation is referring to <https://github.com/vqdang/hover_net/blob/master/extract_patches.py>. The command is like:
 ```
 python -m monai.bundle run --config_file configs/inference.json
 ```
 # References
 [1] Simon Graham, Quoc Dang Vu, Shan E Ahmed Raza, Ayesha Azam, Yee Wah Tsang, Jin Tae Kwak, Nasir Rajpoot, Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images, Medical Image Analysis, 2019 https://doi.org/10.1016/j.media.2019.101563

configs/metadata.json CHANGED Viewed

@@ -1,7 +1,8 @@
 {
     "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_hovernet_20221124.json",
-    "version": "0.1.6",
     "changelog": {
         "0.1.6": "add non-deterministic note",
         "0.1.5": "update benchmark on A100",
         "0.1.4": "adapt to BundleWorkflow interface",

 {
     "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_hovernet_20221124.json",
+    "version": "0.1.7",
     "changelog": {
+        "0.1.7": "Update README Formatting",
         "0.1.6": "add non-deterministic note",
         "0.1.5": "update benchmark on A100",
         "0.1.4": "adapt to BundleWorkflow interface",

docs/README.md CHANGED Viewed

@@ -1,10 +1,8 @@
 # Model Overview
 A pre-trained model for simultaneous segmentation and classification of nuclei within multi-tissue histology images based on CoNSeP data. The details of the model can be found in [1].
-## Workflow
 The model is trained to simultaneously segment and classify nuclei. Training is done via a two-stage approach. First initialized the model with pre-trained weights on the [ImageNet dataset](https://ieeexplore.ieee.org/document/5206848), trained only the decoders for the first 50 epochs, and then fine-tuned all layers for another 50 epochs. There are two training modes in total. If "original" mode is specified, [270, 270] and [80, 80] are used for `patch_size` and `out_size` respectively. If "fast" mode is specified, [256, 256] and [164, 164] are used for `patch_size` and `out_size` respectively. The results shown below are based on the "fast" mode.
-### Pre-trained weights
 The first stage is trained with pre-trained weights from some internal data.The [original author's repo](https://github.com/vqdang/hover_net#data-format) also provides pre-trained weights but for non-commercial use.
 Each user is responsible for checking the content of models/datasets and the applicable licenses and determining if suitable for the intended use.
@@ -22,6 +20,8 @@ The training data is from <https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet
 The provided labelled data was partitioned, based on the original split, into training (27 tiles) and testing (14 tiles) datasets.
 After download the datasets, please run `scripts/prepare_patches.py` to prepare patches from tiles. Prepared patches are saved in `your-concep-dataset-path`/Prepared. The implementation is referring to <https://github.com/vqdang/hover_net/blob/master/extract_patches.py>. The command is like:
 ```
@@ -118,9 +118,6 @@ python -m monai.bundle run --config_file "['configs/train.json','configs/evaluat
 python -m monai.bundle run --config_file configs/inference.json
 ```
-# Disclaimer
-This is an example, not to be used for diagnostic purposes.
 # References
 [1] Simon Graham, Quoc Dang Vu, Shan E Ahmed Raza, Ayesha Azam, Yee Wah Tsang, Jin Tae Kwak, Nasir Rajpoot, Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images, Medical Image Analysis, 2019 https://doi.org/10.1016/j.media.2019.101563

 # Model Overview
 A pre-trained model for simultaneous segmentation and classification of nuclei within multi-tissue histology images based on CoNSeP data. The details of the model can be found in [1].
 The model is trained to simultaneously segment and classify nuclei. Training is done via a two-stage approach. First initialized the model with pre-trained weights on the [ImageNet dataset](https://ieeexplore.ieee.org/document/5206848), trained only the decoders for the first 50 epochs, and then fine-tuned all layers for another 50 epochs. There are two training modes in total. If "original" mode is specified, [270, 270] and [80, 80] are used for `patch_size` and `out_size` respectively. If "fast" mode is specified, [256, 256] and [164, 164] are used for `patch_size` and `out_size` respectively. The results shown below are based on the "fast" mode.
 The first stage is trained with pre-trained weights from some internal data.The [original author's repo](https://github.com/vqdang/hover_net#data-format) also provides pre-trained weights but for non-commercial use.
 Each user is responsible for checking the content of models/datasets and the applicable licenses and determining if suitable for the intended use.
 The provided labelled data was partitioned, based on the original split, into training (27 tiles) and testing (14 tiles) datasets.
+### Preprocessing
 After download the datasets, please run `scripts/prepare_patches.py` to prepare patches from tiles. Prepared patches are saved in `your-concep-dataset-path`/Prepared. The implementation is referring to <https://github.com/vqdang/hover_net/blob/master/extract_patches.py>. The command is like:
 ```
 python -m monai.bundle run --config_file configs/inference.json
 ```
 # References
 [1] Simon Graham, Quoc Dang Vu, Shan E Ahmed Raza, Ayesha Azam, Yee Wah Tsang, Jin Tae Kwak, Nasir Rajpoot, Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images, Medical Image Analysis, 2019 https://doi.org/10.1016/j.media.2019.101563