scripts for project of medical dataset bcss (modality=histopathology).

projects/medical/2d_image/fundus_photography/rite/README.md → projects/medical/2d_image/histopathology/bcss/README.md

@@ -1,48 +1,52 @@
-# Retinal Images vessel Tree Extraction (RITE)
+# Breast Cancer Semantic Segmentation (BCSS)
 
 ## Description
 
-This project support **`Retinal Images vessel Tree Extraction (RITE) `**, and the dataset used in this project can be downloaded from [here](https://opendatalab.com/RITE).
+This project support **`Breast Cancer Semantic Segmentation (BCSS) `**, and the dataset used in this project can be downloaded from [here](https://bcsegmentation.grand-challenge.org/).
 
 ### Dataset Overview
 
-The RITE (Retinal Images vessel Tree Extraction) is a database that enables comparative studies on segmentation or classification of arteries and veins on retinal fundus images, which is established based on the public available DRIVE database (Digital Retinal Images for Vessel Extraction). RITE contains 40 sets of images, equally separated into a training subset and a test subset, the same as DRIVE. The two subsets are built from the corresponding two subsets in DRIVE. For each set, there is a fundus photograph, a vessel reference standard. The fundus photograph is inherited from DRIVE. For the training set, the vessel reference standard is a modified version of 1st_manual from DRIVE. For the test set, the vessel reference standard is 2nd_manual from DRIVE.
+The BCSS dataset contains over 20,000 segmentation annotations of tissue region from breast cancer images from TCGA. This large-scale dataset was annotated through the collaborative effort of pathologists, pathology residents, and medical students using the Digital Slide Archive.  It enables the generation of highly accurate machine-learning models for tissue segmentation.
 
-### Statistic Information
+### Information Statistics
 
-| dataset name                         | anatomical region | task type    | modality           | num. classes | train/val/test images | release date | License                                                         |
-| ------------------------------------ | ----------------- | ------------ | ------------------ | ------------ | --------------------- | ------------ | --------------------------------------------------------------- |
-| [Rite](https://opendatalab.com/RITE) | head_and_neck     | segmentation | fundus_photography | 2            | 20/-/20               | 2013         | [CC-BY-NC 4.0](https://creativecommons.org/licenses/by-sa/4.0/) |
+| dataset_name                                        | anatomical region | task type    | modality       | number of categories | train/val/test image | release date | License                                                       |
+| --------------------------------------------------- | ----------------- | ------------ | -------------- | -------------------- | -------------------- | ------------ | ------------------------------------------------------------- |
+| [bcss](https://bcsegmentation.grand-challenge.org/) | throax            | segmentation | histopathology | 6                    | 151/-/-              | 2019         | [CC0 1.0](https://creativecommons.org/publicdomain/zero/1.0/) |
 
-| class name | pixel percentage | Num. images in this category |
-| ---------- | ---------------- | ---------------------------- |
-| background | 91.60            | 40                           |
-| vessel     | 8.40             | 40                           |
+| class_name   | Percentage of pixels（%） | Number of pictures in this category |
+| ------------ | ------------------------- | ----------------------------------- |
+| background   | 21.75                     | 49                                  |
+| tumor        | 31.04                     | 151                                 |
+| stroma       | 28.16                     | 151                                 |
+| inflammatory | 9.44                      | 126                                 |
+| necrosis     | 5.16                      | 91                                  |
+| other        | 4.45                      | 141                                 |
 
 ### Visualization
 
-![rite](https://github.com/uni-medical/medical-datasets-visualization/blob/main/2d/semantic_seg/fundus_photography/rite/rite_dataset.png?raw=true)
+![bcss](https://github.com/uni-medical/medical-datasets-visualization/blob/main/2d/semantic_seg/histopathology/bcss/bcss_dataset.png?raw=true)
 
 ### Prerequisites
 
 - Python 3.8
 - PyTorch 1.10.0
-- pillow(PIL) 9.3.0
-- scikit-learn(sklearn) 1.2.0
+- pillow(PIL)
+- scikit-learn(sklearn)
 - [MIM](https://github.com/open-mmlab/mim) v0.3.4
 - [MMCV](https://github.com/open-mmlab/mmcv) v2.0.0rc4
 - [MMEngine](https://github.com/open-mmlab/mmengine) v0.2.0 or higher
 - [MMSegmentation](https://github.com/open-mmlab/mmsegmentation) v1.0.0rc5
 
-All the commands below rely on the correct configuration of PYTHONPATH, which should point to the project's directory so that Python can locate the module files. In rite/ root directory, run the following line to add the current directory to PYTHONPATH:
+All the commands below rely on the correct configuration of PYTHONPATH, which should point to the project's directory so that Python can locate the module files. In bcss/ root directory, run the following line to add the current directory to PYTHONPATH:
 
 ```shell
 export PYTHONPATH=`pwd`:$PYTHONPATH
 ```
 
 ### Dataset preparing
 
-- download dataset from [here](https://opendatalab.com/RITE) and decompression data to path 'data/'.
+- download dataset from [here](https://bcsegmentation.grand-challenge.org/) and decompression data to path 'data/'.
 - run script `"python tools/prepare_dataset.py"` to split dataset and change folder structure as below.
 
 ```none
@@ -51,8 +55,8 @@ export PYTHONPATH=`pwd`:$PYTHONPATH
   ├── projects
   │   ├── medical
   │   │   ├── 2d_image
-  │   │   │   ├── fundus_photography
-  │   │   │   │   ├── rite
+  │   │   │   ├── histopathology
+  │   │   │   │   ├── bcss
   │   │   │   │   │   ├── configs
   │   │   │   │   │   ├── datasets
   │   │   │   │   │   ├── tools
@@ -101,21 +105,21 @@ You should claim whether this is based on the pre-trained weights, which are con
 
 ## Results
 
-### Retinal Images Vessel Tree Extraction
+### Breast Cancer Semantic Segmentation (BCSS)
 
-|     Method      | Backbone | Crop Size |   lr   | mIoU  | mDice |                                                                                       config                                                                                        |
-| :-------------: | :------: | :-------: | :----: | :---: | :---: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
-| fcn_unet_s5-d16 |   unet   |  512x512  |  0.01  | 76.48 | 84.68 |  [config](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/projects/medical/2d_image/fundus_photography/rite/configs/fcn-unet-s5-d16_unet_1xb16-0.01-20k_rite-512x512.py)  |
-| fcn_unet_s5-d16 |   unet   |  512x512  | 0.001  | 61.06 | 63.69 | [config](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/projects/medical/2d_image/fundus_photography/rite/configs/fcn-unet-s5-d16_unet_1xb16-0.001-20k_rite-512x512.py)  |
-| fcn_unet_s5-d16 |   unet   |  512x512  | 0.0001 | 58.87 | 62.42 | [config](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/projects/medical/2d_image/fundus_photography/rite/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_rite-512x512.py) |
+|     Method      | Backbone | Crop Size |   lr   | mIoU  | mDice |                                                                                     config                                                                                      |
+| :-------------: | :------: | :-------: | :----: | :---: | :---: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+| fcn_unet_s5-d16 |   unet   |  512x512  |  0.01  | 76.48 | 84.68 |  [config](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/projects/medical/2d_image/histopathology/bcss/configs/fcn-unet-s5-d16_unet_1xb16-0.01-20k_bcss-512x512.py)  |
+| fcn_unet_s5-d16 |   unet   |  512x512  | 0.001  | 61.06 | 63.69 | [config](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/projects/medical/2d_image/histopathology/bcss/configs/fcn-unet-s5-d16_unet_1xb16-0.001-20k_bcss-512x512.py)  |
+| fcn_unet_s5-d16 |   unet   |  512x512  | 0.0001 | 58.87 | 62.42 | [config](https://github.com/open-mmlab/mmsegmentation/tree/dev-1.x/projects/medical/2d_image/histopathology/bcss/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_bcss-512x512.py) |
 
 ## Checklist
 
 - [x] Milestone 1: PR-ready, and acceptable to be one of the `projects/`.
 
   - [x] Finish the code
   - [x] Basic docstrings & proper citation
-  - [x] Test-time correctness
+  - [ ] Test-time correctness
   - [x] A full README
 
 - [x] Milestone 2: Indicates a successful model implementation.

projects/medical/2d_image/fundus_photography/rite/configs/rite_512x512.py → projects/medical/2d_image/histopathology/bcss/configs/bcss_512x512.py

@@ -1,4 +1,4 @@
-dataset_type = 'RITEDataset'
+dataset_type = 'BCSSDataset'
 data_root = 'data/'
 img_scale = (512, 512)
 train_pipeline = [

projects/medical/2d_image/fundus_photography/rite/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_rite-512x512.py → projects/medical/2d_image/histopathology/bcss/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_bcss-512x512.py

@@ -1,16 +1,16 @@
 _base_ = [
-    'mmseg::_base_/models/fcn_unet_s5-d16.py', './rite_512x512.py',
+    'mmseg::_base_/models/fcn_unet_s5-d16.py', './bcss_512x512.py',
     'mmseg::_base_/default_runtime.py',
     'mmseg::_base_/schedules/schedule_20k.py'
 ]
-custom_imports = dict(imports='datasets.rite_dataset')
+custom_imports = dict(imports='datasets.bcss_dataset')
 img_scale = (512, 512)
 data_preprocessor = dict(size=img_scale)
 optimizer = dict(lr=0.0001)
 optim_wrapper = dict(optimizer=optimizer)
 model = dict(
     data_preprocessor=data_preprocessor,
-    decode_head=dict(num_classes=2),
+    decode_head=dict(num_classes=6),
     auxiliary_head=None,
     test_cfg=dict(mode='whole', _delete_=True))
 vis_backends = None

projects/medical/2d_image/fundus_photography/rite/configs/fcn-unet-s5-d16_unet_1xb16-0.001-20k_rite-512x512.py → projects/medical/2d_image/histopathology/bcss/configs/fcn-unet-s5-d16_unet_1xb16-0.001-20k_bcss-512x512.py

@@ -1,16 +1,16 @@
 _base_ = [
-    'mmseg::_base_/models/fcn_unet_s5-d16.py', './rite_512x512.py',
+    'mmseg::_base_/models/fcn_unet_s5-d16.py', './bcss_512x512.py',
     'mmseg::_base_/default_runtime.py',
     'mmseg::_base_/schedules/schedule_20k.py'
 ]
-custom_imports = dict(imports='datasets.rite_dataset')
+custom_imports = dict(imports='datasets.bcss_dataset')
 img_scale = (512, 512)
 data_preprocessor = dict(size=img_scale)
 optimizer = dict(lr=0.001)
 optim_wrapper = dict(optimizer=optimizer)
 model = dict(
     data_preprocessor=data_preprocessor,
-    decode_head=dict(num_classes=2),
+    decode_head=dict(num_classes=6),
     auxiliary_head=None,
     test_cfg=dict(mode='whole', _delete_=True))
 vis_backends = None

projects/medical/2d_image/fundus_photography/rite/configs/fcn-unet-s5-d16_unet_1xb16-0.01-20k_rite-512x512.py → projects/medical/2d_image/histopathology/bcss/configs/fcn-unet-s5-d16_unet_1xb16-0.01-20k_bcss-512x512.py

@@ -1,16 +1,16 @@
 _base_ = [
-    'mmseg::_base_/models/fcn_unet_s5-d16.py', './rite_512x512.py',
+    'mmseg::_base_/models/fcn_unet_s5-d16.py', './bcss_512x512.py',
     'mmseg::_base_/default_runtime.py',
     'mmseg::_base_/schedules/schedule_20k.py'
 ]
-custom_imports = dict(imports='datasets.rite_dataset')
+custom_imports = dict(imports='datasets.bcss_dataset')
 img_scale = (512, 512)
 data_preprocessor = dict(size=img_scale)
 optimizer = dict(lr=0.01)
 optim_wrapper = dict(optimizer=optimizer)
 model = dict(
     data_preprocessor=data_preprocessor,
-    decode_head=dict(num_classes=2),
+    decode_head=dict(num_classes=6),
     auxiliary_head=None,
     test_cfg=dict(mode='whole', _delete_=True))
 vis_backends = None

projects/medical/2d_image/fundus_photography/rite/datasets/rite_dataset.py → projects/medical/2d_image/histopathology/bcss/datasets/bcss_dataset.py

@@ -3,21 +3,22 @@
 
 
 @DATASETS.register_module()
-class RITEDataset(BaseSegDataset):
-    """RITEDataset dataset.
-
-    In segmentation map annotation for RITEDataset,
-    0 stands for background, which is included in 2 categories.
-    ``reduce_zero_label`` is fixed to False. The ``img_suffix``
-    is fixed to '.png' and ``seg_map_suffix`` is fixed to '.png'.
+class BCSSDataset(BaseSegDataset):
+    """BCSSDataset dataset.
 
+    In segmentation map annotation for BCSSDataset, 0 stands for background,
+    which is included in 6 categories. ``reduce_zero_label`` is fixed to
+    False. The ``img_suffix`` is fixed to '.png' and ``seg_map_suffix`` is
+    fixed to '.png'.
     Args:
         img_suffix (str): Suffix of images. Default: '.png'
         seg_map_suffix (str): Suffix of segmentation maps. Default: '.png'
         reduce_zero_label (bool): Whether to mark label zero as ignored.
-            Default to False.
+            Default to False..
     """
-    METAINFO = dict(classes=('background', 'vessel'))
+    METAINFO = dict(
+        classes=('background', 'tumor', 'stroma', 'inflammatory', 'necrosis',
+                 'other'))
 
     def __init__(self,
                  img_suffix='.png',