CodeCamp #140 [New] [Feature] Add synapse dataset and data augmentation in dev-1.x.

configs/_base_/datasets/synapse.py

@@ -0,0 +1,41 @@
+dataset_type = 'SynapseDataset'
+data_root = 'data/synapse/'
+img_scale = (224, 224)
+train_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='LoadAnnotations'),
+ dict(type='Resize', scale=img_scale, keep_ratio=True),
+ dict(type='RandomRotFlip', rotate_prob=0.5, flip_prob=0.5, degree=20),
+ dict(type='PackSegInputs')
+]
+test_pipeline = [
+ dict(type='LoadImageFromFile'),
+ dict(type='Resize', scale=img_scale, keep_ratio=True),
+ dict(type='LoadAnnotations'),
+ dict(type='PackSegInputs')
+]
+train_dataloader = dict(
+ batch_size=6,
+ num_workers=2,
+ persistent_workers=True,
+ sampler=dict(type='InfiniteSampler', shuffle=True),
+ dataset=dict(
+ type=dataset_type,
+ data_root=data_root,
+ data_prefix=dict(
+ img_path='img_dir/train', seg_map_path='ann_dir/train'),
+ pipeline=train_pipeline))
+val_dataloader = dict(
+ batch_size=1,
+ num_workers=4,
+ persistent_workers=True,
+ sampler=dict(type='DefaultSampler', shuffle=False),
+ dataset=dict(
+ type=dataset_type,
+ data_root=data_root,
+ data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
+ pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(type='IoUMetric', iou_metrics=['mDice'])
+test_evaluator = val_evaluator

docs/en/user_guides/2_dataset_prepare.md

@@ -414,3 +414,84 @@ The contents of LIP datasets include:
 │   │ │ ├── 100034_483681.png
 │   │ │ ├── ...
 ```
+
+## Synapse dataset
+
+This dataset could be download from [this page](https://www.synapse.org/#!Synapse:syn3193805/wiki/)
+
+To follow the data preparation setting of [TransUNet](https://arxiv.org/abs/2102.04306), which splits original training set (30 scans)
+into new training (18 scans) and validation set (12 scans). Please run the following command to prepare the dataset.
+
+```shell
+unzip RawData.zip
+cd ./RawData/Training
+```
+
+Then create `train.txt` and `val.txt` to split dataset.
+
+According to TransUnet, the following is the data set division.
+
+train.txt
+
+```none
+img0005.nii.gz
+img0006.nii.gz
+img0007.nii.gz
+img0009.nii.gz
+img0010.nii.gz
+img0021.nii.gz
+img0023.nii.gz
+img0024.nii.gz
+img0026.nii.gz
+img0027.nii.gz
+img0028.nii.gz
+img0030.nii.gz
+img0031.nii.gz
+img0033.nii.gz
+img0034.nii.gz
+img0037.nii.gz
+img0039.nii.gz
+img0040.nii.gz
+```
+
+val.txt
+
+```none
+img0008.nii.gz
+img0022.nii.gz
+img0038.nii.gz
+img0036.nii.gz
+img0032.nii.gz
+img0002.nii.gz
+img0029.nii.gz
+img0003.nii.gz
+img0001.nii.gz
+img0004.nii.gz
+img0025.nii.gz
+img0035.nii.gz
+```
+
+The contents of synapse datasets include:
+
+```none
+├── Training
+│ ├── img
+│ │ ├── img0001.nii.gz
+│ │ ├── img0002.nii.gz
+│ │ ├── ...
+│ ├── label
+│ │ ├── label0001.nii.gz
+│ │ ├── label0002.nii.gz
+│ │ ├── ...
+│ ├── train.txt
+│ ├── val.txt
+```
+
+Then, use this command to convert synapse dataset.
+
+```shell
+python tools/dataset_converters/synapse.py --dataset-path /path/to/synapse
+```
+
+Noted that MMSegmentation default evaluation metric (such as mean dice value) is calculated on 2D slice image,
+which is not comparable to results of 3D scan in some paper such as [TransUNet](https://arxiv.org/abs/2102.04306).

mmseg/datasets/__init__.py

@@ -18,6 +18,7 @@
 from .pascal_context import PascalContextDataset, PascalContextDataset59
 from .potsdam import PotsdamDataset
 from .stare import STAREDataset
+from .synapse import SynapseDataset
 # yapf: disable
 from .transforms import (CLAHE, AdjustGamma, BioMedical3DPad,
  BioMedical3DRandomCrop, BioMedicalGaussianBlur,
@@ -26,9 +27,9 @@
  LoadBiomedicalAnnotation, LoadBiomedicalData,
  LoadBiomedicalImageFromFile, LoadImageFromNDArray,
  PackSegInputs, PhotoMetricDistortion, RandomCrop,
- RandomCutOut, RandomMosaic, RandomRotate, Rerange,
- ResizeShortestEdge, ResizeToMultiple, RGB2Gray,
- SegRescale)
+ RandomCutOut, RandomMosaic, RandomRotate,
+ RandomRotFlip, Rerange, ResizeShortestEdge,
+ ResizeToMultiple, RGB2Gray, SegRescale)
 from .voc import PascalVOCDataset
 
 # yapf: enable
@@ -46,5 +47,6 @@
  'LoadBiomedicalAnnotation', 'LoadBiomedicalData', 'GenerateEdge',
  'DecathlonDataset', 'LIPDataset', 'ResizeShortestEdge',
  'BioMedicalGaussianNoise', 'BioMedicalGaussianBlur',
- 'BioMedicalRandomGamma', 'BioMedical3DPad'
+ 'BioMedicalRandomGamma', 'BioMedical3DPad', 'RandomRotFlip',
+ 'SynapseDataset'
 ]

mmseg/datasets/synapse.py

@@ -0,0 +1,26 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from mmseg.registry import DATASETS
+from .basesegdataset import BaseSegDataset
+
+
+@DATASETS.register_module()
+class SynapseDataset(BaseSegDataset):
+ """Synapse dataset.
+
+ In segmentation map annotation for Synapse, 0 stands for background, which
+ is not include in 13 categories. The ``img_suffix`` is fixed to '.jpg' and
+ ``seg_map_suffix`` is fixed to '.png'.
+ """
+ METAINFO = dict(
+ classes=('background', 'aorta', 'gallbladder', 'left_kidney',
+ 'right_kidney', 'liver', 'pancreas', 'spleen', 'stomach'),
+ palette=[[0, 0, 0], [0, 0, 255], [0, 255, 0], [255, 0, 0],
+ [0, 255, 255], [255, 0, 255], [255, 255, 0], [60, 255, 255],
+ [240, 240, 240]])
+
+ def __init__(self,
+ img_suffix='.jpg',
+ seg_map_suffix='.png',
+ **kwargs) -> None:
+ super().__init__(
+ img_suffix=img_suffix, seg_map_suffix=seg_map_suffix, **kwargs)

mmseg/datasets/transforms/__init__.py

@@ -8,9 +8,9 @@
  BioMedical3DRandomCrop, BioMedicalGaussianBlur,
  BioMedicalGaussianNoise, BioMedicalRandomGamma,
  GenerateEdge, PhotoMetricDistortion, RandomCrop,
- RandomCutOut, RandomMosaic, RandomRotate, Rerange,
- ResizeShortestEdge, ResizeToMultiple, RGB2Gray,
- SegRescale)
+ RandomCutOut, RandomMosaic, RandomRotate,
+ RandomRotFlip, Rerange, ResizeShortestEdge,
+ ResizeToMultiple, RGB2Gray, SegRescale)
 
 # yapf: enable
 __all__ = [
@@ -20,5 +20,5 @@
  'ResizeToMultiple', 'LoadImageFromNDArray', 'LoadBiomedicalImageFromFile',
  'LoadBiomedicalAnnotation', 'LoadBiomedicalData', 'GenerateEdge',
  'ResizeShortestEdge', 'BioMedicalGaussianNoise', 'BioMedicalGaussianBlur',
- 'BioMedicalRandomGamma', 'BioMedical3DPad'
+ 'BioMedicalRandomGamma', 'BioMedical3DPad', 'RandomRotFlip'
 ]

mmseg/datasets/transforms/transforms.py

@@ -861,6 +861,84 @@ def __repr__(self):
  return repr_str
 
 
+@TRANSFORMS.register_module()
+class RandomRotFlip(BaseTransform):
+ """Rotate and flip the image & seg or just rotate the image & seg.
+
+ Required Keys:
+
+ - img
+ - gt_seg_map
+
+ Modified Keys:
+
+ - img
+ - gt_seg_map
+
+ Args:
+ rotate_prob (float): The probability of rotate image.
+ flip_prob (float): The probability of rotate&flip image.
+ degree (float, tuple[float]): Range of degrees to select from. If
+ degree is a number instead of tuple like (min, max),
+ the range of degree will be (``-degree``, ``+degree``)
+ """
+
+ def __init__(self, rotate_prob=0.5, flip_prob=0.5, degree=(-20, 20)):
+ self.rotate_prob = rotate_prob
+ self.flip_prob = flip_prob
+ assert 0 <= rotate_prob <= 1 and 0 <= flip_prob <= 1
+ if isinstance(degree, (float, int)):
+ assert degree > 0, f'degree {degree} should be positive'
+ self.degree = (-degree, degree)
+ else:
+ self.degree = degree
+ assert len(self.degree) == 2, f'degree {self.degree} should be a ' \
+ f'tuple of (min, max)'
+
+ def random_rot_flip(self, results: dict) -> dict:
+ k = np.random.randint(0, 4)
+ results['img'] = np.rot90(results['img'], k)
+ for key in results.get('seg_fields', []):
+ results[key] = np.rot90(results[key], k)
+ axis = np.random.randint(0, 2)
+ results['img'] = np.flip(results['img'], axis=axis).copy()
+ for key in results.get('seg_fields', []):
+ results[key] = np.flip(results[key], axis=axis).copy()
+ return results
+
+ def random_rotate(self, results: dict) -> dict:
+ angle = np.random.uniform(min(*self.degree), max(*self.degree))
+ results['img'] = mmcv.imrotate(results['img'], angle=angle)
+ for key in results.get('seg_fields', []):
+ results[key] = mmcv.imrotate(results[key], angle=angle)
+ return results
+
+ def transform(self, results: dict) -> dict:
+ """Call function to rotate or rotate & flip image, semantic
+ segmentation maps.
+
+ Args:
+ results (dict): Result dict from loading pipeline.
+
+ Returns:
+ dict: Rotated or rotated & flipped results.
+ """
+ rotate_flag = 0
+ if random.random() < self.rotate_prob:
+ results = self.random_rotate(results)
+ rotate_flag = 1
+ if random.random() < self.flip_prob and rotate_flag == 0:
+ results = self.random_rot_flip(results)
+ return results
+
+ def __repr__(self):
+ repr_str = self.__class__.__name__
+ repr_str += f'(rotate_prob={self.rotate_prob}, ' \
+ f'flip_prob={self.flip_prob}, ' \
+ f'degree={self.degree})'
+ return repr_str
+
+
 @TRANSFORMS.register_module()
 class RandomMosaic(BaseTransform):
  """Mosaic augmentation. Given 4 images, mosaic transform combines them into

mmseg/utils/__init__.py

@@ -6,8 +6,8 @@
  get_palette, isaid_classes, isaid_palette,
  loveda_classes, loveda_palette, potsdam_classes,
  potsdam_palette, stare_classes, stare_palette,
- vaihingen_classes, vaihingen_palette, voc_classes,
- voc_palette)
+ synapse_classes, synapse_palette, vaihingen_classes,
+ vaihingen_palette, voc_classes, voc_palette)
 # yapf: enable
 from .collect_env import collect_env
 from .io import datafrombytes
@@ -27,5 +27,5 @@
  'cityscapes_palette', 'ade_palette', 'voc_palette', 'cocostuff_palette',
  'loveda_palette', 'potsdam_palette', 'vaihingen_palette', 'isaid_palette',
  'stare_palette', 'dataset_aliases', 'get_classes', 'get_palette',
- 'datafrombytes'
+ 'datafrombytes', 'synapse_palette', 'synapse_classes'
 ]

mmseg/utils/class_names.py

@@ -265,6 +265,20 @@ def stare_palette():
  return [[120, 120, 120], [6, 230, 230]]
 
 
+def synapse_palette():
+ """Synapse palette for external use."""
+ return [[0, 0, 0], [0, 0, 255], [0, 255, 0], [255, 0, 0], [0, 255, 255],
+ [255, 0, 255], [255, 255, 0], [60, 255, 255], [240, 240, 240]]
+
+
+def synapse_classes():
+ """Synapse class names for external use."""
+ return [
+ 'background', 'aorta', 'gallbladder', 'left_kidney', 'right_kidney',
+ 'liver', 'pancreas', 'spleen', 'stomach'
+ ]
+
+
 def lip_classes():
  """LIP class names for external use."""
  return [

tests/test_datasets/test_dataset.py

@@ -9,7 +9,7 @@
 from mmseg.datasets import (ADE20KDataset, BaseSegDataset, CityscapesDataset,
  COCOStuffDataset, DecathlonDataset, ISPRSDataset,
  LIPDataset, LoveDADataset, PascalVOCDataset,
- PotsdamDataset, iSAIDDataset)
+ PotsdamDataset, SynapseDataset, iSAIDDataset)
 from mmseg.registry import DATASETS
 from mmseg.utils import get_classes, get_palette
 
@@ -220,6 +220,19 @@ def test_vaihingen():
  assert len(test_dataset) == 1
 
 
+def test_synapse():
+ test_dataset = SynapseDataset(
+ pipeline=[],
+ data_prefix=dict(
+ img_path=osp.join(
+ osp.dirname(__file__),
+ '../data/pseudo_synapse_dataset/img_dir'),
+ seg_map_path=osp.join(
+ osp.dirname(__file__),
+ '../data/pseudo_synapse_dataset/ann_dir')))
+ assert len(test_dataset) == 2
+
+
 def test_isaid():
  test_dataset = iSAIDDataset(
  pipeline=[],