Python-基于各种挑战的SOTA医学图像分割方法

# State-of-the-art medical image segmentation methods based on various challenges! (Updated 201908) ## Contents **Head** - 2019 MICCAI: Multimodal Brain Tumor Segmentation Challenge (BraTS2019) [(Ongoing!!!)](http://braintumorsegmentation.org/) - 2019 MICCAI: Automatic Structure Segmentation for Radiotherapy Planning Challenge [(Ongoing!!!)](https://structseg2019.grand-challenge.org/) - 2018 MICCAI: Multimodal Brain Tumor Segmentation Challenge - 2018 MICCAI: Ischemic stroke lesion segmentation - 2018 MICCAI Grand Challenge on MR Brain Image Segmentation **Chest & Abdomen** - 2019 MICCAI: VerSe2019: Large Scale Vertebrae Segmentation Challenge [(Ongoing!!!)](https://verse2019.grand-challenge.org/Home/) - 2019 MICCAI: Multi-sequence Cardiac MR Segmentation Challenge - 2018 MICCAI: Left Ventricle Full Quantification Challenge  - 2018 MICCAI: Atrial Segmentation Challenge - 2019 MICCAI: Kidney Tumor Segmentation Challenge - 2019 ISBI: Segmentation of THoracic Organs at Risk in CT images - 2017 ISBI & MICCAI: Liver tumor segmentation challenge  - 2012 MICCAI: Prostate MR Image Segmentation  **Others** - 2018 MICCAI Medical Segmentation Decathlon - Awesome Open Source Tools - Loss functions for class imbalanced Problems ## Brain - 2019 MICCAI: Multimodal Brain Tumor Segmentation Challenge (BraTS2019) [(Ongoing!!!)](http://braintumorsegmentation.org/) - 2019 MICCAI: 6-month Infant Brain MRI Segmentation from Multiple Sites (iSeg2019) [(Ongoing!!!)](http://iseg2019.web.unc.edu/) ## Heart ### 2019 MICCAI: Multi-sequence Cardiac MR Segmentation Challenge [(MS-CMRSeg)](http://www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mscmrseg19/) **Waiting for results** > Multi-sequence ventricle and myocardium segmentation. ## Chest and Abdomen ### 2019 MICCAI: Kidney Tumor Segmentation Challenge [(KiTS19)](https://kits19.grand-challenge.org/) **[Leaderboard (2019/07/30)](http://results.kits-challenge.org/miccai2019/)** |Date|First Author |Title|Composite Dice|Kidney Dice|Tumor Dice|Remark| |---|---|---|---|---|---|---| |20190730|[Fabian Isensee](https://scholar.google.com/citations?user=PjerEe4AAAAJ&hl=en)|An attempt at beating the 3D U-Net [(paper)](http://results.kits-challenge.org/miccai2019/manuscripts/Isensee_1.pdf)|0.9123|0.9737|0.8509|1st Place| |20190730|Xiaoshuai Hou |Cascaded Semantic Segmentation for Kidney and Tumor [(paper)](http://results.kits-challenge.org/miccai2019/manuscripts/PingAnTech_3.pdf)|0.9064|0.9674|0.8454|2nd Place| |20190730|Guangrui Mu|Segmentation of kidney tumor by multi-resolution VB-nets [(paper)](http://results.kits-challenge.org/miccai2019/manuscripts/gr_6.pdf)|0.9025|0.9729|0.8321|3rd Place| ### 2019 ISBI: Segmentation of THoracic Organs at Risk in CT images [(SegTHOR)](https://competitions.codalab.org/competitions/21012) |Date|First Author |Title|Esophagus|Heart|Trachea|Aorta| |---|---|---|---|---|---|---| |20190320|Miaofei Han|Segmentation of CT thoracic organs by multi-resolution VB-nets [(paper)](http://pagesperso.litislab.fr/cpetitjean/wp-content/uploads/sites/19/2019/04/SegTHOR2019_paper_1.pdf)|86|95|92|94| |20190606|[Shadab Khan](https://scholar.google.ca/citations?user=HD4-OxgAAAAJ&hl=en&oi=ao)|Extreme Points Derived Confidence Map as a Cue For Class-Agnostic Segmentation Using Deep Neural Network [(paper)](https://arxiv.org/pdf/1906.02421.pdf)|89.87|95.97|91.87|94| > [Challenge results](http://pagesperso.litislab.fr/cpetitjean/wp-content/uploads/sites/19/2019/04/SegTHOR_presentation_2.pdf) ### 2017 ISBI & MICCAI: Liver tumor segmentation challenge [(LiTS)](https://competitions.codalab.org/competitions/17094) *Summary: The Liver Tumor Segmentation Benchmark (LiTS), Patrick Bilic et al. 201901 [(arxiv)](https://arxiv.org/abs/1901.04056)* |Date|First Author |Title|Liver Dice|Tumor Dice| |---|---|---|---|---| |201709|[Xiaomeng Li](https://scholar.google.ca/citations?user=uVTzPpoAAAAJ&hl=zh-CN&oi=sra)| H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes, [(paper)](https://arxiv.org/abs/1709.07330), [(Keras code)](https://github.com/xmengli999/H-DenseUNet) |0.961|0.722| ### 2012 MICCAI: Prostate MR Image Segmentation [(PROMISE12)](https://promise12.grand-challenge.org/) |Date|First Author |Title|Whole Dice|Overall Score| |---|---|---|---|---| |201904|Anonymous|3D segmentation and 2D boundary network [(paper)](https://drive.google.com/file/d/1yGKeFNyXMajBQ1yebzXM2V-GiGf6GFBJ/view)|-|90.34| |201902|Qikui Zhu|Boundary-weighted Domain Adaptive Neural Network for Prostate MR Image Segmentation [(paper)](https://arxiv.org/abs/1902.08128)|91.41|89.59| ## Others ### [2018 MICCAI Medical Segmentation Decathlon](http://medicaldecathlon.com/) |Task|Data Info|Fabian Isensee et al. [(paper)](https://arxiv.org/abs/1809.10486)| Yingda Xia et al. [(paper)](https://arxiv.org/abs/1811.12506)| |---|---|---|---| |Brats|Multimodal multisite MRI data (FLAIR, T1w, T1gd,T2w), (484 Training + 266 Testing) |0.68/0.48/0.68|0.675/0.45/0.68| |Heart|Mono-modal MRI (20 Training + 10 Testing) |0.93|0.925| |Hippocampus head and body|Mono-modal MRI (263 Training + 131 Testing)|0.90/0.89|0.88/0.867| |Liver & Tumor|Portal venous phase CT (131 Training + 70 Testing)|0.95/0.74|0.95/0.714| |Lung|CT (64 Training + 32 Testing)|0.69|0.52| |Pancreas & Tumor|Portal venous phase CT (282 Training +139 Testing) |0.80/0.52|0.784/0.385| |Prostate central gland and peripheral|Multimodal MR (T2, ADC) (32 Training + 16 Testing)|0.76/0.90|0.69/0.867| |Hepatic vessel& Tumor| CT, (303 Training + 140 Testing)|0.63/0.69|-| |Spleen|CT (41 Training + 20 Testing)|0.96|-| |Colon|CT (41 Training + 20 Testing)|0.56|-| > Only showing Dice Score. ### Recent papers on Medical Segmentation Decathlon |Date|First Author |Title|Score| |---|---|---|---| |20190606|Zhuotun Zhu|V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation [(arxiv)](https://arxiv.org/abs/1906.02817)|Lung tumor: 55.27; Pancreas and tumor: 79.94, 37.78 (4-fold CV)| # Past Challenges (New submission closed) ### 2018 MICCAI: Multimodal Brain Tumor Segmentation Challenge[(BraTS)](https://www.med.upenn.edu/sbia/brats2018.html) *Summary: Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge Spyridon Bakas et al. 201811, [(arxiv)](https://arxiv.org/abs/1811.02629)* |Rank(18) |First Author |Title|Val. WT/EN/TC Dice|Test Val. WT/ET/TC Dice| |---|---|---|---|---| |1|Andriy Myronenko|3D MRI Brain Tumor Segmentation Using Autoencoder Regularization [(paper)](https://arxiv.org/pdf/1810.11654.pdf)|0.91/0.823/0.867|0.884/0.766/0.815| |2|[Fabian Isensee](https://scholar.google.ca/citations?user=PjerEe4AAAAJ&hl=zh-CN&oi=ao)|No New-Net [(paper)](https://arxiv.org/abs/1809.10483)|0.913/0.809/0.863|0.878/0.779/0.806| |3|[Richard McKinley](https://scholar.google.ca/citations?user=MVFfMZcAAAAJ&hl=zh-CN&oi=sra)|Ensembles of Densely-Connected CNNs with Label-Uncertainty for Brain Tumor Segmentation [(paper)](https://link.springer.com/chapter/10.1007/978-3-030-11726-9_40)|0.903/0.796/0.847|0.886/0.732/0.799| |3|Chenhong Zhou|Learning Contextual and Attentive Information for Brain Tumor Segmentation [(paper)](https://link.springer.com/chapter/10.1007/978-3-030-11726-9_44)|0.9095/0.8136/0.8651|0.8842/0.7775/0.7960| |New|[Xuhua Ren](https://scholar.google.com/citations?user=V2ujH7IAAAAJ&hl=zh-CN)|Task Decomposition and Synchronization for Semantic Biomedical Image Segmentation [(paper)](https://arxiv.org/abs/1905.08720)|0.915/0.832/0.883|-| ### 2018 MICCAI: Ischemic stroke lesion segmentation [(ISLES )](http://www.isles-challenge.org/) |Date |First Author |Title|Dice| |---|---|---|---| |20190605|Yu Chen|OctopusNet: A Deep Learning Segmentation Network for Multi-modal Medical Images [(paper)](https://arxiv.org/abs/1906.02031)|57.90 (5-fold CV)| |201812|[Hoel Kervadec](https://scholar.google.ca/citations?user=yeFGhfgAAAAJ&hl=zh-CN&oi=sra)|Boundary loss