PLS4MIS is an open-source toolbox for partially labeled medical image segmentation.
- This project aims to facilitate research in scenarios where full pixel-wise annotations are expensive or infeasible by providing literature reviews, benchmark implementations, and practical PyTorch code.
- π Focused on partially labeled supervision for 3D medical image segmentation
- π Includes daily-updated literature reviews
- π οΈ Implements six representative algorithms
- π§ͺ Ready-to-run examples and scripts
π Literature reviews of partially labeled learning approach for medical image segmentation (PLS4MIS)
Date | The First and Last Authors | Title | Code | Reference |
---|---|---|---|---|
2024-06 | B. Billot and P. Golland | Network conditioning for synergistic learning on partial annotations | Code | MIDL2024 |
2024-05 | H. Liu and S. Grbic | COSST: Multi-Organ Segmentation With Partially Labeled Datasets Using Comprehensive Supervisions and Self-Training | None | TMI2024 |
2023-09 | Y. Xie and C. Shen | Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation | Code | TPAMI2023 |
2023-06 | X. Liu and S. Yang | CCQ: Cross-Class Query Network for Partially Labeled Organ Segmentation | Code | AAAI2023 |
2022-08 | R. Deng and Y. Huo | Omni-Seg: A Single Dynamic Network for Multi-label Renal Pathology Image Segmentation using Partially Labeled Data | Code | MIDL2022 |
2022-04 | H. Wu and A. Sowmya | Tgnet: A Task-Guided Network Architecture for Multi-Organ and Tumour Segmentation from Partially Labelled Datasets | None | ISBI2022 |
2021-09 | L. Fidon and T. Vercauteren | Label-Set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation | Code | MICCAI2021 |
2021-05 | G. Shi and SK. Zhou | Marginal loss and exclusion loss for partially supervised multi-organ segmentation | Code | MedIA2021 |
2021-03 | J. Zhang and C. Shen | DoDNet: Learning To Segment Multi-Organ and Tumors From Multiple Partially Labeled Datasets | Code | CVPR2021 |
2020-11 | X. Fang and P. Yan | Multi-Organ Segmentation Over Partially Labeled Datasets With Multi-Scale Feature Abstraction | Code | TMI2020 |
Some implementations of partially labeled learning methods can be found in this Link.
We welcome contributions, suggestions, and collaborations!
- π§ Email: [email protected]
- π¬ QQ Group (Chinese): 906808850