🧠 PLS4MIS: Partially Labeled Supervision for Medical Image Segmentation

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.

• This project was originally developed for our previous works. We are continuing to extend it to be more user-friendly and to support additional approaches that further facilitate research in this area. If you use this codebase in your research, please cite the following works:

    @article{li2025pl,
    title={PL-Seg: Partially labeled abdominal organ segmentation via classwise orthogonal contrastive learning and progressive self-distillation},
    author={Li, He and Luo, Xiangde and Fu, Jia and Gu, Ran and Liao, Wenjun and Zhang, Shichuan and Li, Kang and Wang, Guotai and Zhang, Shaoting},
    journal={Medical Image Analysis},
    pages={103885},
    year={2025},
    publisher={Elsevier}}
  

---

📌 Highlights

• 📁 Focused on partially labeled supervision for 3D medical image segmentation
• 📚 Includes daily-updated literature reviews
• 🛠️ Implements six representative algorithms
• 🧪 Ready-to-run examples and scripts

---

📊 Datasets for partially labeled medical image segmentation.

Some information and download links of the partially labeled learning datasets can be found in this Link.

---

🔬 Code for partially labeled medical image segmentation.

Some implementations of partially labeled learning methods can be found in this Link.

---

📖 Literature reviews of partially labeled learning approach for medical image segmentation (PLS4MIS)

Date	The First and Last Authors	Title	Code	Reference
2025-10	Z. Zhang and X. Duan	AMOTS: Partially supervised framework for abdominal multi-organ and tumor segmentation via aspect-aware complementary	Code	AIMed2025
2025-09	X. Liu and Z. Song	Deep Mutual Learning among Partially Labeled Datasets for Multi-Organ Segmentation	None	TMI2025
2025-09	S. Zhu and J. Hu	Visual prompt-driven universal model for medical image segmentation in radiotherapy	None	KBS2025
2025-07	H. Gong and H. Li	Boundary as the Bridge: Toward Heterogeneous Partially-Labeled Medical Image Segmentation and Landmark Detection	Code	TMI2025
2025-01	X. Jiang and X. Yang	Labeled-to-unlabeled distribution alignment for partially-supervised multi-organ medical image segmentation	Code	MedIA2025
2024-11	Q. Liu and Y. Liang	Many birds, one stone: Medical image segmentation with multiple partially labeled datasets	Code	PR2024
2024-10	J. Liu and Z. Zhou	Universal and extensible language-vision models for organ segmentation and tumor detection from abdominal computed tomography	Code	MedIA2024
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
2024-03	Y. Gao and DN. Metaxas	Training like a medical resident: Context-prior learning toward universal medical image segmentation	Code	CVPR2024
2024-03	X. Chen and Y. Fan	Versatile medical image segmentation learned from multi-source datasets via model self-disambiguation	None	CVPR2024
2024-02	H. Wang and S. Wan	A multi-objective segmentation method for chest X-rays based on collaborative learning from multiple partially annotated datasets	None	InfFusion2024
2023-10	Y. Ye and Y. Xia	Uniseg: A prompt-driven universal segmentation model as well as a strong representation learner	Code	MICCAI2023
2023-10	C. Ulrich and KH. Maier-Hein	MultiTalent: A Multi-dataset Approach to Medical Image Segmentation	Code	MICCAI2023
2023-09	Y. Xie and C. Shen	Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation	Code	TPAMI2023
2023-09	R. Deng and Y. Huo	Omni-seg: A scale-aware dynamic network for renal pathological image segmentation	Code	TBME2023
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
2020-09	R. Huang and H. Li	Multi-organ segmentation via co-training weight-averaged models from few-organ datasets	None	MICCAI2020
2019-11	Y. Zhou and AL. Yuille	Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation	None	ICCV2019
2019-06	K. Dmitriev and AE. Kaufman	Learning multi-class segmentations from single-class datasets	None	CVPR2019

---

❓ Questions and Suggestions

We welcome contributions, suggestions, and collaborations!

• 📧 Email: lihe200203@gmail.com
• 💬 QQ Group (Chinese): 906808850