SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-Training
- 3 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 1636-1651
Abstract
Medical image segmentation is a critical yet challenging task, primarily due to the difficulty of obtaining extensive datasets of high-quality, expert-annotated images. Contrastive learning presents a potential but still problematic solution to this issue. Because most existing methods focus on extracting instance-level or pixel-to-pixel representation, which ignores the characteristics between intra-image similar pixel groups. Moreover, when considering contrastive pairs generation, most SOTA methods mainly rely on manually setting thresholds, which requires a large number of gradient experiments and lacks efficiency and generalization. To address these issues, we propose a novel contrastive learning approach named SuperCL for medical image segmentation pre-training. Specifically, our SuperCL exploits the structural prior and pixel correlation of images by introducing two novel contrastive pairs generation strategies: Intra-image Local Contrastive Pairs (ILCP) Generation and Inter-image Global Contrastive Pairs (IGCP) Generation. Considering superpixel cluster aligns well with the concept of contrastive pairs generation, we utilize the superpixel map to generate pseudo masks for both ILCP and IGCP to guide supervised contrastive learning. Moreover, we also propose two modules named Average SuperPixel Feature Map Generation (ASP) and Connected Components Label Generation (CCL) to better exploit the prior structural information for IGCP. Finally, experiments on 8 medical image datasets indicate our SuperCL outperforms existing 12 methods. i.e. Our SuperCL achieves a superior performance with more precise predictions from visualization figures and 3.15%, 5.44%, 7.89% DSC higher than the previous best results on MMWHS, CHAOS, Spleen with 10% annotations. Our code is released at https://github.com/stevezs315/SuperCL.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (82371112)
- National Natural Science Foundation of China (62501020)
- National Key Research and Development Program of China (2025YFA1805700)
- Science Foundation of Peking University Cancer Hospital (JC202505)
- China National Postdoctoral Program for Innovative Talents (BX20250368)
- Peking University Medicine Plus X Pilot Program-Artificial Intelligence and Medical Development Initiative
This publication has 53 references indexed in Scilit:
- Low-Rank Mixture-of-Experts for Continual Medical Image Segmentation2024
- MedNeXt: Transformer-Driven Scaling of ConvNets for Medical Image Segmentation2023
- MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets2023
- DeSD: Self-Supervised Learning with Deep Self-Distillation for 3D Medical Image Segmentation2022
- Positional Contrastive Learning for Volumetric Medical Image Segmentation2021
- SimTriplet: Simple Triplet Representation Learning with a Single GPU2021
- Shape-Aware Semi-supervised 3D Semantic Segmentation for Medical Images2020
- Whole Heart and Great Vessel Segmentation in Congenital Heart Disease Using Deep Neural Networks and Graph Matching2019
- Uncertainty-Aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation2019
- Superpixel Sampling Networks2018