# Boosting Semi-Supervised Medical Image Segmentation via Masked Image Consistency and Discrepancy Learning

arXiv: https://arxiv.org/abs/2503.14013 · HTML: https://mlsanity.com/paper/2503.14013/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 20 of 20)

- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation](https://mlsanity.com/paper/2206.08023/) (2022)
- [Semi-supervised Medical Image Segmentation through Dual-task Consistency](https://mlsanity.com/paper/2009.04448/) (2020)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Guided Collaborative Training for Pixel-wise Semi-Supervised Learning](https://mlsanity.com/paper/2008.05258/) (2020)
- [Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2111.12903/) (2021)
- [Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency](https://mlsanity.com/paper/2012.07042/) (2020)
- [Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2203.01324/) (2022)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [Debiased Self-Training for Semi-Supervised Learning](https://mlsanity.com/paper/2202.07136/) (2022)
- [Calibrating Label Distribution for Class-Imbalanced Barely-Supervised Knee Segmentation](https://mlsanity.com/paper/2205.03644/) (2022)
- [RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2301.05500/) (2023)
- [DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2307.11960/) (2023)
- [Addressing Class Imbalance in Semi-supervised Image Segmentation: A Study on Cardiac MRI](https://mlsanity.com/paper/2209.00123/) (2022)
- [An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2211.11086/) (2022)
- [Semi-supervised Semantic Segmentation Meets Masked Modeling:Fine-grained Locality Learning Matters in Consistency Regularization](https://mlsanity.com/paper/2312.08631/) (2023)

## Abstract (arXiv)

Semi-supervised learning is of great significance in medical image segmentation by exploiting unlabeled data. Among its strategies, the co-training framework is prominent. However, previous co-training studies predominantly concentrate on network initialization variances and pseudo-label generation, while overlooking the equilibrium between information interchange and model diversity preservation. In this paper, we propose the Masked Image Consistency and Discrepancy Learning (MICD) framework with three key modules. The Masked Cross Pseudo Consistency (MCPC) module enriches context perception and small sample learning via pseudo-labeling across masked-input branches. The Cross Feature Consistency (CFC) module fortifies information exchange and model robustness by ensuring decoder feature consistency. The Cross Model Discrepancy (CMD) module utilizes EMA teacher networks to oversee outputs and preserve branch diversity. Together, these modules address existing limitations by focusing on fine-grained local information and maintaining diversity in a heterogeneous framework. Experiments on two public medical image datasets, AMOS and Synapse, demonstrate that our approach outperforms state-of-the-art methods.