# Beyond Visual Cues: CoT-Enhanced Reasoning for Semi-supervised Medical Image Segmentation

arXiv: https://arxiv.org/abs/2606.17958 · HTML: https://mlsanity.com/paper/2606.17958/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [Medical Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2009.13120/) (2020)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2305.00673/) (2023)
- [LViT: Language meets Vision Transformer in Medical Image Segmentation](https://mlsanity.com/paper/2206.14718/) (2022)
- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [OSegNet: Operational Segmentation Network for COVID-19 Detection using Chest X-ray Images](https://mlsanity.com/paper/2202.10185/) (2022)
- [Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2301.04465/) (2023)
- [Retrieval-augmented Few-shot Medical Image Segmentation with Foundation Models](https://mlsanity.com/paper/2408.08813/) (2024)
- [SimTxtSeg: Weakly-Supervised Medical Image Segmentation with Simple Text Cues](https://mlsanity.com/paper/2406.19364/) (2024)
- [Dual Cross-image Semantic Consistency with Self-aware Pseudo Labeling for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2507.21440/) (2025)
- [Combating Ambiguity for Hash-code Learning in Medical Instance Retrieval](https://mlsanity.com/paper/2105.08872/) (2021)
- [CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learning](https://mlsanity.com/paper/2603.05911/) (2026)

## Abstract (arXiv)

Semi-supervised medical image segmentation has emerged as a dominant research problem in medical image analysis, mitigating annotation scarcity by leveraging consistency regularization on unlabeled data. However, existing approaches operate predominantly via visual pattern matching, relying heavily on pixel-level similarities. This visual-centric dependency often falters in clinical scenarios characterized by the visual-semantic mismatch, where visually similar lesions warrant distinct diagnostic conclusions, thus failing to capture the underlying diagnostic logic used by experts. To address this, we move beyond visual cues and propose CERS (CoT-Enhanced Reasoning Segmentation), a framework that integrates Chain-of-Thought (CoT) reasoning to distinguish pathologically distinct cases. Specifically, we construct a knowledge pool enriched with linguistic reasoning descriptions generated by large language models (LLMs). A semantic-aware reference selection strategy is introduced to identify historical evidence, filtering candidates first by morphology, and then refining them via CoT consistency to eliminate hard negatives. Furthermore, a multi-scale coordinate attention module (MCAM) is designed to effectively fuse this reasoning-derived context into the decoding process. Extensive experiments demonstrate the superiority of CERS against state-of-the-art approaches, particularly in resolving boundary ambiguities and semantic inconsistencies. The code is available at https://github.com/cymasuna/CERS.