# Semi-Supervised Medical Image Segmentation via Knowledge Mining from Large Models

arXiv: https://arxiv.org/abs/2503.06816 · HTML: https://mlsanity.com/paper/2503.06816/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 26 of 26)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://mlsanity.com/paper/2303.11381/) (2023)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation](https://mlsanity.com/paper/2206.08023/) (2022)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [Can AI help in screening Viral and COVID-19 pneumonia?](https://mlsanity.com/paper/2003.13145/) (2020)
- [Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging](https://mlsanity.com/paper/2304.04155/) (2023)
- [Caption Anything: Interactive Image Description with Diverse Multimodal Controls](https://mlsanity.com/paper/2305.02677/) (2023)
- [DMT: Dynamic Mutual Training for Semi-Supervised Learning](https://mlsanity.com/paper/2004.08514/) (2020)
- [Input Augmentation with SAM: Boosting Medical Image Segmentation with Segmentation Foundation Model](https://mlsanity.com/paper/2304.11332/) (2023)
- [Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentation](https://mlsanity.com/paper/2201.08657/) (2022)
- [COVID-19 Infection Localization and Severity Grading from Chest X-ray Images](https://mlsanity.com/paper/2103.07985/) (2021)
- [All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning](https://mlsanity.com/paper/2307.00290/) (2023)
- [Using DUCK-Net for Polyp Image Segmentation](https://mlsanity.com/paper/2311.02239/) (2023)
- [SAM-Path: A Segment Anything Model for Semantic Segmentation in Digital Pathology](https://mlsanity.com/paper/2307.09570/) (2023)
- [Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models](https://mlsanity.com/paper/2310.12995/) (2023)
- [Boosting Medical Image Classification with Segmentation Foundation Model](https://mlsanity.com/paper/2406.11026/) (2024)
- [Segment Anything Model for Brain Tumor Segmentation](https://mlsanity.com/paper/2309.08434/) (2023)

## Built on by (most cited first, 1 of 1)

- [Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates](https://mlsanity.com/paper/2504.02008/) (2025)

## Abstract (arXiv)

Large-scale vision models like SAM have extensive visual knowledge, yet their general nature and computational demands limit their use in specialized tasks like medical image segmentation. In contrast, task-specific models such as U-Net++ often underperform due to sparse labeled data. This study introduces a strategic knowledge mining method that leverages SAM's broad understanding to boost the performance of small, locally hosted deep learning models. In our approach, we trained a U-Net++ model on a limited labeled dataset and extend its capabilities by converting SAM's output infered on unlabeled images into prompts. This process not only harnesses SAM's generalized visual knowledge but also iteratively improves SAM's prediction to cater specialized medical segmentation tasks via U-Net++. The mined knowledge, serving as "pseudo labels", enriches the training dataset, enabling the fine-tuning of the local network. Applied to the Kvasir SEG and COVID-QU-Ex datasets which consist of gastrointestinal polyp and lung X-ray images respectively, our proposed method consistently enhanced the segmentation performance on Dice by 3% and 1% respectively over the baseline U-Net++ model, when the same amount of labelled data were used during training (75% and 50% of labelled data). Remarkably, our proposed method surpassed the baseline U-Net++ model even when the latter was trained exclusively on labeled data (100% of labelled data). These results underscore the potential of knowledge mining to overcome data limitations in specialized models by leveraging the broad, albeit general, knowledge of large-scale models like SAM, all while maintaining operational efficiency essential for clinical applications.