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

• URL: http://arxiv.org/abs/2503.06816v1
• Date: Mon, 10 Mar 2025 00:43:45 GMT
• Title: Semi-Supervised Medical Image Segmentation via Knowledge Mining from Large Models
• Authors: Yuchen Mao, Hongwei Li, Yinyi Lai, Giorgos Papanastasiou, Peng Qi, Yunjie Yang, Chengjia Wang,
• Abstract summary: This study introduces a strategic knowledge mining method to boost the performance of small, locally hosted deep learning models.<n>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.<n>Our proposed method consistently enhanced the segmentation performance on Dice by 3% and 1% respectively over the baseline U-Net++ model.
• Score: 7.470921455418383
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Task-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image Segmentation [13.018234326432964]
  We propose a novel and generalizable task-specific knowledge distillation framework for medical image segmentation.<n>Our method fine-tunes the VFM on the target segmentation task to capture task-specific features before distilling the knowledge to smaller models.<n> Experimental results across five medical image datasets demonstrate that our method consistently outperforms task-agnostic knowledge distillation.
  arXiv  Detail & Related papers  (2025-03-10T06:39:53Z)
• Medical Image Segmentation with SAM-generated Annotations [12.432602118806573]
  We evaluate the performance of the Segment Anything Model (SAM) as an annotation tool for medical data. We generate so-called "pseudo labels" on the Medical Decathlon (MSD) computed tomography (CT) tasks. The pseudo labels are then used in place of ground truth labels to train a UNet model in a weakly-supervised manner.
  arXiv  Detail & Related papers  (2024-09-30T12:43:20Z)
• Adapting Segment Anything Model for Unseen Object Instance Segmentation [70.60171342436092]
  Unseen Object Instance (UOIS) is crucial for autonomous robots operating in unstructured environments. We propose UOIS-SAM, a data-efficient solution for the UOIS task. UOIS-SAM integrates two key components: (i) a Heatmap-based Prompt Generator (HPG) to generate class-agnostic point prompts with precise foreground prediction, and (ii) a Hierarchical Discrimination Network (HDNet) that adapts SAM's mask decoder.
  arXiv  Detail & Related papers  (2024-09-23T19:05:50Z)
• Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation [17.69933345468061]
  scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation. We introduce a textbfVersatile textbfSemi-supervised framework to exploit more unlabeled data for semi-supervised medical image segmentation.
  arXiv  Detail & Related papers  (2023-11-20T11:35:52Z)
• A Simple and Efficient Baseline for Data Attribution on Images [107.12337511216228]
  Current state-of-the-art approaches require a large ensemble of as many as 300,000 models to accurately attribute model predictions. In this work, we focus on a minimalist baseline, utilizing the feature space of a backbone pretrained via self-supervised learning to perform data attribution. Our method is model-agnostic and scales easily to large datasets.
  arXiv  Detail & Related papers  (2023-11-03T17:29:46Z)
• Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning [53.00683059396803]
  Mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images. We propose a decision-based MIM that utilizes reinforcement learning (RL) to automatically search for optimal image masking ratio and masking strategy. Our approach has a significant advantage over alternative self-supervised methods on the task of neuron segmentation.
  arXiv  Detail & Related papers  (2023-10-06T10:40:46Z)
• nnSAM: Plug-and-play Segment Anything Model Improves nnUNet Performance [12.169801149021566]
  The Segment Anything Model (SAM) has emerged as a versatile tool for image segmentation without specific domain training. Traditional models like nnUNet perform automatic segmentation during inference but need extensive domain-specific training. We propose nnSAM, integrating SAM's robust feature extraction with nnUNet's automatic configuration to enhance segmentation accuracy on small datasets.
  arXiv  Detail & Related papers  (2023-09-29T04:26:25Z)
• Ladder Fine-tuning approach for SAM integrating complementary network [5.46706034286531]
  In medical imaging, the lack of training samples due to privacy concerns and other factors presents a major challenge for applying these generalized models to medical image segmentation task. In this study, we propose to combine a complementary Convolutional Neural Network (CNN) along with the standard SAM network for medical image segmentation. This strategy significantly reduces trainnig time and achieves competitive results on publicly available dataset.
  arXiv  Detail & Related papers  (2023-06-22T08:36:17Z)
• Learnable Weight Initialization for Volumetric Medical Image Segmentation [66.3030435676252]
  We propose a learnable weight-based hybrid medical image segmentation approach. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-15T17:55:05Z)
• CHALLENGER: Training with Attribution Maps [63.736435657236505]
  We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. In particular, we show that our generic domain-independent approach yields state-of-the-art results in vision, natural language processing and on time series tasks.
  arXiv  Detail & Related papers  (2022-05-30T13:34:46Z)
• Hierarchical Self-Supervised Learning for Medical Image Segmentation Based on Multi-Domain Data Aggregation [23.616336382437275]
  We propose Hierarchical Self-Supervised Learning (HSSL) for medical image segmentation. We first aggregate a dataset from several medical challenges, then pre-train the network in a self-supervised manner, and finally fine-tune on labeled data. Compared to learning from scratch, our new method yields better performance on various tasks.
  arXiv  Detail & Related papers  (2021-07-10T18:17:57Z)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.