SSL-MedSAM2: A Semi-supervised Medical Image Segmentation Framework Powered by Few-shot Learning of SAM2

• URL: http://arxiv.org/abs/2512.11548v1
• Date: Fri, 12 Dec 2025 13:33:38 GMT
• Title: SSL-MedSAM2: A Semi-supervised Medical Image Segmentation Framework Powered by Few-shot Learning of SAM2
• Abstract summary: Semi-supervised learning has emerged as an appealing strategy in training with limited annotations.<n>We propose a novel SSL framework SSL-MedSAM2, which contains a training-free few-shot learning branch TFFS-MedSAM2 for pseudo label generation.<n>The results on MICCAI2025 challenge demonstrate an outstanding performance of SSL-MedSAM2 among other methods.
• Score: 4.5218971269045225
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the success of deep learning based models in medical image segmentation, most state-of-the-art (SOTA) methods perform fully-supervised learning, which commonly rely on large scale annotated training datasets. However, medical image annotation is highly time-consuming, hindering its clinical applications. Semi-supervised learning (SSL) has been emerged as an appealing strategy in training with limited annotations, largely reducing the labelling cost. We propose a novel SSL framework SSL-MedSAM2, which contains a training-free few-shot learning branch TFFS-MedSAM2 based on the pretrained large foundation model Segment Anything Model 2 (SAM2) for pseudo label generation, and an iterative fully-supervised learning branch FSL-nnUNet based on nnUNet for pseudo label refinement. The results on MICCAI2025 challenge CARE-LiSeg (Liver Segmentation) demonstrate an outstanding performance of SSL-MedSAM2 among other methods. The average dice scores on the test set in GED4 and T1 MRI are 0.9710 and 0.9648 respectively, and the Hausdorff distances are 20.07 and 21.97 respectively. The code is available via https://github.com/naisops/SSL-MedSAM2/tree/main.

Related papers

• VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel [68.24765319399286]
  We present VesSAM, a powerful and efficient framework tailored for 2D vessel segmentation.<n>VesSAM integrates (1) a convolutional adapter to enhance local texture features, (2) a multi-prompt encoder that fuses anatomical prompts, and (3) a lightweight mask decoder to reduce jagged artifacts.<n>VesSAM consistently outperforms state-of-the-art PEFT-based SAM variants by over 10% Dice and 13% IoU.
  arXiv  Detail & Related papers  (2025-11-02T15:47:05Z)
• Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image Segmentation [47.789013598970925]
  We propose a learnable prompting SAM-induced Knowledge distillation framework (KnowSAM) for semi-supervised medical image segmentation.<n>Our model outperforms the state-of-the-art semi-supervised segmentation approaches.
  arXiv  Detail & Related papers  (2024-12-18T11:19:23Z)
• Annotation-Efficient Task Guidance for Medical Segment Anything [0.31077024712075796]
  Medical image segmentation is a key task in the imaging workflow, influencing many image-based decisions.<n>Traditional, fully-supervised segmentation models rely on large amounts of labeled training data, which can be an expensive, time-consuming, and error-prone process.<n>We propose SAM-Mix, a novel multitask learning framework for medical image segmentation.
  arXiv  Detail & Related papers  (2024-12-11T17:47:00Z)
• Cross Prompting Consistency with Segment Anything Model for Semi-supervised Medical Image Segmentation [44.54301473673582]
  Semi-supervised learning (SSL) has achieved notable progress in medical image segmentation. Recent developments in visual foundation models, such as the Segment Anything Model (SAM), have demonstrated remarkable adaptability. We propose a cross-prompting consistency method with segment anything model (CPC-SAM) for semi-supervised medical image segmentation.
  arXiv  Detail & Related papers  (2024-07-07T15:43:20Z)
• Wound Tissue Segmentation in Diabetic Foot Ulcer Images Using Deep Learning: A Pilot Study [5.397013836968946]
  We have created a DFUTissue dataset for the research community to evaluate wound tissue segmentation algorithms. The dataset contains 110 images with tissues labeled by wound experts and 600 unlabeled images. Due to the limited amount of annotated data, our framework consists of both supervised learning (SL) and semi-supervised learning (SSL) phases.
  arXiv  Detail & Related papers  (2024-06-23T05:01:51Z)
• ASLseg: Adapting SAM in the Loop for Semi-supervised Liver Tumor Segmentation [2.3617131367115705]
  Liver tumor segmentation is essential for computer-aided diagnosis, surgical planning, and prognosis evaluation. Semi-Supervised Learning (SSL) is a common technique to address these challenges. We propose a novel semi-supervised framework, named ASLseg, which can effectively adapt the SAM to the SSL setting.
  arXiv  Detail & Related papers  (2023-12-13T08:31:26Z)
• Are foundation models efficient for medical image segmentation? [0.8158530638728501]
  The Segment Anything model (SAM) asserts an ability to segment a wide spectrum of objects but required supervised training at unprecedented scale. We compared SAM's performance (against clinical ground truth) and resources (labeling time, compute) to a modality-specific, label-free self-supervised learning (SSL) method on 25 measurements for 100 cardiac ultrasounds.
  arXiv  Detail & Related papers  (2023-11-08T17:33:09Z)
• SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation [65.52097667738884]
  We introduce SurgicalSAM, a novel end-to-end efficient-tuning approach for SAM to integrate surgical-specific information with SAM's pre-trained knowledge for improved generalisation. Specifically, we propose a lightweight prototype-based class prompt encoder for tuning, which directly generates prompt embeddings from class prototypes. In addition, to address the low inter-class variance among surgical instrument categories, we propose contrastive prototype learning.
  arXiv  Detail & Related papers  (2023-08-17T02:51:01Z)
• ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images [47.43840961882509]
  Self-supervised learning is appealing to such annotation-heavy tasks. We first benchmark representative SSL methods for dense prediction tasks in pathology images. We propose concept contrastive learning (ConCL), an SSL framework for dense pre-training.
  arXiv  Detail & Related papers  (2022-07-14T08:38:17Z)
• A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning [54.617688468341704]
  Few-shot learning aims to learn models that generalize to novel classes with limited training samples. We propose a novel paradigm containing two parts: (1) a well-designed meta-training algorithm for mitigating ambiguity between base and novel classes caused by unreliable pseudo labels and (2) a model adaptation mechanism to learn discriminative features for novel classes while preserving base knowledge using few labeled and all the unlabeled data.
  arXiv  Detail & Related papers  (2021-10-21T13:25:52Z)
• Medical Instrument Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning [62.13520959168732]
  We propose a semi-supervised learning framework for instrument segmentation in 3D US. To achieve the SSL learning, a Dual-UNet is proposed to segment the instrument. Our proposed method achieves Dice score of about 68.6%-69.1% and the inference time of about 1 sec. per volume.
  arXiv  Detail & Related papers  (2021-07-30T07:59:45Z)
• Self-Supervised Learning of Graph Neural Networks: A Unified Review [50.71341657322391]
  Self-supervised learning is emerging as a new paradigm for making use of large amounts of unlabeled samples. We provide a unified review of different ways of training graph neural networks (GNNs) using SSL. Our treatment of SSL methods for GNNs sheds light on the similarities and differences of various methods, setting the stage for developing new methods and algorithms.
  arXiv  Detail & Related papers  (2021-02-22T03:43:45Z)

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.