A Few Cases Are All You Need: An Empirical Study of Annotation-Efficient LoRA Fine-Tuning of MedSAM3

• URL: http://arxiv.org/abs/2608.18731v1
• Date: Wed, 19 Aug 2026 09:34:34 GMT
• Title: A Few Cases Are All You Need: An Empirical Study of Annotation-Efficient LoRA Fine-Tuning of MedSAM3
• Abstract summary: We adapt MedSAM3 with LoRA for five abdominal organs in CT and MRI using only 1, 2, 5, and 10 annotated cases, evaluating on AMOS22 dataset.<n>With just 10 annotated cases, models achieve performance competitive with specialist systems trained on orders of magnitude more data.<n>These findings suggest that ten annotated cases are sufficient for clinically useful segmentation, effectively reducing bottlenecks for both image annotation and training time.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical image segmentation is essential for clinical workflows such as treatment planning and disease assessment. While specialist tools like TotalSegmentator and MRSegmentator achieve strong performance, they require large annotated datasets for training. Medical foundation models offer a promising alternative through large-scale pretraining that reduces the annotation burden for new tasks, but zero-shot performance remains limited. Parameter-efficient adaptation via Low-Rank Adaptation (LoRA) enables efficient specialization with few trainable parameters, but a key question remains: how many expert-annotated cases are needed to achieve clinically useful segmentation performance? We address this by adapting MedSAM3 with LoRA for five abdominal organs (liver, kidneys, spleen, gallbladder, and pancreas) in CT and MRI using only 1, 2, 5, and 10 annotated cases, evaluating on AMOS22 dataset. With just 10 cases, models achieve performance competitive with specialist systems trained on orders of magnitude more data. Notably, this includes reliable gallbladder segmentation (Dice 0.68 CT, 0.59 MRI) where existing tools fail almost completely (Dice 0.0004), while remaining within 5--10% of MRSegmentator for liver, kidneys, and spleen using over 100 times fewer annotations. Furthermore, external validation on the Whole Heart Segmentation dataset shows that the approach extends to cardiac segmentation, a use case beyond the scope of TotalSegmentator (MRI) and MRSegmentator, achieving competitive left ventricle (LV) performance with only 10 annotated cases. Training requires only3--5,hours per organ on a single GPU, approximately 2--3 times faster than nnU-Net. These findings suggest that ten annotated cases are sufficient for clinically useful segmentation, effectively reducing bottlenecks for both image annotation and training time.

Related papers

• Segmentation Pre-training for Label-Efficient Lumbar Spine Degeneration Grading [0.0]
  We pre-train a 3D ResNet encoder to segment the vertebrae, intervertebral discs (IVDs), and the spinal canal.<n>We fine-tune lightweight task-specific grading heads using different proportions of the available training data.<n>With only 20% of grading labels after pre-training, the method achieved near full-supervision performance.
  arXiv  Detail & Related papers  (2026-08-05T13:14:46Z)
• DINO-MVR: Multi-View Readout of Frozen DINOv3 for Annotation-Efficient Medical Segmentation [10.929173865297933]
  We show that frozen DINOv3 features already contain useful structural and boundary cues for medical segmentation.<n>We propose DINO-MVR, a Multi-View Readout framework for annotation-efficient medical segmentation.
  arXiv  Detail & Related papers  (2026-05-08T04:13:01Z)
• Automated Prostate Gland Segmentation in MRI Using nnU-Net [0.14777718769290524]
  We propose a dedicated deep learning-based approach for automatic prostate gland segmentation using the nnUNet v2 framework.<n>The proposed model achieved a mean Dice score of 0.96 +/- 0.00 in cross-validation and 0.82 on the external test set, demonstrating strong generalization despite domain shift.
  arXiv  Detail & Related papers  (2026-04-02T12:28:03Z)
• 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)
• J-RAS: Enhancing Medical Image Segmentation via Retrieval-Augmented Joint Training [0.0]
  We propose a joint training method for guided image segmentation that integrates a segmentation model with a retrieval model.<n>Both models are optimized, enabling the segmentation model to leverage retrieved image-mask pairs to enrich anatomical understanding.<n>We validate J-RAS across multiple segmentation backbones, including U-Net, TransUNet, SAM, and SegFormer, on two benchmark datasets.
  arXiv  Detail & Related papers  (2025-10-11T01:53:28Z)
• A Continual Learning-driven Model for Accurate and Generalizable Segmentation of Clinically Comprehensive and Fine-grained Whole-body Anatomies in CT [67.34586036959793]
  There is no fully annotated CT dataset with all anatomies delineated for training.<n>We propose a novel continual learning-driven CT model that can segment complete anatomies.<n>Our single unified CT segmentation model, CL-Net, can highly accurately segment a clinically comprehensive set of 235 fine-grained whole-body anatomies.
  arXiv  Detail & Related papers  (2025-03-16T23:55:02Z)
• Assessing Foundational Medical 'Segment Anything' (Med-SAM1, Med-SAM2) Deep Learning Models for Left Atrial Segmentation in 3D LGE MRI [0.0]
  Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with heart failure and stroke. Deep learning models, such as the Segment Anything Model (SAM), pre-trained on diverse datasets, have demonstrated promise in generic segmentation tasks. Despite the potential of MedSAM model, it has not yet been evaluated for the complex task of LA segmentation in 3D LGE-MRI.
  arXiv  Detail & Related papers  (2024-11-08T20:49:54Z)
• Self-calibrated convolution towards glioma segmentation [45.74830585715129]
  We evaluate self-calibrated convolutions in different parts of the nnU-Net network to demonstrate that self-calibrated modules in skip connections can significantly improve the enhanced-tumor and tumor-core segmentation accuracy.
  arXiv  Detail & Related papers  (2024-02-07T19:51:13Z)
• Learned Local Attention Maps for Synthesising Vessel Segmentations [43.314353195417326]
  We present an encoder-decoder model for synthesising segmentations of the main cerebral arteries in the circle of Willis (CoW) from only T2 MRI. It uses learned local attention maps generated by dilating the segmentation labels, which forces the network to only extract information from the T2 MRI relevant to synthesising the CoW.
  arXiv  Detail & Related papers  (2023-08-24T15:32:27Z)
• Domain Transfer Through Image-to-Image Translation for Uncertainty-Aware Prostate Cancer Classification [42.75911994044675]
  We present a novel approach for unpaired image-to-image translation of prostate MRIs and an uncertainty-aware training approach for classifying clinically significant PCa. Our approach involves a novel pipeline for translating unpaired 3.0T multi-parametric prostate MRIs to 1.5T, thereby augmenting the available training data. Our experiments demonstrate that the proposed method significantly improves the Area Under ROC Curve (AUC) by over 20% compared to the previous work.
  arXiv  Detail & Related papers  (2023-07-02T05:26:54Z)
• Segmentation of the Myocardium on Late-Gadolinium Enhanced MRI based on 2.5 D Residual Squeeze and Excitation Deep Learning Model [55.09533240649176]
  The aim of this work is to develop an accurate automatic segmentation method based on deep learning models for the myocardial borders on LGE-MRI. A total number of 320 exams (with a mean number of 6 slices per exam) were used for training and 28 exams used for testing. The performance analysis of the proposed ensemble model in the basal and middle slices was similar as compared to intra-observer study and slightly lower at apical slices.
  arXiv  Detail & Related papers  (2020-05-27T20:44:38Z)
• A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging [90.29017019187282]
  " 2018 Left Atrium Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset. Analyse of the submitted algorithms using technical and biological metrics was performed. Results show the top method achieved a dice score of 93.2% and a mean surface to a surface distance of 0.7 mm.
  arXiv  Detail & Related papers  (2020-04-26T08:49:17Z)

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.