Pith. sign in

REVIEW 2 cited by

How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Model

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.09957 v3 pith:B6QAWTU6 submitted 2024-04-15 cs.CV cs.LG

classification cs.CVcs.LG
keywords fine-tuningmodelsegmentationimageperformancefoundationlearningmedical
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Automated segmentation is a fundamental medical image analysis task, which enjoys significant advances due to the advent of deep learning. While foundation models have been useful in natural language processing and some vision tasks for some time, the foundation model developed with image segmentation in mind - Segment Anything Model (SAM) - has been developed only recently and has shown similar promise. However, there are still no systematic analyses or "best-practice" guidelines for optimal fine-tuning of SAM for medical image segmentation. This work summarizes existing fine-tuning strategies with various backbone architectures, model components, and fine-tuning algorithms across 18 combinations, and evaluates them on 17 datasets covering all common radiology modalities. Our study reveals that (1) fine-tuning SAM leads to slightly better performance than previous segmentation methods, (2) fine-tuning strategies that use parameter-efficient learning in both the encoder and decoder are superior to other strategies, (3) network architecture has a small impact on final performance, (4) further training SAM with self-supervised learning can improve final model performance. We also demonstrate the ineffectiveness of some methods popular in the literature and further expand our experiments into few-shot and prompt-based settings. Lastly, we released our code and MRI-specific fine-tuned weights, which consistently obtained superior performance over the original SAM, at https://github.com/mazurowski-lab/finetune-SAM.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Are Vision Foundation Models Ready for Out-of-the-Box Medical Image Registration?

    eess.IV 2025-07 conditional novelty 6.0 of 10

    On a benchmark of four breast MRI registration tasks, the SAM encoder outperforms classical optimization methods for gross breast alignment but not for fine fibroglandular tissue, and medical pre-training did not help.

  2. SegmentAnyMuscle: A universal muscle segmentation model across different locations in MRI

    eess.SP 2025-06 conditional novelty 6.0 of 10

    A publicly released MRI muscle segmentation model, trained on a new 316-exam single-center dataset, reaches DSC 88.45% on common sequences and 86.21% on challenging cases across 11 body locations.

Pith tools