SAM-Med2D

TL;DR

This paper adapts the Segment Anything Model (SAM) for medical image segmentation by creating a large-scale dataset, comprehensive fine-tuning, and extensive evaluation, significantly improving performance and generalization in medical imaging tasks.

Contribution

The paper introduces SAM-Med2D, a fine-tuned version of SAM for medical images, utilizing a large dataset and multiple prompt types for improved segmentation accuracy.

Findings

SAM-Med2D outperforms original SAM in medical segmentation tasks.

Fine-tuning on 4.6M images enhances domain adaptation.

SAM-Med2D generalizes well across diverse datasets.

Abstract

The Segment Anything Model (SAM) represents a state-of-the-art research advancement in natural image segmentation, achieving impressive results with input prompts such as points and bounding boxes. However, our evaluation and recent research indicate that directly applying the pretrained SAM to medical image segmentation does not yield satisfactory performance. This limitation primarily arises from significant domain gap between natural images and medical images. To bridge this gap, we introduce SAM-Med2D, the most comprehensive studies on applying SAM to medical 2D images. Specifically, we first collect and curate approximately 4.6M images and 19.7M masks from public and private datasets, constructing a large-scale medical image segmentation dataset encompassing various modalities and objects. Then, we comprehensively fine-tune SAM on this dataset and turn it into SAM-Med2D. Unlike previous methods that only adopt bounding box or point prompts as interactive segmentation approach, we adapt SAM to medical image segmentation through more comprehensive prompts involving bounding boxes, points, and masks. We additionally fine-tune the encoder and decoder of the original SAM to obtain a well-performed SAM-Med2D, leading to the most comprehensive fine-tuning strategies to date. Finally, we conducted a comprehensive evaluation and analysis to investigate the performance of SAM-Med2D in medical image segmentation across various modalities, anatomical structures, and organs. Concurrently, we validated the generalization capability of SAM-Med2D on 9 datasets from MICCAI 2023 challenge. Overall, our approach demonstrated significantly superior performance and generalization capability compared to SAM.