Customized Segment Anything Model for Medical Image Segmentation

TL;DR

SAMed is a novel approach that fine-tunes a large-scale segmentation model, SAM, for medical image segmentation, achieving competitive results with minimal parameter updates and low deployment costs.

Contribution

The paper introduces SAMed, a method for customizing SAM for medical images using LoRA finetuning, enabling effective segmentation with reduced computational costs.

Findings

SAMed achieves 81.88 DSC on Synapse dataset.

SAMed's fine-tuning approach is efficient and cost-effective.

Results are comparable to state-of-the-art methods.

Abstract

We propose SAMed, a general solution for medical image segmentation. Different from the previous methods, SAMed is built upon the large-scale image segmentation model, Segment Anything Model (SAM), to explore the new research paradigm of customizing large-scale models for medical image segmentation. SAMed applies the low-rank-based (LoRA) finetuning strategy to the SAM image encoder and finetunes it together with the prompt encoder and the mask decoder on labeled medical image segmentation datasets. We also observe the warmup finetuning strategy and the AdamW optimizer lead SAMed to successful convergence and lower loss. Different from SAM, SAMed could perform semantic segmentation on medical images. Our trained SAMed model achieves 81.88 DSC and 20.64 HD on the Synapse multi-organ segmentation dataset, which is on par with the state-of-the-art methods. We conduct extensive experiments to validate the effectiveness of our design. Since SAMed only updates a small fraction of the SAM parameters, its deployment cost and storage cost are quite marginal in practical usage. The code of SAMed is available at https://github.com/hitachinsk/SAMed.