Segmentation of Gray Matters and White Matters from Brain MRI data

TL;DR

This paper adapts the foundation model MedSAM for multi-class brain tissue segmentation in MRI, achieving high accuracy with minimal architectural changes.

Contribution

It introduces a modified MedSAM model for multi-class brain tissue segmentation, extending its capabilities with minimal architectural adjustments.

Findings

Achieved Dice scores up to 0.8751 on the IXI dataset.

Demonstrated foundation models can be adapted for multi-class medical segmentation.

Minimal modifications to MedSAM suffice for effective brain tissue segmentation.

Abstract

Accurate segmentation of brain tissues such as gray matter and white matter from magnetic resonance imaging is essential for studying brain anatomy, diagnosing neurological disorders, and monitoring disease progression. Traditional methods, such as FSL FAST, produce tissue probability maps but often require task-specific adjustments and face challenges with diverse imaging conditions. Recent foundation models, such as MedSAM, offer a prompt-based approach that leverages large-scale pretraining. In this paper, we propose a modified MedSAM model designed for multi-class brain tissue segmentation. Our preprocessing pipeline includes skull stripping with FSL BET, tissue probability mapping with FSL FAST, and converting these into 2D axial, sagittal, coronal slices with multi-class labels (background, gray matter, and white matter). We extend MedSAM's mask decoder to three classes, freezing the pre-trained image encoder and fine-tuning the prompt encoder and decoder. Experiments on the IXI dataset achieve Dice scores up to 0.8751. This work demonstrates that foundation models like MedSAM can be adapted for multi-class medical image segmentation with minimal architectural modifications. Our findings suggest that such models can be extended to more diverse medical imaging scenarios in future work.