用MedSAM改进脑组织分割，仅微调即可实现高精度多类分割。
Segmentation of Gray Matters and White Matters from Brain MRI data
- 基于MedSAM框架，扩展为三类脑组织分割，保持图像编码器不变。
- 在IXI数据集上达到0.8751的Dice分数，优于传统方法。
- 适合医学图像分割新手快速部署，也适用于多模态影像研究。
从磁共振成像中精确分割灰质和白质对研究脑部解剖、诊断神经疾病及监测病情进展至关重要。传统方法如FSL FAST虽可生成组织概率图，但常需针对任务调整，且在不同成像条件下表现不佳。近期基于大模型的MedSAM采用提示驱动方式，利用大规模预训练优势。本文提出一种改进的MedSAM模型，用于多类脑组织分割。预处理流程包括使用FSL BET进行颅骨剥离，FSL FAST生成组织概率图，并将其转换为带有三类标签（背景、灰质、白质）的2D轴向、矢状面和冠状面切片。我们将MedSAM的掩码解码器扩展至三类，冻结预训练图像编码器，仅微调提示编码器和解码器。在IXI数据集上的实验显示，Dice分数最高达0.8751。结果表明，类似MedSAM的基础模型可通过少量架构修改适配多类医学图像分割任务。未来工作可进一步拓展至更广泛的医学影像场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。