Accurate magnetic resonance imaging (MRI) segmentation is crucial for clinical decision-making, but remains labor-intensive when performed manually. Convolutional neural network (CNN)-based methods can be accurate and efficient, but often generalize poorly to MRI's variable contrast, intensity inhomogeneity, and protocols. Although the transformer-based Segment Anything Model (SAM) has demonstrated remarkable generalizability in natural images, existing adaptations often treat MRI as another imaging modality, overlooking these modality-specific challenges. We present SAMRI, an MRI-specialized SAM trained and validated on 1.1 million labeled MR slices spanning whole-body organs and pathologies. We demonstrate that SAM can be effectively adapted to MRI by simply fine-tuning its mask decoder using a two-stage strategy, reducing training time by 94% and trainable parameters by 96% versus full-model retraining. Across diverse MRI segmentation tasks, SAMRI achieves a mean Dice of 0.87, delivering state-of-the-art accuracy across anatomical regions and robust generalization on unseen structures, particularly small and clinically important structures.

翻译：精确的磁共振成像（MRI）分割对于临床决策至关重要，但手动分割仍然劳动密集。基于卷积神经网络（CNN）的方法虽然准确高效，但通常对MRI多变的对比度、强度不均匀性及扫描协议泛化能力较差。尽管基于Transformer的通用分割模型（SAM）在自然图像中展现出卓越的泛化能力，现有改进方法往往仅将MRI视为另一种成像模态，忽视了这些模态特有的挑战。我们提出了SAMRI——一个专门针对MRI的SAM模型，该模型在涵盖全身器官与病变的110万张标注MR切片上进行训练与验证。我们证明，通过采用两阶段策略仅微调SAM的掩码解码器，即可有效适配MRI任务，相比全模型重训练，训练时间减少94%，可训练参数减少96%。在多样化的MRI分割任务中，SAMRI的平均Dice系数达到0.87，在各解剖区域均实现了最先进的精度，并对未见结构（特别是小型及临床关键结构）展现出强大的泛化能力。