The segment-anything model (SAM), was introduced as a fundamental model for segmenting images. It was trained using over 1 billion masks from 11 million natural images. The model can perform zero-shot segmentation of images by using various prompts such as masks, boxes, and points. In this report, we explored (1) the accuracy of SAM on 12 public medical image segmentation datasets which cover various organs (brain, breast, chest, lung, skin, liver, bowel, pancreas, and prostate), image modalities (2D X-ray, histology, endoscropy, and 3D MRI and CT), and health conditions (normal, lesioned). (2) if the computer vision foundational segmentation model SAM can provide promising research directions for medical image segmentation. We found that SAM without re-training on medical images does not perform as accurately as U-Net or other deep learning models trained on medical images.

翻译：分段任意模型（SAM）作为一种图像分割的基础模型被提出。该模型基于1100万张自然图像中的超过10亿个掩码进行训练，能够通过使用掩码、边界框和点等多种提示对图像进行零样本分割。在本报告中，我们探讨了：(1) SAM在12个公开医学图像分割数据集上的准确性，这些数据集涵盖多种器官（脑、乳腺、胸部、肺、皮肤、肝脏、肠道、胰腺和前列腺）、图像模态（二维X光、组织学、内窥镜以及三维MRI和CT）以及健康状态（正常、病变）；(2) 计算机视觉基础分割模型SAM能否为医学图像分割提供有前景的研究方向。我们发现，未在医学图像上重新训练的SAM，其准确性不及U-Net或其他在医学图像上训练的深度学习模型。