使SegmentAnything23D,3D:

Yosuke Yamagishi1, Shouhei Hanaoka1,2, Tomohiro Kikuchi3,4

  • 1Division of Radiology and Biomedical Engineering, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan, 81 3-3815-5411.

JMIR AI
|July 4, 2025
PubMed
概括

细分任何东西模型2 (SAM2) 显示了CT扫描中自动化3D医疗图像细分的前景,特别是在较大的腹部器官. 提示符设置显著影响细分精度.