Intraoperative Stereovision Cortical Surface Segmentation Using Fast Segment Anything Model

被引:0
|
作者
Li, Chengpei [1 ]
Fan, Xiaoyao [1 ]
Duke, Ryan [1 ]
Chen, Kristen [1 ]
Evans, Linton T. [2 ,4 ]
Paulsen, Keith [1 ,2 ,3 ,4 ]
机构
[1] Dartmouth Coll, Thayer Sch Engn, Hanover, NH 03755 USA
[2] Dartmouth Coll, Geisel Sch Med, Hanover, NH 03755 USA
[3] Norris Cotton Canc Ctr, Lebanon, NH 03756 USA
[4] Dartmouth Hitchcock Med Ctr, Lebanon, NH 03756 USA
基金
美国国家卫生研究院;
关键词
image-guided neurosurgery; brain deformation; intraoperative stereovision; Segment Anything Model; U-Net model; 3D SLICER; PLATFORM; BRAIN;
D O I
10.1117/12.3006873
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Introduction In image-guided open cranial surgeries, brain deformation may compromise the accuracy of image guidance immediately following the opening of the dura. A biomechanical model has been developed to update pre-operative MR images to match intraoperative stereovision (iSV), and maintain the accuracy of image guidance. Current methods necessitate manual segmentation of the cortical surface from iSV, a process that demands expertise and prolongs computational time. Methods In this study, we adopted the Fast Segment Anything Model (FastSAM), a newly developed deep learning model that automatically can segment the cortical surface from iSV after dural opening without customized training. We evaluated its performance against manual segmentation as well as a U-Net model. In one patient case, FastSAM was applied to segment the cortical surface with an automatic box prompt, and the segmentation was used for image updating. We compared the three cortical surface segmentation methods in terms of segmentation accuracy (Dice Similarity Coefficient; DSC) and image updating accuracy (target registration errors; TRE). Results All three segmentation methods demonstrated high DSC (>0.95). FastSAM and manual segmentation produced similar performance in terms of image updating efficiency and TRE (similar to 2.2 mm). Conclusion In summary, the performance of FastSAM was consistent with manual segmentation in terms of segmentation accuracy and image updating accuracy. The results suggest FastSAM can be employed in the image updating process to replace manual segmentation to improve efficiency and reduce user dependency.
引用
收藏
页数:7
相关论文
共 50 条
  • [1] Drilling rock image segmentation and analysis using segment anything model
    Shan, Liqun
    Liu, Yanchang
    Du, Ke
    Paul, Shovon
    Zhang, Xingli
    Hei, Xiali
    ADVANCES IN GEO-ENERGY RESEARCH, 2024, 12 (02): : 89 - 101
  • [2] An efficient segment anything model for the segmentation of medical images
    Dong, Guanliang
    Wang, Zhangquan
    Chen, Yourong
    Sun, Yuliang
    Song, Hongbo
    Liu, Liyuan
    Cui, Haidong
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [3] ASPS: Augmented Segment Anything Model for Polyp Segmentation
    Li, Huiqian
    Zhang, Dingwen
    Yao, Jieru
    Han, Longfei
    Li, Zhongyu
    Han, Junwei
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2024, PT IX, 2024, 15009 : 118 - 128
  • [4] Application of Segment Anything Model in Medical Image Segmentation
    Wu, Tong
    Hu, Haoji
    Feng, Yang
    Luo, Qiong
    Xu, Dong
    Zheng, Weizeng
    Jin, Neng
    Yang, Chen
    Yao, Jincao
    Zhongguo Jiguang/Chinese Journal of Lasers, 2024, 51 (21):
  • [5] Cortical Surface Strain Estimation Using Stereovision
    Ji, Songbai
    Fan, Xiaoyao
    Roberts, David W.
    Paulsen, Keith D.
    MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION, MICCAI 2011, PT I, 2011, 6891 : 412 - +
  • [6] Prompting and Tuning: In-Band Interference Segmentation Using Segment Anything Model
    Zhang, Zehui
    An, Jianping
    Ye, Neng
    Niyato, Dusit
    Yang, Kai
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2024, 13 (08) : 2065 - 2069
  • [7] Image Radar Point Cloud Segmentation with Segment Anything Model
    Du, Yu
    Smith, Jeremy S.
    Man, Ka Lok
    Lim, Eng Gee
    2023 20TH INTERNATIONAL SOC DESIGN CONFERENCE, ISOCC, 2023, : 195 - 196
  • [8] Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)
    Maquiling, Virmarie
    Byrne, Sean Anthony
    Niehorster, Diederick C.
    Nystrom, Marcus
    Kasneci, Enkelejda
    PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES, 2024, 7 (02)
  • [9] LeSAM: Adapt Segment Anything Model for Medical Lesion Segmentation
    Gu, Yunbo
    Wu, Qianyu
    Tang, Hui
    Mai, Xiaoli
    Shu, Huazhong
    Li, Baosheng
    Chen, Yang
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2024, 28 (10) : 6031 - 6041
  • [10] EFFICIENT CUTTING TOOL WEAR SEGMENTATION BASED ON SEGMENT ANYTHING MODEL
    Li, Zongshuo
    Huo, Ding
    Meurer, Markus
    Bergs, Thomas
    PROCEEDINGS OF ASME 2024 19TH INTERNATIONAL MANUFACTURING SCIENCE AND ENGINEERING CONFERENCE, MSEC2024, VOL 2, 2024,