本文介绍了一种用于眼眶计算机断层扫描(CT)图像的物体分割方案。文中详细说明了采用超分辨率技术标注眼眶结构真实标签、从CT图像中提取感兴趣区域体积,以及利用二维序列U-Net对眼眶CT图像进行多标签分割建模的方法,以上均适用于监督学习。
Chapters in this video
0:04
Introduction
0:42
Eyeball, Optic Nerve, and Extraocular Muscle Masking on the Orbital CT Scans
1:42
Pre-Processing: Window Clipping and Cropping the VOIs
2:16
Four Cross-Validations of the Orbital Segmentation Model
2:57
Results: Segmentation Results of the Orbital Structures
4:01
Conclusion
Related Videos