logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Diff-UNet: A diffusion embedded network for robust 3D medical image segmentation

delete2025-06-16
delete0
PRE
AI
Z
Zhaohu Xing
L
Liang Wan
H
Huazhu Fu
G
Guang Yang
Y
Yijun Yang
L
Lequan Yu
雷
雷柏英 (Baiying Lei)
L
Lei Zhu
DOI：10.1016/j.media.2025.103654delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A two-branch diffusion-based model to boost 3D medical image segmentation. • A Multi-granularity Boundary Aggregation (MBA) module to introduce boundary features. • A Monte Carlo Diffusion (MC-Diff) module to guide the segmentation loss. • A Progressive Uncertainty-driven REfinement (PURE) strategy to fuse predictions.

Journal

Medical Image Analysis cover
Medical Image Analysis
IF:
11.8
Papers:
3.8K
Citations:
2.4W

Organization

No organization information available