.png){kind=icon}
.png){kind=icon}
Return
From structural complexity to causal representation: A dynamic fractal–attention framework for fine-grained ovarian tumor classification in ultrasound
.png){kind=icon}
PRE
AI
Q
Q
X
X
C
Z
P
DOI：10.1016/j.media.2026.104101.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A unified framework for structural complexity and causal modeling. • Multi-scale activation occupancy estimation for lesion structure. • Edge-guided fractal attention enhances salient structures. • Causal module improves robustness to distribution shifts. • Extensive experiments show superior performance and stability.
Keywords:
structural complexity
causal modeling
fractal attention
lesion segmentation
ovarian tumor classification
Journal
IF:
11.8
Papers:
3.7K
Citations:
2.4W
Organization
Cited Papers