Dynamic U-shaped convolutional network for mouse cardiac image segmentation and quantification
-
By
-
Yu Wang
-
Wenwen Zhang
-
Wanjun Zhang
-
Cenbin Huang
-
Ming Zhang
-
Naian Xiao
-
Shengge Xu
-
May 28, 2026
-
Clinical Scorecard: Adaptive U-shaped Convolutional Network for Segmentation and Analysis of Mouse Cardiac Images
At a Glance
| Category | Detail |
|---|
| Condition | |
| Key Mechanisms | Dynamic U-shaped convolution and dual-stream fusion block for enhanced segmentation. |
| Target Population | |
| Care Setting | |
Key Highlights
- Proposed DUCNet achieves an average Dice coefficient of 80.68%.
- Dynamic convolution focuses on irregular U-shaped local features.
- Dataset of 243 annotated mouse cardiac slice images created.
Guideline-Based Recommendations
Diagnosis
- Utilize automated segmentation for accurate assessment of myocardial injury.
Management
- Implement DUCNet for quantifying infarcted and risk areas.
Monitoring & Follow-up
- Regularly assess segmentation performance using Dice coefficient.
Risks
- Manual analysis may lead to high subjectivity and poor reproducibility.
Patient & Prescribing Data
Mice used in cardiovascular disease research.
DUCNet provides robust automated analysis for myocardial infarction.
Clinical Best Practices
Related Resources & Content
