What does this research mean for the field?

A dynamic U-shaped convolutional network incorporating dual-stream fusion and attention gating significantly improves the automatic segmentation and quantification accuracy of infarcted and high-risk areas in mouse cardiac images compared to existing methods. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to improve the segmentation and quantification of mouse cardiac images, particularly in the context of myocardial infarction.

June 1, 2026Frontiers in Medicine0 citationsOpen Access

Dynamic U-shaped convolutional network for mouse cardiac image segmentation and quantification

Q: What is the clinical evidence from this study?

Study design: Other. Population: Myocardial infarction (mouse model) (n=243). Intervention: Dynamic U-shaped Convolutional Network (DUCNet) vs. Existing segmentation algorithms (e.g., DSCNet). Primary outcome: Average Dice coefficient for cardiac slice segmentation.

YWYue Wang WZWenwen Zhang WZWanjun Zhang

Key Result

The Dynamic U-shaped Convolutional Network (DUCNet) achieved an average Dice coefficient of 80.68% for mouse cardiac slice image segmentation, outperforming the best existing algorithm by 1.7%.

Key Points

This research aims to improve the segmentation and quantification of mouse cardiac images, particularly in the context of myocardial infarction.
Designed a dynamic convolutional network focusing on U-shaped local features.
Implemented a dual-stream fusion block to optimize performance.
Constructed a dataset of 243 mouse cardiac slice images for training and validation.
Achieved an average Dice coefficient of 80.68%, outperforming existing algorithms by 1.7%.
For infarct size segmentation, reached 80.13%, exceeding the optimal method by 2.43%.
Enabled quantification of the ratio of infarcted to risk areas, aiding in evaluating myocardial injury severity.

Structured PICO

Population

243 mouse cardiac slice images with myocardial infarction

Intervention

Dynamic U-shaped convolutional network with dynamic convolution, dual-stream fusion block, and attention gate mechanism

Comparator

Existing segmentation algorithms

Outcome

Average Dice coefficient for segmentationsurrogate

A novel dynamic U-shaped convolutional network improves the automated segmentation and quantification of myocardial infarction in mouse cardiac slice images.

Main Result

Absolute Event Rate: 80.68% vs 78.98%

Limitations

The proposed algorithm has high computational complexity with 239.04M parameters and 263.13G FLOPs, limiting its model efficiency.

Abstract

Accurately segmenting and quantifying mouse cardiac slice images with myocardial infarction is of great significance in cardiovascular disease research. Manual methods are time-consuming, so automatic segmentation is highly sought after. However, due to the irregular U-shaped structure of infarcted and high-risk areas, the task is complex. This study proposes a dynamic U-shaped convolutional network that adapts to these irregular structures. We designed a dynamic convolution to focus on U-shaped local features, and developed a dual-stream fusion block to enhance performance. An attention gate mechanism suppresses irrelevant information, highlighting key features. We constructed a dataset of 243 mouse cardiac slice images with myocardial infarction. The proposed method outperforms other models, achieving an average Dice coefficient of 80.68%, 1.7% higher than the best existing algorithm. For infarct size segmentation, it reached 80.13%, surpassing the current optimal method by 2.43%. Additionally, our approach can quantify the ratio of infarcted to risk areas, aiding the assessment of myocardial injury severity. The dataset is available at https://github.com/wwz4416/mouse-cardiac-dataset .

问 AI

Bookmark

View Full Paper

问 AI

Bookmark

View Full Paper

Cite This Study

Wang et al. (Thu,) conducted a other in Myocardial infarction (mouse model) (n=243). Dynamic U-shaped Convolutional Network (DUCNet) vs. Existing segmentation algorithms (e.g., DSCNet) was evaluated on Average Dice coefficient for cardiac slice segmentation. The Dynamic U-shaped Convolutional Network (DUCNet) achieved an average Dice coefficient of 80.68% for mouse cardiac slice image segmentation, outperforming the best existing algorithm by 1.7%.

synapsesocial.com/papers/6a1d20bc02fbce91306370b8 https://doi.org/https://doi.org/10.3389/fmed.2026.1836537

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: