Key result
DUCNet outperforms existing algorithms by ~2% in mouse cardiac slice segmentation.
Why the study?
Manual segmentation of mouse cardiac slice images with myocardial infarction is time-consuming, while automatic segmentation is complicated by the irregular U-shaped structure of infarcted and high-risk areas.
A novel dynamic U-shaped convolutional network improves the automated segmentation and quantification of myocardial infarction in mouse cardiac slice images.
Automates irregular infarct segmentation in mouse models; extends dynamic networks for preclinical cardiovascular imaging research.
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 .
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied 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%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: