Key result
DSS-Net achieves competitive myocardial pathology segmentation reaching a ~0.75 Dice score for edema.
Why the study?
Myocardial scar and edema segmentation from multi-sequence cardiac magnetic resonance remains challenging due to heterogeneous modal characteristics, severe class imbalance, and small, ambiguous pathological regions.
Population
Multi-sequence cardiac magnetic resonance images from MyoPS 2020 and MyoPS 2024 datasets
Comparison
DSS-Net vs SOTA methods in the MyoPS 2020 Challenge
Design
Algorithm development and validation study
Authors
Loading...
DSS-Net boosts scar/edema segmentation accuracy in MS-CMR; extends synergistic DL frameworks for imbalanced cardiac imaging.
The proposed DSS-Net provides a promising strategy for robust myocardial scar and edema segmentation in MS-CMR images by combining anatomical guidance with pathology-aware multi-modal learning.
Ruan et al. (2026) studied Myocardial infarction (myocardial scar and edema). Dynamic synergistic segmentation network (DSS-Net) vs. State-of-the-art methods was evaluated on Dice scores for scar and edema segmentation. The dynamic synergistic segmentation network (DSS-Net) achieved competitive performance for myocardial pathology segmentation, reaching Dice scores of 0.706 for scar and 0.753 for edema.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: