Aug 2026· Machine Learning for Biomedical Imaging· 0 citations· 27 references
EngineeringComputer Science
TL;DR
Findings from the Myocardial Segmentation with Automated Infarct Quantification (MYOSAIQ) challenge indicate that well-designed UNet-based techniques outperform fully automatic foundation models for LGE MR segmentation.
Abstract
Late gadolinium enhancement (LGE) cardiac magnetic resonance (MR) imaging is the modality of choice to assess myocardial infarction (MI) lesions. Nowadays MI volume quantification is not performed routinely in clinical practice. Numerous deep learning (DL) methods have been developed to automate the segmentation of the myocardium and infarct regions. However, most studies rely on relatively small datasets which typically undergo pre-processing steps to standardize images and focus on a specific phase of myocardial infarction following reperfusion therapy. These limitations have impeded the development of models that are generalizable across diverse conditions and thus suitable for routine clinical use. To advance research and establish benchmarks in generalizable learning for myocardial infarct quantification, this paper presents findings from the Myocardial Segmentation with Automated Infarct Quantification (MYOSAIQ) challenge. The dataset set up for the challenge combines 439 CMR volumes from two multicenter clinical trials, with representative data acquired in acute and chronic phases after acute MI. Data were acquired in 16 centers using MRI scanners from three different vendors. Six teams participated until the end of the challenge, employing various baseline models, data augmentation techniques, and confidence strategies. To enhance the significance of this study, we compare the challengers’ results with those of fine-tuned foundation models. Our results indicate that well-designed UNet-based techniques outperform fully automatic foundation models for LGE MR segmentation. While the best methods achieve high-quality and stable delineations of the left ventricle and myocardium under various conditions, they remain improvable in accurately segmenting infarct regions.
Findings from the Myocardial Segmentation with Automated Infarct Quantification (MYOSAIQ) challenge indicate that well-designed UNet-based techniques outperform fully automatic foundation models for LGE MR segmentation.
Olivier Bernard, W. Romero, Cyprien Bouton et al.· 0 citations
The approach enabled low-error NWU quantification from baseline NCCT without advanced imaging, supporting further prospective clinical evaluation and targeting NCCT-only infarct segmentation across heterogeneous external cohorts, although performance varied across domains.
Linus Britt, M. Nielsen, S. Klapproth et al.· arXiv.org· 0 citations
Purpose To evaluate the diagnostic performance of endogenous T1ρ mapping, compared with native T1 and T2 mapping, for identifying late gadolinium enhancement (LGE)-defined peri-infarct zones in acute ST-elevation myocardial infarction (STEMI) and chronic myocardial infarction (MI). Methods This retrospective study incl...
Yunchen Li, Shu-Tian An, Shuang-Shuang Xu et al.· European Journal of Radiolog...· 0 citations
Practical recommendations for automated segmentation and future validation requirements are outlined: favor self-configuring frameworks like nnU-Net when compute resources permit, consider lightweight 2D models such as YOLOv8 for fast screening, and ensure rigorous cross-site validation before potential clinical use.
Patricia García-Berlanga, Juan Zapata, J. Martínez-Alajarín et al.· Journal of Intelligent Syste...· 0 citations
The potential role of the proposed CT-based framework in providing complementary scar-related information and identifying high-risk patients who may benefit from further CMR evaluation in appropriate clinical settings is supported.
Ren-Jie Lu, Tai-Yu Yang, Ming-Yang Li et al.· Journal of imaging informati...· 0 citations
Artificial intelligence-based quantitative assessment of LGE is an independent predictor of adverse cardiovascular outcomes in patients with HCM and may represent a clinically meaningful imaging biomarker for risk stratification.
Youngsang Jeong, Jong-Il Park, Kang-Un Choi et al.· The Korean Journal of Intern...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.