Multi-section myocardial status evaluation algorithm based on electrocardiogram and ultrasound image fusion

• Published in: Information fusion Vol. 124; p. 103438
• Main Authors: Tian, Mingjun, Zheng, Minjuan, Qiu, Shi, Lu, Hongbing
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2025
• Subjects: Assessment; Electrocardiogram; Fusion; Myocardium; Ultrasound; Myocardium; Ultrasound; Fusion; Electrocardiogram; Assessment
• ISSN: 1566-2535
• DOI: 10.1016/j.inffus.2025.103438

•Based on electrocardiographic characteristics, multi-faceted echocardiographic images are calibrated from a temporal dimension.•A multi-scale model is constructed from both deep and shallow feature levels to achieve myocardial segmentation.•Based on the myocardial response intensity in ultrasound images, visually perceptible quantitative indicators are established to assess myocardial status. The heart is a vital organ in the human body, with the myocardium being an essential component. The microcirculatory state of the myocardium is directly correlated with heart function, making its study of significant importance. Currently, myocardial analysis predominantly relies on subjective assessments by physicians, lacking quantitative indicators and effective imaging techniques. To facilitate real-time observation of cardiac conditions, we propose a multi-section myocardial status evaluation algorithm based on electrocardiogram and ultrasound image fusion. 1) Aligning multi-section ultrasound images in the temporal perspective using electrocardiograms as a foundation for subsequent analyses. 2) Introducing a myocardial segmentation model that incorporates both deep and shallow features, utilizing multi-scale to obtain more information and achieve myocardial precise extraction. 3) Constructing a bullseye plot based on medical diagnostic standards, and introducing quantitative indicators for assessment, intuitively displayed the results through color mapping. We compile an imaging dataset from 411 clinical groups. Two professional radiologists mark the myocardial regions using a blinded method, with their qualitative assessments of cardiac conduction status serving as the gold standard. Experiments show that: 1) The algorithm effectively segments the myocardium, achieving an Area Overlap Measure (AOM) of 94 %, which is a 13 % improvement over the EUnet model. 2) The myocardial status assessment algorithm yields acceptable results, assisting directly in the diagnosis in 84 % of cases, thereby enhancing the accuracy of physicians’ detections.