Motion-Informed Neural Network Towards Diastolic Mechanics in Takotsubo Syndrome
Circulation: Cardiovascular Imaging · 11.11.2026
DOI: 10.1161/circimaging.126.020258 ↗Kurz gefasst
Fachartikel in der Zeitschrift Circulation: Cardiovascular Imaging, online erschienen am 11.11.2026. Verfasst von Fahim Zaman und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering (F.Z., X.C., X.W.), University of Iowa. Die Arbeit nennt 42 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND: The pathophysiology of Takotsubo syndrome (TTS) remains perplexing. We developed a motion-informed neural network (MiNN-Echo) using echocardiograms to elucidate the diastolic mechanics of TTS. METHODS: We trained and validated MiNN-Echo, a deep convolutional neural network (2D+t) echocardiographic prediction model using multi-vendor echocardiograms from 1142 patients (596 TTS and 546 anterior myocardial infarction) in a multi-institutional cohort. A total of 68 expert echocardiographic readers performed human interpretation. The network’s dual-branch architecture independently learns spatial and temporal features, using 2-dimensional image frames for spatial representation and segmentation, and optical flow with sinusoidal phase encoding for temporal dynamics. The MiNN-Echo model integrates static cardiac anatomic changes with motion details from 2-dimensional echocardiographic videos to produce interpretable disease predictions. RESULTS: The MiNN-Echo model achieved an area under the curve of 0.77, compared with 0.69 among human readers in differentiating TTS from acute myocardial infarction. Myocardial motion features during diastole contributed more (≈71%) to the differential diagnosis than those during systole. Compared with patients with acute myocardial infarction, TTS patients showed increased isovolumic relaxation time (112.5 [interquartile range (IQR), 68.75–165.94] ms versus 87.5 [IQR, 54.17–140] ms, P
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering (F.Z., X.C., X.W.), University of Iowa.
- Department of Internal Medicine (A.C.), University of Iowa.
- Cardiovascular Division, Department of Internal Medicine, Washington University in St. Louis, MO (F.S.-E., S.J.K., Y.C., C.L., S.V., K.L.).
- National Heart, Lung, and Blood Institute, Bethesda, MD (M.-L.N.).
- Department of Mathematics, California State University Dominguez Hills, Carson (Y.G.W.).
- Department of Cardiology, University of Missouri-Kansas City (T.A.).
ORCID-Profile: Fahim Zaman, Amanda Chang, Frank Seghatol-Eslami, Xiaojie Chen, Yi Grace Wang, Jian Chen, Tou Kun Chong, Christian Templin, Xiaodong Wu, Kan Liu
Zitieren
APA
Zaman, F., Chang, A., Seghatol-Eslami, F., Kovács, S. J., Nguyen, M. L., Chen, X., Chen, Y., Wang, Y. G., Licari, C., Vaughn, S., Asif, T., Chen, J., Chong, T. K., Di Vece, D., Templin, C., Wu, X., & Liu, K. (2026). Motion-Informed Neural Network Towards Diastolic Mechanics in Takotsubo Syndrome. Circulation: Cardiovascular Imaging. https://doi.org/10.1161/circimaging.126.020258
Vancouver
Zaman F, Chang A, Seghatol-Eslami F, Kovács SJ, Nguyen ML, Chen X, et al. Motion-Informed Neural Network Towards Diastolic Mechanics in Takotsubo Syndrome. Circulation: Cardiovascular Imaging. 2026. doi:10.1161/circimaging.126.020258
BibTeX
@article{Zaman2026,
author = {Zaman, Fahim and Chang, Amanda and Seghatol-Eslami, Frank and Kovács, Sándor J and Nguyen, My-Le and Chen, Xiaojie and Chen, Yuyi and Wang, Yi Grace and Licari, Crystal and Vaughn, Sabrina and Asif, Talal and Chen, Jian and Chong, Tou Kun and Di Vece, Davide and Templin, Christian and Wu, Xiaodong and Liu, Kan},
title = {Motion-Informed Neural Network Towards Diastolic Mechanics in Takotsubo Syndrome},
journal = {Circulation: Cardiovascular Imaging},
year = {2026},
doi = {10.1161/circimaging.126.020258}
}
EUVIMED