Motion-Informed Neural Network Towards Diastolic Mechanics in Takotsubo Syndrome
- 11 November 2026
- journal article
- Published by Wolters Kluwer Health in Circulation: Cardiovascular Imaging
Abstract
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 P P P P =0.006), passive (0.45 [IQR, 0.33–0.58] versus 0.50 [IQR, 0.38–0.68]; P P =0.001) phases, and altered rotation angles (away from the horizontal A–V plane) in the passive ventricular filling phase (−70.19 [IQR, −89.62 to −41.33] versus −60.34 [IQR, −87.07 to −30.84]; P =0.020). CONCLUSIONS: MiNN-Echo in echocardiograms elucidates unique myocardial relaxation kinematics to characterize TTS-associated diastolic mechanics.This publication has 39 references indexed in Scilit:
- Integrating Imaging Markers for Clinical Risk Stratification of Takotsubo SyndromeCanadian Journal of Cardiology, 2026
- Latent diffusion for medical image segmentation: End-to-end learning for fast sampling and accuracyBiomedical Signal Processing and Control, 2025
- Correlation between Echocardiographic Diastolic Parameters and Invasive Measurements of Left Ventricular Filling Pressure in Patients with Takotsubo CardiomyopathyJournal of the American Society of Echocardiography, 2022
- Assessment of Artificial Intelligence in Echocardiography Diagnostics in Differentiating Takotsubo Syndrome From Myocardial InfarctionJAMA Cardiology, 2022
- Spatio-temporal hybrid neural networks reduce erroneous human “judgement calls” in the diagnosis of Takotsubo syndromeeClinicalMedicine, 2021
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- Recommendations for the Evaluation of Left Ventricular Diastolic Function by Echocardiography: An Update from the American Society of Echocardiography and the European Association of Cardiovascular ImagingJournal of the American Society of Echocardiography, 2016
- Recommendations for Cardiac Chamber Quantification by Echocardiography in Adults: An Update from the American Society of Echocardiography and the European Association of Cardiovascular ImagingJournal of the American Society of Echocardiography, 2015
- Attention and visual perceptionCurrent Opinion in Neurobiology, 2005
- Two-Frame Motion Estimation Based on Polynomial Expansion2003