Saved in:
Bibliographic Details
Main Authors: Su, Haoyang, Rui, Shaohao, Xiang, Jinyi, Wu, Lianming, Wang, Xiaosong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.16612
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918149566234624
author Su, Haoyang
Rui, Shaohao
Xiang, Jinyi
Wu, Lianming
Wang, Xiaosong
author_facet Su, Haoyang
Rui, Shaohao
Xiang, Jinyi
Wu, Lianming
Wang, Xiaosong
contents Accurate and contrast-free Major Adverse Cardiac Events (MACE) prediction from Cine MRI sequences remains a critical challenge. Existing methods typically necessitate supervised learning based on human-refined masks in the ventricular myocardium, which become impractical without contrast agents. We introduce a self-supervised framework, namely Codebook-based Temporal-Spatial Learning (CTSL), that learns dynamic, spatiotemporal representations from raw Cine data without requiring segmentation masks. CTSL decouples temporal and spatial features through a multi-view distillation strategy, where the teacher model processes multiple Cine views, and the student model learns from reduced-dimensional Cine-SA sequences. By leveraging codebook-based feature representations and dynamic lesion self-detection through motion cues, CTSL captures intricate temporal dependencies and motion patterns. High-confidence MACE risk predictions are achieved through our model, providing a rapid, non-invasive solution for cardiac risk assessment that outperforms traditional contrast-dependent methods, thereby enabling timely and accessible heart disease diagnosis in clinical settings.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16612
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CTSL: Codebook-based Temporal-Spatial Learning for Accurate Non-Contrast Cardiac Risk Prediction Using Cine MRIs
Su, Haoyang
Rui, Shaohao
Xiang, Jinyi
Wu, Lianming
Wang, Xiaosong
Computer Vision and Pattern Recognition
Accurate and contrast-free Major Adverse Cardiac Events (MACE) prediction from Cine MRI sequences remains a critical challenge. Existing methods typically necessitate supervised learning based on human-refined masks in the ventricular myocardium, which become impractical without contrast agents. We introduce a self-supervised framework, namely Codebook-based Temporal-Spatial Learning (CTSL), that learns dynamic, spatiotemporal representations from raw Cine data without requiring segmentation masks. CTSL decouples temporal and spatial features through a multi-view distillation strategy, where the teacher model processes multiple Cine views, and the student model learns from reduced-dimensional Cine-SA sequences. By leveraging codebook-based feature representations and dynamic lesion self-detection through motion cues, CTSL captures intricate temporal dependencies and motion patterns. High-confidence MACE risk predictions are achieved through our model, providing a rapid, non-invasive solution for cardiac risk assessment that outperforms traditional contrast-dependent methods, thereby enabling timely and accessible heart disease diagnosis in clinical settings.
title CTSL: Codebook-based Temporal-Spatial Learning for Accurate Non-Contrast Cardiac Risk Prediction Using Cine MRIs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.16612