CineMyoPS: Segmenting Myocardial Pathologies from Cine Cardiac MR

2025-07-02

AI Summary

This study addresses the challenge of automatically segmenting myocardial scar and edema regions using only non-contrast cine cardiac magnetic resonance (CMR) sequences—eliminating reliance on multi-sequence acquisitions such as late gadolinium enhancement (LGE) and T2-weighted imaging. To this end, we propose an end-to-end spatiotemporal deep network that jointly models myocardial motion dynamics and anatomical structure. Specifically, we introduce a consistency loss to enforce temporal coherence of pathological segmentation across cardiac frames and design a multi-stage temporal feature aggregation module to enhance discriminative representation learning. Evaluated on a multicenter dataset, our method achieves state-of-the-art performance in three complementary tasks: pathological tissue segmentation, myocardial motion estimation, and anatomical myocardial segmentation. It significantly outperforms frame-wise baseline methods, demonstrating superior effectiveness, robustness, and clinical generalizability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Myocardial infarction (MI) is a leading cause of death worldwide. Late gadolinium enhancement (LGE) and T2-weighted cardiac magnetic resonance (CMR) imaging can respectively identify scarring and edema areas, both of which are essential for MI risk stratification and prognosis assessment. Although combining complementary information from multi-sequence CMR is useful, acquiring these sequences can be time-consuming and prohibitive, e.g., due to the administration of contrast agents. Cine CMR is a rapid and contrast-free imaging technique that can visualize both motion and structural abnormalities of the myocardium induced by acute MI. Therefore, we present a new end-to-end deep neural network, referred to as CineMyoPS, to segment myocardial pathologies, ie scars and edema, solely from cine CMR images. Specifically, CineMyoPS extracts both motion and anatomy features associated with MI. Given the interdependence between these features, we design a consistency loss (resembling the co-training strategy) to facilitate their joint learning. Furthermore, we propose a time-series aggregation strategy to integrate MI-related features across the cardiac cycle, thereby enhancing segmentation accuracy for myocardial pathologies. Experimental results on a multi-center dataset demonstrate that CineMyoPS achieves promising performance in myocardial pathology segmentation, motion estimation, and anatomy segmentation.

Problem

• Segment myocardial pathologies from cine CMR images
• Identify scars and edema without contrast agents
• Combine motion and anatomy features for accurate segmentation

Innovation

• Deep neural network segments pathologies from cine CMR
• Consistency loss enhances joint feature learning
• Time-series aggregation improves segmentation accuracy