Multimodal Learning To Improve Cardiac Late Mechanical Activation Detection From Cine MR Images

arXiv:2402.18507v1 Announce Type: new
Abstract: This paper presents a multimodal deep learning framework that utilizes advanced image techniques to improve the performance of clinical analysis heavily dependent on routinely acquired standard images. More specifically, we develop a joint learning network that for the first time leverages the accuracy and reproducibility of myocardial strains obtained from Displacement Encoding with Stimulated Echo (DENSE) to guide the analysis of cine cardiac magnetic resonance (CMR) imaging in late mechanical activation (LMA) detection. An image …

abstract acquired advanced analysis arxiv clinical cs.cv deep learning deep learning framework detection framework image images multimodal multimodal deep learning multimodal learning network paper performance standard type