Multimodal Learning To Improve Cardiac Late Mechanical Activation Detection From Cine MR Images
This work addresses a clinical analysis problem for cardiac imaging by incrementally improving LMA detection from routine images.
The paper tackled the problem of detecting late mechanical activation (LMA) from standard cine cardiac MR images by developing a multimodal deep learning framework that uses DENSE-derived strains as guidance, resulting in substantial performance improvements that align more closely with DENSE achievements.
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 registration network is utilized to acquire the knowledge of cardiac motions, an important feature estimator of strain values, from standard cine CMRs. Our framework consists of two major components: (i) a DENSE-supervised strain network leveraging latent motion features learned from a registration network to predict myocardial strains; and (ii) a LMA network taking advantage of the predicted strain for effective LMA detection. Experimental results show that our proposed work substantially improves the performance of strain analysis and LMA detection from cine CMR images, aligning more closely with the achievements of DENSE.