Multiparametric Deep Learning Tissue Signatures for Muscular Dystrophy: Preliminary Results
This addresses a clinical problem for patients with muscular dystrophy by improving tissue identification, but it appears incremental as it applies deep learning to a specific medical imaging task.
The researchers tackled the challenge of distinguishing fat, fat-infiltrated muscle, and muscle tissue in limb girdle muscular dystrophy 2I using multiparametric MRI, and their novel deep learning model achieved excellent segmentation results.
A current clinical challenge is identifying limb girdle muscular dystrophy 2I(LGMD2I)tissue changes in the thighs, in particular, separating fat, fat-infiltrated muscle, and muscle tissue. Deep learning algorithms have the ability to learn different features by using the inherent tissue contrasts from multiparametric magnetic resonance imaging (mpMRI). To that end, we developed a novel multiparametric deep learning network (MPDL) tissue signature model based on mpMRI and applied it to LGMD2I. We demonstrate a new tissue signature model of muscular dystrophy with the MPDL algorithm segments different tissue types with excellent results.