The development of computational models for the prediction of cardiac cellular dynamics remains a challenge due to the lack of first-principled mathematical models. We develop a novel machine-learning approach hybridizing physics simulation and graph networks to deliver robust predictions of cardiomyocyte dynamics. Embedded with inductive physical priors, the proposed constraint-based interaction neural projection (CINP) algorithm can uncover hidden physical constraints from sparse image data on a small set of beating cardiac cells and provide robust predictions for heterogenous large-scale cell sets.
View Article and Find Full Text PDFSclerosing mucoepidermoid carcinoma (SMEC) of the salivary glands is a rare variant of low-grade mucoepidermoid carcinoma with scanty cellular atypia characterized by marked fibrosis/sclerosis and a rich inflammatory infiltrate. Herein, we report 25 unpublished cases of SMEC, two of them with prominent eosinophilia (2/25; 8%) and three with abundant IgG4-positive plasma cells (3/25; 12%). In our series of salivary SMEC, molecular analysis using fluorescence in situ hybridization (FISH) and/or next-generation sequencing (NGS) provided evidence of MAML2 gene rearrangement in 18 cases of the 21 analyzable cases tested (86%), while this gene locus was intact in 3 cases (14%).
View Article and Find Full Text PDF