Shape constrained CNN for segmentation guided prediction of myocardial shape and pose parameters in cardiac MRI

no code implementations • 2 Mar 2022 • Sofie Tilborghs, Jan Bogaert, Frederik Maes

We show the benefits of simultaneous semantic segmentation and the two newly defined loss functions for the prediction of shape parameters.

Image Segmentation Medical Image Segmentation +3

Shape Constrained CNN for Cardiac MR Segmentation with Simultaneous Prediction of Shape and Pose Parameters

no code implementations • 18 Oct 2020 • Sofie Tilborghs, Tom Dresselaers, Piet Claus, Jan Bogaert, Frederik Maes

We evaluated the proposed method in a fivefold cross validation on a in-house clinical dataset with 75 subjects containing a total of 1539 delineated short-axis slices covering LV from apex to base, and achieved a correlation of 99% for LV area, 94% for myocardial area, 98% for LV dimensions and 88% for regional wall thicknesses.

LV Segmentation Pose Prediction +2