Print Email Facebook Twitter Regularization of end-to-end learning for cardiac diagnosis by multitask learning with segmentation Title Regularization of end-to-end learning for cardiac diagnosis by multitask learning with segmentation Author Snaauw, Gerard (TU Delft Mechanical, Maritime and Materials Engineering) Contributor Niessen, Wiro (mentor) Verjans, Johan (mentor) Carneiro, Gustavo (mentor) Degree granting institution Delft University of Technology Programme Biomedical Engineering Date 2018-09-28 Abstract Cardiac magnetic resonance (CMR) is used extensively in the diagnosis and management of cardiovascular disease. Deep learning methods have proven to deliver segmentation results comparable to human experts in CMR imaging, however, no successful attempts have been made at fully automated diagnosis. This has been contributed to a lack of sufficiently large datasets required for end-to-end learning of diagnoses. Here we propose to exploit the excellent results obtained in segmentation by jointly training with diagnosis in a multitask learning setting. We hypothesize that segmentation has a regularizing effect on learning and promotes learning of features relevant for diagnosis. Results show a three-fold reduction of the classification error to 0.12 compared to a baseline without segmentation, both results are obtained by training on just 75 cases in a dataset (ACDC) that is equally distributed over 5 classes. Subject Deep LearningCardiac DiagnosisMultitask LearningCMRend-to-end training To reference this document use: http://resolver.tudelft.nl/uuid:69b93800-0683-4e34-82df-06015062e049 Part of collection Student theses Document type master thesis Rights © 2018 Gerard Snaauw Files PDF Master_Thesis_Gerard_Snaauw.pdf 1.91 MB Close viewer /islandora/object/uuid:69b93800-0683-4e34-82df-06015062e049/datastream/OBJ/view