TY - JOUR T1 - Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences JF - bioRxiv DO - 10.1101/339630 SP - 339630 AU - Jason A. Fries AU - Paroma Varma AU - Vincent S. Chen AU - Ke Xiao AU - Heliodoro Tejeda AU - Priyanka Saha AU - Jared Dunnmon AU - Henry Chubb AU - Shiraz Maskatia AU - Madalina Fiterau AU - Scott Delp AU - Euan Ashley AU - Christopher RĂ© AU - James R. Priest Y1 - 2019/01/01 UR - http://biorxiv.org/content/early/2019/05/11/339630.abstract N2 - Biomedical repositories such as the UK Biobank provide increasing access to prospectively collected cardiac imaging, however these data are unlabeled which creates barriers to their use in supervised machine learning. We develop a weakly supervised deep learning model for classification of aortic valve malformations using up to 4,000 unlabeled cardiac MRI sequences. Instead of requiring highly curated training data, weak supervision relies on noisy heuristics defined by domain experts to programmatically generate large-scale, imperfect training labels. For aortic valve classification, models trained with imperfect labels substantially outperform a supervised model trained on hand-labeled MRIs. In an orthogonal validation experiment using health outcomes data, our model identifies individuals with a 1.8-fold increase in risk of a major adverse cardiac event. This work formalizes a learning baseline for aortic valve classification and outlines a general strategy for using weak supervision to train machine learning models using unlabeled medical images at scale. ER -