Sparse Bayesian learning for label efficiency in cardiac real-time MRI

Statistics and Computing, vol. 36

Abstract

Abstract Cardiac real-time magnetic resonance imaging (MRI) is an emerging technology that images the heart at up to 50 frames per second, offering insight into the respiratory effects on the heartbeat. However, this method significantly increases the number of images that must be segmented to derive critical health indicators. Although neural networks perform well on inner slices, predictions on outer slices are often unreliable. This work proposes sparse Bayesian learning (SBL) to predict the ventricular volume on outer slices with minimal manual labeling to address this challenge. The ventricular volume over time is assumed to be dominated by sparse frequencies corresponding to the heart and respiratory rates. Moreover, SBL identifies these sparse frequencies on well-segmented inner slices by optimizing hyperparameters via type-II likelihood, automatically pruning irrelevant components. The identified sparse frequencies guide the selection of outer slice images for labeling, minimizing posterior variance. This work provides performance guarantees for the greedy algorithm. Testing on patient data demonstrates that only a few labeled images are necessary for accurate volume prediction. The labeling procedure effectively avoids selecting inefficient images. Furthermore, the Bayesian approach provides uncertainty estimates, highlighting unreliable predictions (e.g., when choosing suboptimal labels).

Authors 7

1. Anja Bach

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   Institute of Aerospace Medicine, Cardiovascular Aerospace Medicine, German Aerospace Center (DLR), Cologne, Germany

2. Achim Basermann

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   Institute of Software Technology, High-Performance Computing, German Aerospace Center (DLR), Cologne, Germany

3. Darius A. Gerlach

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   Institute of Aerospace Medicine, Cardiovascular Aerospace Medicine, German Aerospace Center (DLR), Cologne, Germany

4. Philipp Knechtges

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   Institute of Software Technology, High-Performance Computing, German Aerospace Center (DLR), Cologne, Germany

5. Jens Tank

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   Institute of Aerospace Medicine, Cardiovascular Aerospace Medicine, German Aerospace Center (DLR), Cologne, Germany

6. Raul F. Tempone Aachen Chair of Mathematics for Uncertainty Quantification Department of Mathematics

   King Abdullah University of Science and Technology · RWTH Aachen University

   Affiliation as printed

   Chair of Mathematics for Uncertainty Quantification, Department of Mathematics, RWTH Aachen University, Aachen, Germany

   Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia

7. Felix Terhag corresponding Aachen Chair of Mathematics for Uncertainty Quantification Department of Mathematics

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR) · RWTH Aachen University

   Affiliation as printed

   Chair of Mathematics for Uncertainty Quantification, Department of Mathematics, RWTH Aachen University, Aachen, Germany

   Institute of Software Technology, High-Performance Computing, German Aerospace Center (DLR), Cologne, Germany