A probabilistic deep motion model for unsupervised cardiac shape anomaly assessment

Zakeri, A., Hokmabadi, A., Ravikumar, N., Frangi, A. F. and Gooya, A. (2022) A probabilistic deep motion model for unsupervised cardiac shape anomaly assessment. Medical Image Analysis, 75, 102276. (doi: 10.1016/j.media.2021.102276) (PMID:34753021)

Abstract

Automatic shape anomaly detection in large-scale imaging data can be useful for screening suboptimal segmentations and pathologies altering the cardiac morphology without intensive manual labour. We propose a deep probabilistic model for local anomaly detection in sequences of heart shapes, modelled as point sets, in a cardiac cycle. A deep recurrent encoder-decoder network captures the spatio-temporal dependencies to predict the next shape in the cycle and thus derive the outlier points that are attributed to excessive deviations from the network prediction. A predictive mixture distribution models the inlier and outlier classes via Gaussian and uniform distributions, respectively. A Gibbs sampling Expectation-Maximisation (EM) algorithm computes soft anomaly scores of the points via the posterior probabilities of each class in the E-step and estimates the parameters of the network and the predictive distribution in the M-step. We demonstrate the versatility of the method using two shape datasets derived from: (i) one million biventricular CMR images from 20,000 participants in the UK Biobank (UKB), and (ii) routine diagnostic imaging from Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac Image (M & Ms). Experiments show that the detected shape anomalies in the UKB dataset are mostly associated with poor segmentation quality, and the predicted shape sequences show significant improvement over the input sequences. Furthermore, evaluations on U-Net based shapes from the M and Ms dataset reveals that the anomalies are attributable to the underlying pathologies that affect the ventricles. The proposed model can therefore be used as an effective mechanism to sift shape anomalies in large-scale cardiac imaging pipelines for further analysis.

• Item Type: Articles
• Additional Information: This work was supported by the Engineering and Physical Sciences Research Council (EPSRC) (grant number EP/S012796/1). AFF is partially supported by a Royal Academy of Engineering Chair in Emerging Technologies Scheme (CiET1819/19) and CardioX (GrowMedTech POC041).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Gooya, Dr Ali
• Authors: Zakeri, A., Hokmabadi, A., Ravikumar, N., Frangi, A. F., and Gooya, A.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: Medical Image Analysis
• Publisher: Elsevier
• ISSN: 1361-8415
• ISSN (Online): 1361-8423
• Published Online: 16 October 2021