Skip to Main Content
About this Publication
Generative models for reproducible coronary calcium scoring.
Pubmed ID
35664539 (View this publication on the PubMed website)
Digital Object Identifier
J Med Imaging (Bellingham). 2022 Sep; Volume 9 (Issue 5): Pages 052406
van Velzen SGM, de Vos BD, Noothout JMH, Verkooijen HM, Viergever MA, Išgum I
  • Amsterdam UMC location University of Amsterdam, Department of Biomedical Engineering and Physics, Amsterdam, The Netherlands.
  • University Medical Center Utrecht, Imaging Division, Utrecht, The Netherlands.
  • Utrecht University, University Medical Center Utrecht, Image Sciences Institute, Utrecht, The Netherlands.

Purpose: Coronary artery calcium (CAC) score, i.e., the amount of CAC quantified in CT, is a strong and independent predictor of coronary heart disease (CHD) events. However, CAC scoring suffers from limited interscan reproducibility, which is mainly due to the clinical definition requiring application of a fixed intensity level threshold for segmentation of calcifications. This limitation is especially pronounced in non-electrocardiogram-synchronized computed tomography (CT) where lesions are more impacted by cardiac motion and partial volume effects. Therefore, we propose a CAC quantification method that does not require a threshold for segmentation of CAC. Approach: Our method utilizes a generative adversarial network (GAN) where a CT with CAC is decomposed into an image without CAC and an image showing only CAC. The method, using a cycle-consistent GAN, was trained using 626 low-dose chest CTs and 514 radiotherapy treatment planning (RTP) CTs. Interscan reproducibility was compared to clinical calcium scoring in RTP CTs of 1662 patients, each having two scans. Results: A lower relative interscan difference in CAC mass was achieved by the proposed method: 47% compared to 89% manual clinical calcium scoring. The intraclass correlation coefficient of Agatston scores was 0.96 for the proposed method compared to 0.91 for automatic clinical calcium scoring. Conclusions: The increased interscan reproducibility achieved by our method may lead to increased reliability of CHD risk categorization and improved accuracy of CHD event prediction.

Related CDAS Studies
Related CDAS Projects