Coronary artery segmentation in non-contrast calcium scoring CT images using deep learning

Abstract

Precise localization of coronary arteries in Computed Tomography (CT) scans is critical from the perspective of medical assessment of various heart pathologies. Although manifold methods exist that offer high-quality segmentation of coronary arteries in cardiac contrast-enhanced CT scans, the potential of less invasive, non-contrast CT is still not fully exploited. Since such fine anatomical structures are hardly visible in this type of medical image, the existing methods are characterized by high recall and low precision, and are used mainly for filtering of calcified atherosclerotic plaques in the context of calcium scoring. In this paper, we address this research gap and introduce a deep learning algorithm for segmenting coronary arteries in multi-vendor ECG-gated non-contrast cardiac CT images which benefits from a novel framework for semi-automatic generation of Ground Truth (GT) via image registration. We hypothesize that the proposed GT generation process is much more efficient in this case than manual segmentation, as it allows for a fast generation of large volumes of diverse data, which translates to well-generalizing models. To thoroughly evaluate the segmentation quality based on such an approach, we propose a novel method for manual mesh-to-image registration, which is used to create our test-GT. The experimental study shows that our AutoML-powered deep machine learning model delineates the coronary arteries significantly more accurately than the GT used for its training, and leads to the Dice and clDice metrics close to the interrater variability.

Keywords: Coronary arteries; Deep learning; Ground-truth generation; Non-contrast CT; Segmentation.