An automatic deep learning approach for coronary artery calcium segmentation

TL;DR

This paper introduces a deep learning system using CNNs for automatic segmentation and calcium scoring of coronary artery calcifications in cardiac CT images, achieving high accuracy and agreement with expert assessments.

Contribution

The study presents a novel CNN-based method for automatic coronary calcium detection and scoring, demonstrating high sensitivity, specificity, and correlation with manual evaluation.

Findings

Sensitivity of 91.24% for lesion detection

Pearson correlation coefficient of 0.983 with manual scores

High agreement (Cohen's k = 0.879) with expert risk prediction

Abstract

Coronary artery calcium (CAC) is a significant marker of atherosclerosis and cardiovascular events. In this work we present a system for the automatic quantification of calcium score in ECG-triggered non-contrast enhanced cardiac computed tomography (CT) images. The proposed system uses a supervised deep learning algorithm, i.e. convolutional neural network (CNN) for the segmentation and classification of candidate lesions as coronary or not, previously extracted in the region of the heart using a cardiac atlas. We trained our network with 45 CT volumes; 18 volumes were used to validate the model and 56 to test it. Individual lesions were detected with a sensitivity of 91.24%, a specificity of 95.37% and a positive predicted value (PPV) of 90.5%; comparing calcium score obtained by the system and calcium score manually evaluated by an expert operator, a Pearson coefficient of 0.983 was obtained. A high agreement (Cohen's k = 0.879) between manual and automatic risk prediction was also observed. These results demonstrated that convolutional neural networks can be effectively applied for the automatic segmentation and classification of coronary calcifications.