A Cascade Approach for Automatic Segmentation of Coronary Arteries Calcification in Computed Tomography Images Using Deep Learning

One of the indicators of possible occurrences of cardiovascular diseases is the amount of coronary artery calcium. Recently, approaches using new technologies such as deep learning have been used to help identify these indicators. This work proposes a segmentation method for calcification of the coronary arteries that has three steps: (1) extraction of the ROI using U-Net with batch normalization after convolution layers, (2) segmentation of the calcifications and (3) removal of false positives using Modified U-Net with EfficientNet. The method uses histogram matching as preprocessing in order to increase the contrast between tissue and calcification and normalize the different types of exams. Multiple architectures were tested and the best achieved 96.9% F1-Score, 97.1% recall and 98.3% in the OrcaScore Dataset.