
Research Article
A Cascade Approach for Automatic Segmentation of Coronary Arteries Calcification in Computed Tomography Images Using Deep Learning
@INPROCEEDINGS{10.1007/978-3-031-60665-6_7, author={Alan de C. Ara\^{u}jo and Arist\^{o}fanes C. Silva and Jo\"{a}o M. Pedrosa and Italo F. S. Silva and Jo\"{a}o O. B. Diniz}, title={A Cascade Approach for Automatic Segmentation of Coronary Arteries Calcification in Computed Tomography Images Using Deep Learning}, proceedings={Wireless Mobile Communication and Healthcare. 12th EAI International Conference, MobiHealth 2023, Vila Real, Portugal, November 29-30, 2023 Proceedings}, proceedings_a={MOBIHEALTH}, year={2024}, month={6}, keywords={Coronary artery calcium Segmentation U-Net EfficientNetB0 OrcaScore Dataset}, doi={10.1007/978-3-031-60665-6_7} }
- Alan de C. Araújo
Aristófanes C. Silva
João M. Pedrosa
Italo F. S. Silva
João O. B. Diniz
Year: 2024
A Cascade Approach for Automatic Segmentation of Coronary Arteries Calcification in Computed Tomography Images Using Deep Learning
MOBIHEALTH
Springer
DOI: 10.1007/978-3-031-60665-6_7
Abstract
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.