University Medical Center Utrecht (Lessmann et al.)
Model weights not public. Contact creators for more information.
Two-stage convolutional neural network that automatically detects and anatomically labels coronary artery, thoracic aorta, and cardiac-valve calcifications in low-dose chest CT acquired for lung-cancer screening. A first CNN with a large receptive field (via dilated convolutions) identifies and anatomically labels candidate calcifications; a second CNN filters true positives from the candidates. Trained and evaluated on 1,744 CT scans from the National Lung Screening Trial (NLST), reaching an F1 of 0.89 (soft-filter reconstructions) / 0.84 (sharp-filter reconstructions) for coronary artery calcifications and a linearly-weighted kappa of 0.90-0.91 for per-subject cardiovascular risk categorization versus the manual reference standard.
Architecture
CNN (2D)
Two consecutive 2D CNNs with dilated convolutions: a candidate-identification/anatomical-labeling network with an enlarged receptive field, followed by a true-positive classification network, applied per axial slice
Framework
Other
Added to catalog
2026-08-12
Low-dose chest CT scans from heavy smokers in the NLST lung-cancer screening trial, reconstructed with both soft and medium/sharp filters, with per-scan coronary artery, thoracic aorta, and cardiac-valve calcification annotations.
Per-slice detection and anatomical labeling of coronary artery, thoracic aorta, and cardiac-valve calcifications in low-dose chest CT
Per-subject cardiovascular risk categorization from total coronary artery calcium (Agatston-based risk categories)