University of California, San Francisco (Avram, Tison et al.)
Training code and model weights not public. Contact creators for more information.
Fully automated pipeline for interpreting coronary angiograms that chains four purpose-built neural networks: (1) angiographic projection-angle identification, (2) left/right coronary artery detection, (3) arterial segment localization, and (4) stenosis-severity estimation. Trained on 13,843 angiographic studies (195,195 videos) from 11,972 adult patients at UCSF (2008-2019), with projection-angle and LCA/RCA-detection tasks each reaching precision/sensitivity/F1 at or above 90%. For predicting obstructive coronary artery disease (>=70% stenosis), CathAI reaches an AUC of 0.862 internally, 0.869 on external angiograms from the University of Ottawa Heart Institute, and 0.775 after retraining on quantitative-coronary-angiography labels from the Montreal Heart Institute core lab. No public code or model weights have been released.
Architecture
Hybrid
Sequential pipeline of purpose-built CNNs: projection-angle classifier, LCA/RCA detector, arterial-segment localizer (with bounding boxes), and a stenosis-severity estimation network
Added to catalog
2026-08-10
UCSF Coronary Angiography Cohort (CathAI)
13,843 angiographic studies (195,195 total angiographic videos) from 11,972 adult patients; mean age 63.5 (SD 13.7) years.
University of Ottawa Heart Institute Angiography Cohort
Real-world coronary angiograms used as an external validation cohort for the CathAI stenosis-estimation pipeline.
Angiographic projection-angle identification and left/right coronary artery detection (pipeline stages 1-2)
Localization of coronary artery stenosis within the angiogram
Binary classification of obstructive coronary artery disease (>=70% stenosis) from coronary angiogram segments