Coronary artery disease detection using deep learning and ultrahigh-resolution photon-counting coronary CT angiography - 04/10/24

Doi : 10.1016/j.diii.2024.09.012

Jan M. Brendel ^a, Jonathan Walterspiel ^a, Florian Hagen ^a, Jens Kübler ^a, Andreas S. Brendlin ^a, Saif Afat ^a, Jean-François Paul ^b,^c, Thomas Küstner ^d, Konstantin Nikolaou ^a, Meinrad Gawaz ^e, Simon Greulich ^e, Patrick Krumm ^a,^⁎ , Moritz T. Winkelmann ^a
^a Department of Radiology, Diagnostic and Interventional Radiology, University of Tübingen, 72076, Germany
^b Institut Mutualiste Montsouris, Department of Radiology, Cardiac Imaging, 75014 Paris, France
^c Spimed-AI, 75014 Paris, France
^d Department of Radiology, Diagnostic and Interventional Radiology, Medical Image and Data Analysis (MIDAS.lab), University of Tübingen, 72076, Germany
^e Department of Internal Medicine III, Cardiology and Angiology, University of Tübingen, 72076, Germany

^⁎Corresponding author.

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Friday 04 October 2024

Highlights

•	Artificial intelligence shows remarkable performance in detecting significant coronary artery disease on ultrahigh-resolution photon-counting CT.
•	Artificial intelligence may serve as a valuable pre-reading tool to assist human readers for coronary artery disease detection on photon-counting coronary CT angiography in daily clinical practice.
•	Integrating artificial intelligence for coronary artery disease detection could improve workflow efficiency and help radiologists manage increasing workloads.

Le texte complet de cet article est disponible en PDF.

Abstract

Purpose

The purpose of this study was to evaluate the diagnostic performance of automated deep learning in the detection of coronary artery disease (CAD) on photon-counting coronary CT angiography (PC-CCTA).

Materials and methods

Consecutive patients with suspected CAD who underwent PC-CCTA between January 2022 and December 2023 were included in this retrospective, single-center study. Non-ultra-high resolution (UHR) PC-CCTA images were analyzed by artificial intelligence using two deep learning models (CorEx, Spimed-AI), and compared to human expert reader assessment using UHR PC-CCTA images. Diagnostic performance for global CAD assessment (at least one significant stenosis ≥ 50 %) was estimated at patient and vessel levels.

Results

A total of 140 patients (96 men, 44 women) with a median age of 60 years (first quartile, 51; third quartile, 68) were evaluated. Significant CAD on UHR PC-CCTA was present in 36/140 patients (25.7 %). The sensitivity, specificity, accuracy, positive predictive value), and negative predictive value of deep learning-based CAD were 97.2 %, 81.7 %, 85.7 %, 64.8 %, and 98.9 %, respectively, at the patient level and 96.6 %, 86.7 %, 88.1 %, 53.8 %, and 99.4 %, respectively, at the vessel level. The area under the receiver operating characteristic curve was 0.90 (95 % CI: 0.83–0.94) at the patient level and 0.92 (95 % CI: 0.89–0.94) at the vessel level.

Conclusion

Automated deep learning shows remarkable performance for the diagnosis of significant CAD on non-UHR PC-CCTA images. AI pre-reading may be of supportive value to the human reader in daily clinical practice to target and validate coronary artery stenosis using UHR PC-CCTA.

Le texte complet de cet article est disponible en PDF.

Keywords : Computed tomography, Coronary artery disease, Deep learning, Photon-counting CT, Ultrahigh resolution

Abbreviations : AI, AUC, CAD, CAD-RADS, CCTA, CDTI_vol, CI, DLP, FFR, FFRai, PC, PC-CCTA, PPV, NPV, SD, UHR