CAD-RADS scoring of coronary CT angiography with Multi-Axis Vision Transformer: A clinically-inspired deep learning pipeline.

CAD-RADS Coronary Artery Disease Deep Learning Explainable AI Max-ViT

Journal

Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513

Informations de publication

Date de publication:
21 Dec 2023
Historique:
received: 26 08 2023
revised: 10 11 2023
accepted: 17 12 2023
medline: 24 12 2023
pubmed: 24 12 2023
entrez: 23 12 2023
Statut: aheadofprint

Résumé

The standard non-invasive imaging technique used to assess the severity and extent of Coronary Artery Disease (CAD) is Coronary Computed Tomography Angiography (CCTA). However, manual grading of each patient's CCTA according to the CAD-Reporting and Data System (CAD-RADS) scoring is time-consuming and operator-dependent, especially in borderline cases. This work proposes a fully automated, and visually explainable, deep learning pipeline to be used as a decision support system for the CAD screening procedure. The pipeline performs two classification tasks: firstly, identifying patients who require further clinical investigations and secondly, classifying patients into subgroups based on the degree of stenosis, according to commonly used CAD-RADS thresholds. The pipeline pre-processes multiplanar projections of the coronary arteries, extracted from the original CCTAs, and classifies them using a fine-tuned Multi-Axis Vision Transformer architecture. With the aim of emulating the current clinical practice, the model is trained to assign a per-patient score by stacking the bi-dimensional longitudinal cross-sections of the three main coronary arteries along channel dimension. Furthermore, it generates visually interpretable maps to assess the reliability of the predictions. When run on a database of 1873 three-channel images of 253 patients collected at the Monzino Cardiology Center in Milan, the pipeline obtained an AUC of 0.87 and 0.93 for the two classification tasks, respectively. According to our knowledge, this is the first model trained to assign CAD-RADS scores learning solely from patient scores and not requiring finer imaging annotation steps that are not part of the clinical routine.

Sections du résumé

BACKGROUND AND OBJECTIVE OBJECTIVE
The standard non-invasive imaging technique used to assess the severity and extent of Coronary Artery Disease (CAD) is Coronary Computed Tomography Angiography (CCTA). However, manual grading of each patient's CCTA according to the CAD-Reporting and Data System (CAD-RADS) scoring is time-consuming and operator-dependent, especially in borderline cases. This work proposes a fully automated, and visually explainable, deep learning pipeline to be used as a decision support system for the CAD screening procedure. The pipeline performs two classification tasks: firstly, identifying patients who require further clinical investigations and secondly, classifying patients into subgroups based on the degree of stenosis, according to commonly used CAD-RADS thresholds.
METHODS METHODS
The pipeline pre-processes multiplanar projections of the coronary arteries, extracted from the original CCTAs, and classifies them using a fine-tuned Multi-Axis Vision Transformer architecture. With the aim of emulating the current clinical practice, the model is trained to assign a per-patient score by stacking the bi-dimensional longitudinal cross-sections of the three main coronary arteries along channel dimension. Furthermore, it generates visually interpretable maps to assess the reliability of the predictions.
RESULTS RESULTS
When run on a database of 1873 three-channel images of 253 patients collected at the Monzino Cardiology Center in Milan, the pipeline obtained an AUC of 0.87 and 0.93 for the two classification tasks, respectively.
CONCLUSION CONCLUSIONS
According to our knowledge, this is the first model trained to assign CAD-RADS scores learning solely from patient scores and not requiring finer imaging annotation steps that are not part of the clinical routine.

Identifiants

pubmed: 38141455
pii: S0169-2607(23)00655-7
doi: 10.1016/j.cmpb.2023.107989
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

107989

Informations de copyright

Copyright © 2023 The Author(s). Published by Elsevier B.V. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of Competing Interest Riccardo Bellazzi is co-founder and shareholder of two spin-offs of the University of Pavia (Engenome s.r.l. and Biomeris s.r.l.) that operate in the field of data management, artificial intelligence and bioinformatics. All the other authors have nothing to declare.

Auteurs

Alessia Gerbasi (A)

Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, Pavia, Italy. Electronic address: alessia.gerbasi01@universitadipavia.it.

Arianna Dagliati (A)

Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, Pavia, Italy.

Giuseppe Albi (G)

Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, Pavia, Italy.

Mattia Chiesa (M)

Centro Cardiologico Monzino IRCCS, Milan, Italy.

Daniele Andreini (D)

Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Biomedical and Clinical Sciences, University of Milan, Milan, Italy.

Andrea Baggiano (A)

Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Clinical Sciences and Community Health, University of Milan, Milan, Italy.

Saima Mushtaq (S)

Centro Cardiologico Monzino IRCCS, Milan, Italy.

Gianluca Pontone (G)

Centro Cardiologico Monzino IRCCS, Milan, Italy; Department of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy.

Riccardo Bellazzi (R)

Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, Pavia, Italy; IRCCS Istituti Clinici Scientifici Maugeri, Pavia, Pavia, Italy.

Gualtiero Colombo (G)

Centro Cardiologico Monzino IRCCS, Milan, Italy.

Classifications MeSH