Automatic CAD-RADS Scoring Using Deep Learning

Abstract

Coronary CT angiography (CCTA) has established its role as a non-invasive modality for the diagnosis of coronary artery disease (CAD). The CAD-Reporting and Data System (CAD-RADS) has been developed to standardize communication and aid in decision making based on CCTA findings. The CAD-RADS score is determined by manual assessment of all coronary vessels and the grading of lesions within the coronary artery tree. We propose a bottom-up approach for fully-automated prediction of this score using deep-learning operating on a segment-wise representation of the coronary arteries. The method relies solely on a prior fully-automated centerline extraction and segment labeling and predicts the segment-wise stenosis degree and the overall calcification grade as auxiliary tasks in a multi-task learning setup. We evaluate our approach on a data collection consisting of 2,867 patients. On the task of identifying patients with a CAD-RADS score indicating the need for further invasive investigation our approach reaches an area under curve (AUC) of 0.923 and an AUC of 0.914 for determining whether the patient suffers from CAD. This level of performance enables our approach to be used in a fully-automated screening setup or to assist diagnostic CCTA reading, especially due to its neural architecture design -- which allows comprehensive predictions.

Published at MICCAI 2020

Cited by in corpus (12)

• Guidelines and Evaluation of Clinical Explainable AI in Medical Image Analysis
• Memory-aware curriculum federated learning for breast cancer classification
• An Adaptive and Altruistic PSO-based Deep Feature Selection Method for Pneumonia Detection from Chest X-Rays
• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• Simultaneous segmentation and classification of the retinal arteries and veins from color fundus images
• Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
• Curriculum learning for improved femur fracture classification: scheduling data with prior knowledge and uncertainty
• FIESTA: Autoencoders for accurate fiber segmentation in tractography
• Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise
• NeXtQSM -- A complete deep learning pipeline for data-consistent quantitative susceptibility mapping trained with hybrid data
• Synthetic Data-Driven Multi-Architecture Framework for Automated Polyp Segmentation Through Integrated Detection and Mask Generation
• Predicting Images for the Dynamics Of stellar Clusters (π-DOC): a deep learning framework to predict mass, distance and age of globular clusters