Deep Learning Algorithms for Coronary Artery Plaque Characterisation from CCTA Scans

TL;DR

This paper compares and enhances three deep learning methods for non-invasive coronary artery plaque assessment from CCTA scans, achieving improved accuracy in predicting revascularisation decisions with AUCs up to 0.90.

Contribution

It introduces a novel 2.5D deep learning approach and improves existing 3D-RCNN and multi-view texture models for better plaque characterization.

Findings

Improved AUC from 0.80 to 0.90 for 3D-RCNN

Enhanced AUC from 0.85 to 0.90 for multi-view approach

Proposed 2.5D method achieves AUC of 0.90

Abstract

Analysing coronary artery plaque segments with respect to their functional significance and therefore their influence to patient management in a non-invasive setup is an important subject of current research. In this work we compare and improve three deep learning algorithms for this task: A 3D recurrent convolutional neural network (RCNN), a 2D multi-view ensemble approach based on texture analysis, and a newly proposed 2.5D approach. Current state of the art methods utilising fluid dynamics based fractional flow reserve (FFR) simulation reach an AUC of up to 0.93 for the task of predicting an abnormal invasive FFR value. For the comparable task of predicting revascularisation decision, we are able to improve the performance in terms of AUC of both existing approaches with the proposed modifications, specifically from 0.80 to 0.90 for the 3D-RCNN, and from 0.85 to 0.90 for the multi-view texture-based ensemble. The newly proposed 2.5D approach achieves comparable results with an AUC of 0.90.