Robust PCA Unrolling Network for Super-resolution Vessel Extraction in X-ray Coronary Angiography

TL;DR

This paper introduces a novel unrolled robust PCA network with sparse feature selection for super-resolution vessel extraction in X-ray coronary angiography, effectively handling noise, artefacts, and dynamic backgrounds.

Contribution

It presents a new deep unrolling network that integrates robust PCA with spatiotemporal super-resolution for improved vessel imaging in XCA.

Findings

Outperforms state-of-the-art methods in vessel network imaging

Effectively reduces noise and artefacts in XCA images

Enhances the intensity and geometry profiles of vessels

Abstract

Although robust PCA has been increasingly adopted to extract vessels from X-ray coronary angiography (XCA) images, challenging problems such as inefficient vessel-sparsity modelling, noisy and dynamic background artefacts, and high computational cost still remain unsolved. Therefore, we propose a novel robust PCA unrolling network with sparse feature selection for super-resolution XCA vessel imaging. Being embedded within a patch-wise spatiotemporal super-resolution framework that is built upon a pooling layer and a convolutional long short-term memory network, the proposed network can not only gradually prune complex vessel-like artefacts and noisy backgrounds in XCA during network training but also iteratively learn and select the high-level spatiotemporal semantic information of moving contrast agents flowing in the XCA-imaged vessels. The experimental results show that the proposed method significantly outperforms state-of-the-art methods, especially in the imaging of the vessel network and its distal vessels, by restoring the intensity and geometry profiles of heterogeneous vessels against complex and dynamic backgrounds.