Fast Prospective Detection of Contrast Inflow in X-ray Angiograms with Convolutional Neural Network and Recurrent Neural Network

TL;DR

This paper introduces two fast, prospective methods using CNN and LSTM to detect contrast inflow in X-ray angiograms, improving robustness over existing techniques and suitable for clinical use.

Contribution

The paper presents novel CNN and LSTM-based approaches for real-time contrast inflow detection in X-ray sequences, enhancing robustness and clinical applicability.

Findings

Both methods accurately detect contrast frames

They outperform current state-of-the-art techniques

The approaches are fast and suitable for clinical deployment

Abstract

Automatic detection of contrast inflow in X-ray angiographic sequences can facilitate image guidance in computer-assisted cardiac interventions. In this paper, we propose two different approaches for prospective contrast inflow detection. The methods were developed and evaluated to detect contrast frames from X-ray sequences. The first approach trains a convolutional neural network (CNN) to distinguish whether a frame has contrast agent or not. The second method extracts contrast features from images with enhanced vessel structures; the contrast frames are then detected based on changes in the feature curve using long short-term memory (LSTM), a recurrent neural network architecture. Our experiments show that both approaches achieve good performance on detection of the beginning contrast frame from X-ray sequences and are more robust than a state-of-the-art method. As the proposed methods work in prospective settings and run fast, they have the potential of being used in clinical practice.