End-to-End Deep Learning Model for Cardiac Cycle Synchronization from Multi-View Angiographic Sequences

TL;DR

This paper presents a deep learning approach to synchronize multi-view angiographic sequences during the cardiac cycle, enabling accurate 3D reconstructions crucial for clinical diagnosis.

Contribution

A novel neural network method that uses raw angiographic videos to automatically synchronize views based on cardiac cycle features, without requiring external signals.

Findings

Achieved 96.04% accuracy in frame synchronization with ECG signals.

Demonstrated effective temporal matching of angiographic sequences.

Enabled improved 3D cardiac imaging for clinical use.

Abstract

Dynamic reconstructions (3D+T) of coronary arteries could give important perfusion details to clinicians. Temporal matching of the different views, which may not be acquired simultaneously, is a prerequisite for an accurate stereo-matching of the coronary segments. In this paper, we show how a neural network can be trained from angiographic sequences to synchronize different views during the cardiac cycle using raw x-ray angiography videos exclusively. First, we train a neural network model with angiographic sequences to extract features describing the progression of the cardiac cycle. Then, we compute the distance between the feature vectors of every frame from the first view with those from the second view to generate distance maps that display stripe patterns. Using pathfinding, we extract the best temporally coherent associations between each frame of both videos. Finally, we compare the synchronized frames of an evaluation set with the ECG signals to show an alignment with 96.04% accuracy.