Spatiotemporal Disentanglement of Arteriovenous Malformations in Digital Subtraction Angiography
This addresses the difficulty clinicians face in visualizing cerebrovascular anatomy for AVM treatment, though it appears incremental as it combines existing techniques.
The researchers tackled the problem of interpreting entangled vasculature in Digital Subtraction Angiography (DSA) for arteriovenous malformations (AVMs) by developing a method that automatically classifies vessels, resulting in efficient differentiation between arteries and veins for enhanced clinical visualizations.
Although Digital Subtraction Angiography (DSA) is the most important imaging for visualizing cerebrovascular anatomy, its interpretation by clinicians remains difficult. This is particularly true when treating arteriovenous malformations (AVMs), where entangled vasculature connecting arteries and veins needs to be carefully identified.The presented method aims to enhance DSA image series by highlighting critical information via automatic classification of vessels using a combination of two learning models: An unsupervised machine learning method based on Independent Component Analysis that decomposes the phases of flow and a convolutional neural network that automatically delineates the vessels in image space. The proposed method was tested on clinical DSA images series and demonstrated efficient differentiation between arteries and veins that provides a viable solution to enhance visualizations for clinical use.