Deformable Registration of MRA and 4D Flow Images to Facilitate Accurate Estimation of Flow Properties within Blood Vessels

TL;DR

This paper introduces a robust method for aligning MRA and 4D Flow images to accurately estimate blood flow properties, improving the analysis of vessel networks in medical imaging.

Contribution

The novel registration approach aligns vessel centerlines from MRA with blood flow data from 4D Flow images, enhancing flow estimation accuracy.

Findings

Median distance between centerlines decreased by 83.5% on average.

Blood flow estimates increased significantly after registration.

Method proved robust to noise and partial data omissions.

Abstract

A method is presented for the registration of MRA and 4D Flow images, with the goal of calculating blood flow properties using both modalities simultaneously. In particular, the method produces an alignment of segmentations of vessel networks, from MRA images, with the blood velocity field within those networks, from the corresponding 4D Flow images. The alignment procedure is driven by the registration of centerlines of vessels extracted from the two modalities. Our approach is robust to noise, small deformations, and partial omissions of vessel surfaces and/or blood velocities. The alignment procedure is tested on 7 patient data sets acquired at Texas Children's Hospital. The quality of the resulting alignment is assessed by (i) an illustration of the aligned and unaligned surface segmentations for a sample patient, (ii) histograms of distances between centerline networks, and (iii) graphs of estimated blood flow. For each of the 7 analyzed data sets, medians of the distance histograms decreased an average of 83.5%, and the estimated blood flow increased significantly as a result of the alignment procedure.