Automated Segmentation and Hemodynamic Quantification

Deep learning and automated segmentation support left-atrial flow quantification and intracranial 4D flow vessel analysis.

Overview

These methods apply to cardiovascular and neurovascular imaging.

Automated segmentation enables more scalable quantitative flow analysis.

Image analysis, 4D flow, and clinical translation are developed together.

automated segmentationdeep learningquantification

Research overview

Figure showing automated left atrial and left atrial appendage segmentation with hemodynamic maps.

Selected work

Deep learning based automated left atrial segmentation and flow quantification of real time phase contrast MRI in patients with atrial fibrillation

Baraboo J, DiCarlo A, Berhane H, Shen D, Passman R, Lee DC, McCarthy PM, Arora R, Kim D, Markl M. Int J Cardiovasc Imaging. 2025.

Automated intracranial vessel segmentation of 4D flow MRI data in patients with atherosclerotic stenosis using a convolutional neural network

Winter P, Berhane H, Moore JE, Aristova M, Reichl T, Wollenberg J, Richter A, Jarvis KB, Patel A, Caprio FZ, Abdalla RN, Ansari SA, Markl M, Schnell S. Front Radiol. 2024.

MRI Investigation of the Association of Left Atrial and Left Atrial Appendage Hemodynamics with Silent Brain Infarction

Pradella M, Baraboo JJ, Prabhakaran S, Zhao L, Hijaz T, McComb EN, Naidich MJ, Heckbert SR, Nasrallah IM, Bryan RN, Passman RS, Markl M, Greenland P. J Magn Reson Imaging. 2025.

Uncertainty-aware automated labeling of intracranial arteries using deep learning

Bisbal J, Winter P, Jofre S, Ponce A, Ansari SA, Abdalla R, Markl M, Welin Odeback O, Uribe S, Tejos C, Sotelo J, Schnell S, Marlevi D. BMC Med Imaging. 2026.