About

Michael Markl is the Lester B. and Frances T. Knight Professor of Cardiac Imaging and a Professor of Biomedical Engineering at Northwestern University Feinberg School of Medicine. His research program focuses on developing multi-parametric imaging techniques to better understand the physiological mechanisms of heart disease and stroke, as well as the impact of therapy. His work has been instrumental in establishing '4D Flow MRI' for comprehensive assessment of cardiovascular hemodynamics in heart disease and stroke. Additionally, he has contributed to the development, validation, and application of novel imaging tools for evaluating the structure and function of the heart.

Research topics

• Computer Science
• Medicine
• Cardiology
• Artificial Intelligence
• Internal medicine
• Mathematics
• Radiology
• Political Science
• Physics
• Statistics
• Anatomy
• Mechanics
• Nuclear magnetic resonance
• Biomedical engineering
• Nuclear medicine
• Engineering
• Materials science
• Genetics
• Medical physics
• Law
• Biology

Selected publications

• Uncertainty-aware automated labeling of intracranial arteries using deep learning

  BMC Medical Imaging · 2026-03-16

  articleOpen access

  Accurate anatomical labeling of intracranial arteries is critical for cerebrovascular diagnosis and hemodynamic analysis, but remains time-consuming and prone to inter-operator variability. While deep learning provides an automated solution, its clinical adoption is limited by the lack of confidence measures. Incorporating uncertainty quantification into automated labeling could enhance interpretability by identifying ambiguous or abnormal regions and support clinical trust, yet this aspect remains underexplored. To address this gap, we introduce an uncertainty-aware deep learning framework for automated artery labeling from 3D Time-of-Flight Magnetic Resonance Angiography (3D ToF-MRA) segmentations (n = 35). Three convolutional neural network architectures were evaluated: (1) UNet with residual encoder blocks, (2) CS-Net, an attention-augmented UNet with spatial attention, and (3) nnUNet, a self-configuring framework that adapts architecture and training to dataset characteristics. Confidence was modeled via test-time augmentation (TTA) combined with a novel coordinate-guided strategy to reduce interpolation errors during inference. Generalizability was assessed by evaluating a subset of the public TubeTK ToF-MRA dataset (n = 20). Voxelwise uncertainty maps highlighted anatomical ambiguities, pathological variations, and inconsistencies in manual references, providing intuitive confidence indicators. nnUNet achieved the highest performance (average Dice score 0.93; clDice 0.94; average surface distance 0.35 mm; 95th percentile of Hausdorff distance 4.51 mm), demonstrating robustness in complex vascular regions. On the TubeTK dataset, nnUNet maintained robust generalization (average Dice score 0.87; clDice 0.87; average surface distance 0.42 mm; 95th percentile of Hausdorff distance 5.85 mm). Validation against co-registered 4D flow MRI showed close agreement between flow velocities derived from automated and manual labels, with no significant differences. The proposed framework delivers a scalable, accurate, and uncertainty-aware solution for intracranial artery labeling. By integrating uncertainty quantification, it offers a transparent and clinically trustworthy tool to facilitate cerebrovascular imaging workflows and support subsequent hemodynamic analyses.

  PublisherDOI

• <scp>5D</scp> Flow <scp>MRI</scp> Reveals Respiration‐Driven Changes in Blood Flow Energetics in Congenital Heart Disease

  Magnetic Resonance in Medicine · 2026-04-26

  articleOpen accessSenior author

  ABSTRACT Purpose Hemodynamic monitoring is essential for patients with right‐sided congenital heart disease (CHD). Respiration may have an increased impact on pulmonary flow in these patients that cannot be assessed by standard tools including 4D flow MRI. This study uses 5D flow MRI to assess respiratory‐cycle variations in flow energetics in patients with CHD. Methods 5D flow was acquired with four respiratory states in 14 Fontan patients (21 ± 8 years, 8 female), 10 intracardiac shunt patients (19 ± 13 years, 8 female), and 9 controls (26 ± 6 years, 1 female). Blood kinetic energy (KE mean ), viscous energy loss (EL total ), and EL fraction (EL total /KE mean ) as a measure of flow inefficiency were calculated in inferior and superior caval veins (IVC, SVC), pulmonary arteries (PA), and aorta. Correlations were assessed with clinical markers of altered cardiac flow function. Results 5D flow was acquired with acceleration factor R = 37–93 varying between respiratory states. Fontan and shunt patients demonstrated significant respiratory‐driven changes in pulmonary flow energetics compared to controls. Fontan IVC and PA KE mean were increased during inspiration (+43%, +37%, p &lt; 0.001) and decreased during expiration (−40%, −35%, p &lt; 0.001), resulting in increased expiratory EL fraction (+34%, +30%, p &lt; 0.05). Shunt patients showed a similar effect in IVC KE mean (+28%, −25%, p &lt; 0.05). Decreased expiratory IVC KE mean was associated with increased Fontan left–right PA flow differential (ρ = −0.68, p &lt; 0.05) and increased shunt Qp/Qs (ρ = −0.70, p &lt; 0.05). Conclusions The findings of this study show that CHD flow energetics and efficiency are modulated by respiration. Respiratory‐resolved imaging is needed to identify these dynamics and their relationships to overall cardiac function.

  PublisherDOI

• Multimodality imaging and computational fluid dynamics framework for quantifying wall shear stress on aortic valve leaflets in aortic stenosis

  Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2025-09-16

  article

  Motivation: Quantifying wall shear stress (WSS) on aortic valve leaflets is crucial for understanding platelet-vWF interactions and assessing the risk of aortic stenosis progression. Goal(s): Develop a multimodal framework to evaluate WSS on aortic valve leaflets in patients by integrating in-vivo, in-vitro, and in-silico imaging to capture valve morphology and flow velocity for precise WSS quantification. Approach: The study utilized CT and echocardiography data, performed 4D flow MRI and CFD simulations, validated CFD results against MRI data, and assessed WSS using the CFD simulation outcomes. Results: CFD results closely matched 4D flow MRI and provided regions of high WSS at the narrowest valve areas. Impact: This framework enables precise WSS mapping on aortic valve leaflets, supporting better AS progression risk assessment. Future investigations could validate the direct use of in-vivo 4D MRI combined with CFD, improving non-invasive diagnostics and treatment planning in AS patients.

  PublisherDOI

• Splanchnic hemodynamic parameters measured with 4D flow MRI can diagnose severe portal hypertension

  European Radiology · 2025-07-15

  article
  PublisherDOI

• 4D flow MRI of splanchnic vasculature for diagnosis of severe portal hypertension and prediction of outcomes

  Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2025-09-16

  article

  Motivation: Non-invasive detection of severe portal hypertension [PH; hepatic venous pressure gradient (HVPG)≥12 mmHg] is important to prevent decompensation and death in patients with chronic liver disease. Goal(s): We assess the diagnostic performance of hemodynamic parameters measured with 4D flow MRI in the splanchnic vasculature for diagnosis of severe PH and prediction of liver decompensation. Approach: In our prospective, single-center study, 56 patients with chronic liver disease had 4D flow MRI within a month of invasive HVPG measurement. Results: Splanchnic hemodynamic measurements by 4D flow MRI identified patients with severe portal hypertension with excellent diagnostic performance, and predicted liver decompensation with good diagnostic performance. Impact: 4D flow MRI diagnoses severe portal hypertension with excellent performance, and predicts hepatic decompensation with equivalent performance to HVPG, making it suitable for integration into surveillance MRI protocols for patients with liver cirrhosis.

  PublisherDOI

• Inter-AI Agreement in Measuring Cine MRI-Derived Cardiac Function and Motion Patterns: A Pilot Study

  Journal of Imaging Informatics in Medicine · 2025-07-08

  article
  PublisherDOI

• Aortic and Pulmonary 3D Blood Flow Dynamics Derived from Contrast Enhanced MRA by Fluid-Physics Informed Deep-Learning

  Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2025-09-16

  articleSenior author

  Motivation: 4D Flow MRI enables comprehensive hemodynamic assessments, but its clinical usage is hindered by long scan times. Contrast-enhanced MRA provides only anatomical information. Goal(s): To develop a series of fluid-physics informed deep-learning (FPI-DL) networks to derive information on time-resolved aortic and pulmonary artery 3D blood flow dynamics directly from cardiothoracic CEMRA. Approach: FPI-DL networks were trained with peak systolic velocities+normalized average velocity time-curve as an input and time-resolved 3D velocities as output. The FPI-DL networks were tested on CEMRA data and compared to pair 4D flow MRI as ground-truth. Results: AI-derived flow showed strong-to-excellent agreement to 4D flow MRI ground-truth across all comparisons. Impact: CEMRA is a widely available, standard-of-care test. As such, this technique enables wider access to complex hemodynamic information in the aorta and pulmonary arteries that generally requires 4D flow MRI, providing better overall patient management and assessments from CEMRA.

  PublisherDOI

• Flexible kt-GRAPPA-initiated compressed sensing reconstruction approach for accelerated dual-venc 5D flow imaging

  Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2025-09-16

  articleSenior author

  Motivation: Dual-venc 5D flow has been proposed to capture an increased dynamic range of hemodynamics over both the cardiac and respiratory cycles. However, scan time is prohibitively long. Goal(s): We propose a novel reconstruction method for accelerated dual-venc 5D flow that uses kt-GRAPPA-initiated compressed sensing to enable nearly 50% reduction in scan time. Approach: We retrospectively simulated dual-venc 5D flow acceleration in N=8 healthy volunteers. Kt-GRAPPA kernels were trained on reference data and applied to fill undersampled velocity encodes before input to compressed sensing. Results: Kt-GRAPPA-initiated compressed sensing had &lt;10% error in flow measurements with double the acceleration compared to standard dual-venc 5D flow. Impact: The proposed reconstruction method enables accelerated dual-venc 5D flow with approximately 50% reduction in scan time, increasing feasibility for a clinical setting. Potential applications include detailed analysis of cardiovascular hemodynamics over the respiratory cycle in patients with congenital heart disease.

  PublisherDOI

• Optimal Location, Regurgitant Volume and Regurgitant Fraction by CMR Derived 4D Flow Analysis for Discriminating Severe Aortic Regurgitation

  Heart Lung and Circulation · 2025-08-01

  articleOpen access
  PublisherOA PDFDOI

• SPIROMICS HF: Rationale, Design, and Reproducibility of Measures

  Circulation Heart Failure · 2025-11-05

  articleOpen access

  BACKGROUND: Although chronic obstructive pulmonary disease (COPD) and heart failure with preserved ejection fraction often coexist with overlapping clinical features, they are usually studied separately. The SPIROMICS HF (Subpopulations and Intermediate Outcome Measures in COPD and Heart Failure Study) is testing hypotheses that new computed tomography emphysema subtypes are associated with specific cardiovascular phenotypes (eg, cor pulmonale , cor pulmonale parvus ), common airway branch variants are associated with right heart dysfunction, and symptomatic tobacco-exposed persons with preserved spirometry have signs of increased left ventricular afterload. METHODS: SPIROMICS is a multicenter observational study of COPD with extensive pulmonary phenotyping of participants with ≥20 pack-years smoking and nonsmoking controls. COPD and COPD severity were defined by standard spirometric criteria and symptomatic tobacco-exposed persons with preserved spirometry by ≥20 pack-years, normal spirometry, and COPD Assessment Test score &gt;10. SPIROMICS HF selected all participants in SPIROMICS visit 5 at major sites. Its comprehensive speckle-tracking echocardiography, which included physiological perturbations of leg raise and low-intensity exercise, was harmonized prospectively with the Multi-Ethnic Study of Atherosclerosis Early Heart Failure and HeartSHARE (Combining Omics, Deep Phenotyping, and Electronic Health Records for Heart Failure Subtypes and Treatment Targets) studies. The cardiopulmonary magnetic resonance imaging protocol with gadolinium administration included myocardial fibrosis sequences, pulmonary angiography, time-resolved 3-dimensional cine magnetic resonance imaging (4-dimensional flow) of venous return, and metronome-paced tachypnea to induce dynamic hyperinflation. Coronary artery calcium was assessed on computed tomography scans. The Kansas City Cardiomyopathy Questionnaire was administered. RESULTS: Of the final sample of 753 participants, 57% had COPD (15% mild, 27% moderate, and 15% severe), 18% had symptomatic tobacco-exposed persons with preserved spirometry, 16% were smoking controls, and 8% were nonsmoking controls. Reproducibility of the main measures from speckle-tracking echocardiography (intraclass correlation coefficient, 0.83–0.99), exercise echocardiography (intraclass correlation coefficient, 0.71–0.99) and magnetic resonance imaging (intraclass correlation coefficient, 0.57–0.99) were good-to-excellent, including in severe COPD. CONCLUSIONS: SPIROMICS HF aims to characterize and understand cardiopulmonary interactions in COPD and COPD-related phenotypes to inform targeted treatments for combined cardiopulmonary failure.

  PublisherOA PDFDOI

Recent grants

• Aortic Plaques and Stroke: Cardiovascular Therapy of Retrograde Embolization Risk

  NIH · $425k · 2016–2019

• Non-invasive Evaluation of Intracranial Atherosclerotic Disease Using Hemodynamic Biomarkers

  NIH · $1.9M · 2020–2025

• Graduate Training Program for Magnetic Resonance Imaging

  NIH · $1.4M · 2019–2029

• Functional Cardiovascular 4D MRI in Congenital Heart Disease

  NIH · $5.2M · 2012–2024

• Comprehensive Cardiac Structure-Function Analysis in Heart Transplantation

  NIH · $6.4M · 2014–2027

Frequent coauthors

• James Carr

  Environmental Molecular Sciences Laboratory

  338 shared

• Alex J. Barker

  328 shared

• Jeremy D. Collins

  Mayo Clinic in Arizona

  205 shared

• Susanne Schnell

  166 shared

• Cynthia K. Rigsby

  Lurie Children's Hospital

  136 shared

• Joshua D. Robinson

  Lurie Children's Hospital

  123 shared

• Bradley D. Allen

  Toronto General Hospital

  109 shared

• Patrick M. McCarthy

  106 shared

Labs

• Markl LabPI