A Machine Learning-Based Approach To Identify Peripheral Artery Disease Using Texture Features From Contrast-Enhanced Magnetic Resonance Imaging

Aug 5, 2026

Upload by Aurelia

Diagnosing and assessing peripheral artery disease (PAD) and its risk remains a central clinical need. Impaired blood circulation in PAD alters microvascular perfusion patterns in calf muscles, the key region linked to intermittent claudication pain. The study hypothesizes that changes in perfusion and connective tissue produce measurable texture-pattern differences on non-invasive contrast-enhanced MRI. An automatic pipeline was built for texture feature extraction from CE-MRI and used to train machine learning models for detecting heterogeneity between PAD patients and matched controls.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages32

Reading Time1 h 21 min

AccessFree to download

Abstract

Clinical motivation: PAD and imaging texture changes

Method: automatic texture-feature extraction pipeline

Model training and classification strategy

Performance outcomes

The Texas Medical Center Library DigitalCommons@TMC | Faculty and Staff Publications | Baylor College of Medicine | | --- | --- | | 2-1-2024
A Machine Learning-Based Approach To Identify Peripheral Artery Disease Using Texture Features From Contrast-Enhanced Magnetic Resonance Imaging
Bijen Khagi
Tatiana Belousova
Christina M Short
Addison Taylor Vijay Nambi
See next page for additional authors
Follow this and additional works at: [https://digitalcommons.library.tmc.edu/baylor_docs](https://digitalcommons.library.tmc.edu/baylor_docs)
Part of the Medical Sciences Commons, and the Medical Specialties Commons | | Recommended Citation Khagi, Bijen; Belousova, Tatiana; Short, Christina M; et al., "A Machine Learning-Based Approach To Identify Peripheral Artery Disease Using Texture Features From Contrast-Enhanced Magnetic Resonance Imaging" (2024) . Faculty and Staff Publications. 4154. [https://digitalcommons.library.tmc.edu/baylor_docs/4154](https://digitalcommons.library.tmc.edu/baylor_docs/4154) This Article is brought to you for free and open access by the Baylor College of Medicine at DigitalCommons@TMC. It has been accepted for inclusion in Faculty and Staff Publications by an authorized administrator of DigitalCommons@TMC. For more information, please contact [digcommons@library.tmc.edu](digcommons@library.tmc.edu). Authors Bijen Khagi, Tatiana Belousova, Christina M Short, Addison Taylor, Vijay Nambi, Christie M Ballantyne, Jean Bismuth, Dipan J Shah, and Gerd Brunner This article is available at DigitalCommons@TMC: [https://digitalcommons.library.tmc.edu/baylor_docs/4154](https://digitalcommons.library.tmc.edu/baylor_docs/4154) Author Manuscript Author Manuscript Author Manuscript Author Manuscript | | HHS Public Access
Author manuscript
Magn Reson Imaging. Author manuscript; available in PMC 2025 February 01. | | --- | --- | Published in final edited form as: Magn Reson Imaging. 2024 February ; 106: 31–42. doi:10.1016/j.mri.2023.11.014 . A Machine Learning-Based Approach to Identify Peripheral Artery Disease Using Texture Features From Contrast-Enhanced Magnetic Resonance Imaging Bijen Khagi, PhD 1 , Tatiana Belousova, MD5 , Christina M. Short, MBA2 , Addison Taylor, MD, PhD4,2 , Vijay Nambi, MD, PhD4,2,3 , Christie M Ballantyne, MD2,3 , Jean Bismuth, MD6 , Dipan J. Shah, MD5 , Gerd Brunner, MS, PhD 1,2 1 Penn State Heart and Vascular Institute, Pennsylvania State University College of Medicine, Hershey, PA, USA 2Section of Cardiovascular Research, Baylor College of Medicine, Houston, TX, USA 3Sections of Cardiology, Department of Medicine, Baylor College of Medicine, Houston, TX, USA 4Michael E. DeBakey Veterans Affairs Medical Center, Houston, TX 5Methodist DeBakey Heart and Vascular Center, Houston Methodist Hospital, Houston, TX 6 Division of Vascular Surgery, USF Health Morsani School of Medicine, Tampa, FL Abstract Diagnosing and assessing the risk of peripheral artery disease (PAD) has long been a focal point for medical practitioners. The impaired blood circulation in PAD patients results in altered microvascular perfusion patterns in the calf muscles which is the primary location of intermittent claudication pain. Consequently, we hypothesized that changes in perfusion and increase in connective tissue could lead to alterations in the appearance or texture patterns of the skeletal calf muscles, as visualized with non-invasive imaging techniques. We designed an automatic pipeline for textural feature extraction from contrast-enhanced magnetic resonance imaging (CE-MRI) Address for correspondence: Gerd Brunner, MS, PhD, 500 University Drive H047, Hershey, PA 17033, Fax: +1 717-531-1792, [gbrunner@pennstatehealth.psu.edu](gbrunner@pennstatehealth.psu.edu). Author statement: Bijen Khagi, Conceptualization, Methodology, Data curation, Formal analysis, Validation, Software, Writing – original draft, Writing – review & editing Wr

FAQs

What clinical problem does the approach target?

It targets diagnosing and assessing peripheral artery disease (PAD) and evaluating risk using non-invasive imaging biomarkers.

How does the method connect PAD to MRI texture patterns?

It links PAD-related impaired blood flow to altered microvascular perfusion in calf muscles, which may change connective tissue and produce distinct skeletal muscle appearance/texture patterns on contrast-enhanced MRI.

What imaging data and modeling strategy are used?

The pipeline extracts texture features from contrast-enhanced MRI, then trains machine learning models to distinguish controls from PAD patients and to further identify a high-risk PAD subgroup via multi-class classification.

Aug 5, 2026

Upload by Aurelia