High-resolution and accelerated multi-parametric mapping with automated characterization of vessel disease using intravascular MRI

Guan Wang, Yi Zhang, Shashank Sathyanarayana Hegde, Paul A Bottomley

Research output: Contribution to journalArticle

Abstract

Background: Atherosclerosis is prevalent in cardiovascular disease, but present imaging modalities have limited capabilities for characterizing lesion stage, progression and response to intervention. This study tests whether intravascular magnetic resonance imaging (IVMRI) measures of relaxation times (T1, T2) and proton density (PD) in a clinical 3 Tesla scanner could characterize vessel disease, and evaluates a practical strategy for accelerated quantification. Methods: IVMRI was performed in fresh human artery segments and swine vessels in vivo, using fast multi-parametric sequences, 1-2 mm diameter loopless antennae and 200-300 μm resolution. T1, T2 and PD data were used to train a machine learning classifier (support vector machine, SVM) to automatically classify normal vessel, and early or advanced disease, using histology for validation. Disease identification using the SVM was tested with receiver operating characteristic curves. To expedite acquisition of T1, T2 and PD data for vessel characterization, the linear algebraic method ('SLAM') was modified to accommodate the antenna's highly-nonuniform sensitivity, and used to provide average T1, T2 and PD measurements from compartments of normal and pathological tissue segmented from high-resolution images at acceleration factors of R ≤ 18-fold. The results were validated using compartment-average measures derived from the high-resolution scans. Results: The SVM accurately classified ~80% of samples into the three disease classes. The 'area-under-the-curve' was 0.96 for detecting disease in 248 samples, with T1 providing the best discrimination. SLAM T1, T2 and PD measures for R ≤ 10 were indistinguishable from the true means of segmented tissue compartments. Conclusion: High-resolution IVMRI measures of T1, T2 and PD with a trained SVM can automatically classify normal, early and advanced atherosclerosis with high sensitivity and specificity. Replacing relaxometric MRI with SLAM yields good estimates of T1, T2 and PD an order-of-magnitude faster to facilitate IVMRI-based characterization of vessel disease.

Original languageEnglish (US)
Article number89
JournalJournal of Cardiovascular Magnetic Resonance
Volume19
Issue number1
DOIs
StatePublished - Nov 20 2017

Fingerprint

Protons
Magnetic Resonance Imaging
R388
Atherosclerosis
ROC Curve
Area Under Curve
Histology
Cardiovascular Diseases
Swine
Arteries
Sensitivity and Specificity
Support Vector Machine

Keywords

  • Accelerated acquisition
  • Atherosclerosis
  • Disease classification
  • Intravascular MRI
  • Machine learning
  • Relaxation times
  • SLAM

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine
  • Family Practice

Cite this

High-resolution and accelerated multi-parametric mapping with automated characterization of vessel disease using intravascular MRI. / Wang, Guan; Zhang, Yi; Hegde, Shashank Sathyanarayana; Bottomley, Paul A.

In: Journal of Cardiovascular Magnetic Resonance, Vol. 19, No. 1, 89, 20.11.2017.

Research output: Contribution to journalArticle

@article{5dea9e87449c46a59a623a8ce677031b,
title = "High-resolution and accelerated multi-parametric mapping with automated characterization of vessel disease using intravascular MRI",
abstract = "Background: Atherosclerosis is prevalent in cardiovascular disease, but present imaging modalities have limited capabilities for characterizing lesion stage, progression and response to intervention. This study tests whether intravascular magnetic resonance imaging (IVMRI) measures of relaxation times (T1, T2) and proton density (PD) in a clinical 3 Tesla scanner could characterize vessel disease, and evaluates a practical strategy for accelerated quantification. Methods: IVMRI was performed in fresh human artery segments and swine vessels in vivo, using fast multi-parametric sequences, 1-2 mm diameter loopless antennae and 200-300 μm resolution. T1, T2 and PD data were used to train a machine learning classifier (support vector machine, SVM) to automatically classify normal vessel, and early or advanced disease, using histology for validation. Disease identification using the SVM was tested with receiver operating characteristic curves. To expedite acquisition of T1, T2 and PD data for vessel characterization, the linear algebraic method ('SLAM') was modified to accommodate the antenna's highly-nonuniform sensitivity, and used to provide average T1, T2 and PD measurements from compartments of normal and pathological tissue segmented from high-resolution images at acceleration factors of R ≤ 18-fold. The results were validated using compartment-average measures derived from the high-resolution scans. Results: The SVM accurately classified ~80{\%} of samples into the three disease classes. The 'area-under-the-curve' was 0.96 for detecting disease in 248 samples, with T1 providing the best discrimination. SLAM T1, T2 and PD measures for R ≤ 10 were indistinguishable from the true means of segmented tissue compartments. Conclusion: High-resolution IVMRI measures of T1, T2 and PD with a trained SVM can automatically classify normal, early and advanced atherosclerosis with high sensitivity and specificity. Replacing relaxometric MRI with SLAM yields good estimates of T1, T2 and PD an order-of-magnitude faster to facilitate IVMRI-based characterization of vessel disease.",
keywords = "Accelerated acquisition, Atherosclerosis, Disease classification, Intravascular MRI, Machine learning, Relaxation times, SLAM",
author = "Guan Wang and Yi Zhang and Hegde, {Shashank Sathyanarayana} and Bottomley, {Paul A}",
year = "2017",
month = "11",
day = "20",
doi = "10.1186/s12968-017-0399-6",
language = "English (US)",
volume = "19",
journal = "Journal of Cardiovascular Magnetic Resonance",
issn = "1097-6647",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - High-resolution and accelerated multi-parametric mapping with automated characterization of vessel disease using intravascular MRI

AU - Wang, Guan

AU - Zhang, Yi

AU - Hegde, Shashank Sathyanarayana

AU - Bottomley, Paul A

PY - 2017/11/20

Y1 - 2017/11/20

N2 - Background: Atherosclerosis is prevalent in cardiovascular disease, but present imaging modalities have limited capabilities for characterizing lesion stage, progression and response to intervention. This study tests whether intravascular magnetic resonance imaging (IVMRI) measures of relaxation times (T1, T2) and proton density (PD) in a clinical 3 Tesla scanner could characterize vessel disease, and evaluates a practical strategy for accelerated quantification. Methods: IVMRI was performed in fresh human artery segments and swine vessels in vivo, using fast multi-parametric sequences, 1-2 mm diameter loopless antennae and 200-300 μm resolution. T1, T2 and PD data were used to train a machine learning classifier (support vector machine, SVM) to automatically classify normal vessel, and early or advanced disease, using histology for validation. Disease identification using the SVM was tested with receiver operating characteristic curves. To expedite acquisition of T1, T2 and PD data for vessel characterization, the linear algebraic method ('SLAM') was modified to accommodate the antenna's highly-nonuniform sensitivity, and used to provide average T1, T2 and PD measurements from compartments of normal and pathological tissue segmented from high-resolution images at acceleration factors of R ≤ 18-fold. The results were validated using compartment-average measures derived from the high-resolution scans. Results: The SVM accurately classified ~80% of samples into the three disease classes. The 'area-under-the-curve' was 0.96 for detecting disease in 248 samples, with T1 providing the best discrimination. SLAM T1, T2 and PD measures for R ≤ 10 were indistinguishable from the true means of segmented tissue compartments. Conclusion: High-resolution IVMRI measures of T1, T2 and PD with a trained SVM can automatically classify normal, early and advanced atherosclerosis with high sensitivity and specificity. Replacing relaxometric MRI with SLAM yields good estimates of T1, T2 and PD an order-of-magnitude faster to facilitate IVMRI-based characterization of vessel disease.

AB - Background: Atherosclerosis is prevalent in cardiovascular disease, but present imaging modalities have limited capabilities for characterizing lesion stage, progression and response to intervention. This study tests whether intravascular magnetic resonance imaging (IVMRI) measures of relaxation times (T1, T2) and proton density (PD) in a clinical 3 Tesla scanner could characterize vessel disease, and evaluates a practical strategy for accelerated quantification. Methods: IVMRI was performed in fresh human artery segments and swine vessels in vivo, using fast multi-parametric sequences, 1-2 mm diameter loopless antennae and 200-300 μm resolution. T1, T2 and PD data were used to train a machine learning classifier (support vector machine, SVM) to automatically classify normal vessel, and early or advanced disease, using histology for validation. Disease identification using the SVM was tested with receiver operating characteristic curves. To expedite acquisition of T1, T2 and PD data for vessel characterization, the linear algebraic method ('SLAM') was modified to accommodate the antenna's highly-nonuniform sensitivity, and used to provide average T1, T2 and PD measurements from compartments of normal and pathological tissue segmented from high-resolution images at acceleration factors of R ≤ 18-fold. The results were validated using compartment-average measures derived from the high-resolution scans. Results: The SVM accurately classified ~80% of samples into the three disease classes. The 'area-under-the-curve' was 0.96 for detecting disease in 248 samples, with T1 providing the best discrimination. SLAM T1, T2 and PD measures for R ≤ 10 were indistinguishable from the true means of segmented tissue compartments. Conclusion: High-resolution IVMRI measures of T1, T2 and PD with a trained SVM can automatically classify normal, early and advanced atherosclerosis with high sensitivity and specificity. Replacing relaxometric MRI with SLAM yields good estimates of T1, T2 and PD an order-of-magnitude faster to facilitate IVMRI-based characterization of vessel disease.

KW - Accelerated acquisition

KW - Atherosclerosis

KW - Disease classification

KW - Intravascular MRI

KW - Machine learning

KW - Relaxation times

KW - SLAM

UR - http://www.scopus.com/inward/record.url?scp=85034629669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034629669&partnerID=8YFLogxK

U2 - 10.1186/s12968-017-0399-6

DO - 10.1186/s12968-017-0399-6

M3 - Article

C2 - 29157260

AN - SCOPUS:85034629669

VL - 19

JO - Journal of Cardiovascular Magnetic Resonance

JF - Journal of Cardiovascular Magnetic Resonance

SN - 1097-6647

IS - 1

M1 - 89

ER -