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 language | English (US) |
|---|---|
| Article number | 89 |
| Journal | Journal of Cardiovascular Magnetic Resonance |
| Volume | 19 |
| Issue number | 1 |
| DOIs | |
| State | Published - Nov 20 2017 |
Fingerprint
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 journal › Article
}
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 -