TY - JOUR
T1 - Automatic Classification of Magnetic Resonance Histology of Peripheral Arterial Chronic Total Occlusions Using a Variational Autoencoder
T2 - A Feasibility Study
AU - Csore, Judit
AU - Karmonik, Christof
AU - Wilhoit, Kayla
AU - Buckner, Lily
AU - Roy, Trisha L.
N1 - Funding Information:
This work was supported by the Houston Methodist Research Institute Clinician-Scholar program and the Jerold B. Katz Academy of Translational Science under project number 15790002 (recipient’s name: Trisha Roy).
Publisher Copyright:
© 2023 by the authors.
PY - 2023/5/31
Y1 - 2023/5/31
N2 - The novel approach of our study consists in adapting and in evaluating a custom-made variational autoencoder (VAE) using two-dimensional (2D) convolutional neural networks (CNNs) on magnetic resonance imaging (MRI) images for differentiate soft vs. hard plaque components in peripheral arterial disease (PAD). Five amputated lower extremities were imaged at a clinical ultra-high field 7 Tesla MRI. Ultrashort echo time (UTE), T1-weighted (T1w) and T2-weighted (T2w) datasets were acquired. Multiplanar reconstruction (MPR) images were obtained from one lesion per limb. Images were aligned to each other and pseudo-color red-green-blue images were created. Four areas in latent space were defined corresponding to the sorted images reconstructed by the VAE. Images were classified from their position in latent space and scored using tissue score (TS) as following: (1) lumen patent, TS:0; (2) partially patent, TS:1; (3) mostly occluded with soft tissue, TS:3; (4) mostly occluded with hard tissue, TS:5. Average and relative percentage of TS was calculated per lesion defined as the sum of the tissue score for each image divided by the total number of images. In total, 2390 MPR reconstructed images were included in the analysis. Relative percentage of average tissue score varied from only patent (lesion #1) to presence of all four classes. Lesions #2, #3 and #5 were classified to contain tissues except mostly occluded with hard tissue while lesion #4 contained all (ranges (I): 0.2–100%, (II): 46.3–75.9%, (III): 18–33.5%, (IV): 20%). Training the VAE was successful as images with soft/hard tissues in PAD lesions were satisfactory separated in latent space. Using VAE may assist in rapid classification of MRI histology images acquired in a clinical setup for facilitating endovascular procedures.
AB - The novel approach of our study consists in adapting and in evaluating a custom-made variational autoencoder (VAE) using two-dimensional (2D) convolutional neural networks (CNNs) on magnetic resonance imaging (MRI) images for differentiate soft vs. hard plaque components in peripheral arterial disease (PAD). Five amputated lower extremities were imaged at a clinical ultra-high field 7 Tesla MRI. Ultrashort echo time (UTE), T1-weighted (T1w) and T2-weighted (T2w) datasets were acquired. Multiplanar reconstruction (MPR) images were obtained from one lesion per limb. Images were aligned to each other and pseudo-color red-green-blue images were created. Four areas in latent space were defined corresponding to the sorted images reconstructed by the VAE. Images were classified from their position in latent space and scored using tissue score (TS) as following: (1) lumen patent, TS:0; (2) partially patent, TS:1; (3) mostly occluded with soft tissue, TS:3; (4) mostly occluded with hard tissue, TS:5. Average and relative percentage of TS was calculated per lesion defined as the sum of the tissue score for each image divided by the total number of images. In total, 2390 MPR reconstructed images were included in the analysis. Relative percentage of average tissue score varied from only patent (lesion #1) to presence of all four classes. Lesions #2, #3 and #5 were classified to contain tissues except mostly occluded with hard tissue while lesion #4 contained all (ranges (I): 0.2–100%, (II): 46.3–75.9%, (III): 18–33.5%, (IV): 20%). Training the VAE was successful as images with soft/hard tissues in PAD lesions were satisfactory separated in latent space. Using VAE may assist in rapid classification of MRI histology images acquired in a clinical setup for facilitating endovascular procedures.
KW - angiography
KW - angioplasty
KW - chronic limb-threatening ischemia
KW - chronic total occlusion
KW - endovascular treatment
KW - non-invasive diagnostics
KW - peripheral arterial disease
KW - ultra-high field magnetic resonance imaging
UR - http://www.scopus.com/inward/record.url?scp=85161794062&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85161794062&partnerID=8YFLogxK
U2 - 10.3390/diagnostics13111925
DO - 10.3390/diagnostics13111925
M3 - Article
C2 - 37296778
AN - SCOPUS:85161794062
SN - 2075-4418
VL - 13
JO - Diagnostics
JF - Diagnostics
IS - 11
M1 - 1925
ER -