TY - JOUR
T1 - Radiomics-Based Image Phenotyping of Kidney Apparent Diffusion Coefficient Maps
T2 - Preliminary Feasibility & Efficacy
AU - Li, Lu Ping
AU - Leidner, Alexander S.
AU - Wilt, Emily
AU - Mikheev, Artem
AU - Rusinek, Henry
AU - Sprague, Stuart M.
AU - Kohn, Orly F.
AU - Srivastava, Anand
AU - Prasad, Pottumarthi V.
N1 - Funding Information:
Funding: This work is supported in part by grants R01DK093793 and R21DK127302 from NIDDK (PVP), U24 EB028980 from NIBIB (HR), and K23DK120811 from NIDDK (AS), and ASL was supported by Ruth L. Kirschstein National Research Service Award T32 DK007169 from NIDDK. ASL and AS are also supported by core resources from the George M. O’Brien Kidney Research Center at Northwestern University (NU-GoKIDNEY) P30DK114857. LPL, AS, and PVP are also supported by the Kidney Precision Medicine Project Opportunity Pool grant under award U2CDK114886.
Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2022/4/1
Y1 - 2022/4/1
N2 - Given the central role of interstitial fibrosis in disease progression in chronic kidney disease (CKD), a role for diffusion-weighted MRI has been pursued. We evaluated the feasibility and preliminary efficacy of using radiomic features to phenotype apparent diffusion coefficient (ADC) maps and hence to the clinical classification(s) of the participants. The study involved 40 individuals (10 healthy and 30 with CKD (eGFR < 60 mL/min/1.73 m2)). Machine learning methods, such as hierarchical clustering and logistic regression, were used. Clustering resulted in the identification of two clusters, one including all individuals with CKD (n = 17), while the second one included all the healthy volunteers (n = 10) and the remaining individuals with CKD (n = 13), resulting in 100% specificity. Logistic regression identified five radiomic features to classify participants as with CKD vs. healthy volunteers, with a sensitivity and specificity of 93% and 70%, respectively, and an AUC of 0.95. Similarly, four radiomic features were able to classify participants as rapid vs. non-rapid CKD progressors among the 30 individuals with CKD, with a sensitivity and specificity of 71% and 43%, respectively, and an AUC of 0.75. These promising preliminary data should support future studies with larger numbers of participants with varied disease severity and etiologies to improve performance.
AB - Given the central role of interstitial fibrosis in disease progression in chronic kidney disease (CKD), a role for diffusion-weighted MRI has been pursued. We evaluated the feasibility and preliminary efficacy of using radiomic features to phenotype apparent diffusion coefficient (ADC) maps and hence to the clinical classification(s) of the participants. The study involved 40 individuals (10 healthy and 30 with CKD (eGFR < 60 mL/min/1.73 m2)). Machine learning methods, such as hierarchical clustering and logistic regression, were used. Clustering resulted in the identification of two clusters, one including all individuals with CKD (n = 17), while the second one included all the healthy volunteers (n = 10) and the remaining individuals with CKD (n = 13), resulting in 100% specificity. Logistic regression identified five radiomic features to classify participants as with CKD vs. healthy volunteers, with a sensitivity and specificity of 93% and 70%, respectively, and an AUC of 0.95. Similarly, four radiomic features were able to classify participants as rapid vs. non-rapid CKD progressors among the 30 individuals with CKD, with a sensitivity and specificity of 71% and 43%, respectively, and an AUC of 0.75. These promising preliminary data should support future studies with larger numbers of participants with varied disease severity and etiologies to improve performance.
KW - ADC
KW - CKD
KW - MRI
KW - diffusion-weighted imaging
KW - kidney
KW - radiomic
UR - http://www.scopus.com/inward/record.url?scp=85127429675&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127429675&partnerID=8YFLogxK
U2 - 10.3390/jcm11071972
DO - 10.3390/jcm11071972
M3 - Article
C2 - 35407587
AN - SCOPUS:85127429675
SN - 2077-0383
VL - 11
JO - Journal of Clinical Medicine
JF - Journal of Clinical Medicine
IS - 7
M1 - 1972
ER -