Medical College of Wisconsin
CTSICores SearchResearch InformaticsREDCap

MRI-based radiomic analysis of soft tissue reactions near total hip arthroplasty. J Orthop Res 2025 Jan;43(1):183-191

Date

09/13/2024

Pubmed ID

39269140

DOI

10.1002/jor.25970

Scopus ID

2-s2.0-85204026806 (requires institutional sign-in at Scopus site)

Abstract

This study applied radiomics to MRI data for automated classification of soft tissue abnormalities near total hip arthroplasty (THA). A total of 126 subjects with 1.5 T MRI of symptomatic THA were included in the analysis. Peri-prosthetic soft tissue regions of interest were manually segmented and classified by an expert radiologist. An established radiomics library was used to extract 96 features from 2D image patches across segmented regions. Logistic regression was employed as the primary radiomic classifier, achieving an average area under curve (AUC) of 0.71 in differentiating tissue classifications spanning normal, infected, and several inflammatory, noninfectious categories. Notably, infection cases were identified with the highest accuracy, attaining an AUC of 0.79. Statement of Clinical Significance: This study demonstrates that radiomics applied to MRI data can effectively automate the classification of soft tissue abnormalities in symptomatic total hip arthroplasty, particularly in differentiating periprosthetic infections.

Author List

Koch KM, Potter HG, Koff MF

Author

Kevin M. Koch PhD Center Director, Professor in the Radiology department at Medical College of Wisconsin




MESH terms used to index this publication - Major topics in bold

Adult
Aged
Aged, 80 and over
Arthroplasty, Replacement, Hip
Female
Humans
Magnetic Resonance Imaging
Male
Middle Aged
Prosthesis-Related Infections