Cartilage Topography Assessment with Local Area Cartilage Segmentation (LACS) for Knee MRI.

OBJECTIVE Local-Area Cartilage Segmentation (LACS) software was developed to segment medial femur (MF) cartilage on MRI. Our current objectives were to 1) extend LACS to the lateral femur (LF), medial tibia (MT), and lateral tibia (LT), 2) compare LACS to an established manual segmentation method, and 3) visualize cartilage responsiveness over each cartilage plate. DESIGN Osteoarthritis Initiative participants with symptomatic knee OA were selected, including knees selected at random (n=40) and knees identified with loss of cartilage based on manual segmentation (Chondrometrics), an enriched sample of 126 knees. LACS was used to segment cartilage in the MF, LF, MT and LT on sagittal 3D DESS MRI scans at baseline and two-year follow-up. We compared LACS and Chondrometrics average thickness measures by estimating the correlation in each cartilage plate and estimating standardized response mean (SRM) for two-year cartilage change. We illustrated cartilage loss topographically with SRM heat-maps. RESULTS Estimated correlation between LACS and Chondrometrics measures was r=0.91 (95%CI: 0.86, 0.94) for LF; r=0.93 (95%CI: 0.89, 0.95) for MF; r=0.97 (95%CI: 0.96, 0.98) for LT, and r=0.87 (95%CI: 0.81, 0.91) for MT. Estimated SRMs for LACS and Chondrometrics measures were similar in the random sample, and SRM heat-maps identified sub-regions of LACS-measured cartilage loss. CONCLUSIONS LACS cartilage thickness measurement in the medial and lateral femur and tibia correlated well with established manual segmentation-based measurement, with similar responsiveness to change, among knees with symptomatic knee OA. LACS measurement of cartilage plate topography enables spatio-temporal analysis of cartilage loss in future knee OA studies.