Prediction model for knee osteoarthritis using magnetic resonance-based radiomic features from the infrapatellar fat pad: data from the osteoarthritis initiative

Abstract

Background: The infrapatellar fat pad (IPFP) plays an important role in the incidence of knee osteoarthritis (OA). Magnetic resonance (MR) signal heterogeneity of the IPFP is related to pathologic changes. In this study, we aimed to investigate whether the IPFP radiomic features have predictive value for incident radiographic knee OA (iROA) 1 year prior to iROA diagnosis.

Methods: Data used in this work were obtained from the osteoarthritis initiative (OAI). In this study, iROA was defined as a knee with a baseline Kellgren-Lawrence grade (KLG) of 0 or 1 that further progressed to KLG ≥2 during the follow-up visit. Intermediate-weighted turbo spin-echo knee MR images at the time of iROA diagnosis and 1 year prior were obtained. Five clinical characteristics-age, sex, body mass index, knee injury history, and knee surgery history-were obtained. A total of 604 knees were selected and matched (302 cases and 302 controls). A U-Net segmentation model was independently trained to automatically segment the IPFP. The prediction models were established in the training set (60%). Three main models were generated using (I) clinical characteristics; (II) radiomic features; (III) combined (clinical plus radiomic) features. Model performance was evaluated in an independent testing set (remaining 40%) using the area under the curve (AUC). Two secondary models were also generated using Hoffa-synovitis scores and clinical characteristics.

Results: The comparison between the automated and manual segmentations of the IPFP achieved a Dice coefficient of 0.900 (95% CI: 0.891-0.908), which was comparable to that of experienced radiologists. The radiomic features model and the combined model yielded superior AUCs of 0.700 (95% CI: 0.630-0.763) and 0.702 (95% CI: 0.635-0.763), respectively. The DeLong test found no statistically significant difference between the receiver operating curves of the radiomic and combined models (P=0.831); however, both models outperformed the clinical model (P=0.014 and 0.004, respectively).

Conclusions: Our results demonstrated that radiomic features of the IPFP are predictive of iROA 1 year prior to the diagnosis, suggesting that IPFP radiomic features can serve as an early quantitative prediction biomarker of iROA.

Keywords: Osteoarthritis (OA); infrapatellar fat pad (IPFP); prediction model; radiomics.

Figure 1

IPFP MR images obtained on sagittal intermediate-weighted turbo spin-echo from the iROA dataset. The red line delineates the IPFP for each case. The Hoffa-synovitis score was determined to be 0 = normal/no hyperintensity, 1= mild, 2= moderate, and 3= severe for (A) to (D), respectively. IPFP, infrapatellar fat pad; MR, magnetic resonance; iROA, incident radiographic knee osteoarthritis.

Figure 2

A flowchart showing participant inclusion and exclusion. OAI, Osteoarthritis Initiative; KLG, Kellgren-Lawrence grade; OA, osteoarthritis; w/o, without; MR, magnetic resonance.

Figure 3

Architecture of 2.5D U-Net for IPFP segmentation. IPFP, infrapatellar fat pad; MR, magnetic resonance.

Figure 4

The prediction model development flowchart. Three models were generated to predict iROA diagnosis (P0) using features collected 1 year before the diagnosis (P-1). The following features were included in the models: (I) clinical characteristics, (II) radiomic features, and (III) clinical plus radiomic features. iROA, incident radiographic knee osteoarthritis. IPFP, infrapatellar fat pad; iROA, incident radiographic knee osteoarthritis.

Figure 5

Comparison of manual and automated IPFP segmentations of the same knee. The red line delineates (A) manual segmentation by radiologist 1, (B) manual segmentation by radiologist 2, (C) manual segmentation by radiologist 3, and (D) 2.5D U-Net model. IPFP, infrapatellar fat pad.

Figure 6

2.5D U-Net model generated IPFP segmentations of 4 representative participants. The red line indicates the segmentation results. IPFP, infrapatellar fat pad.

Figure 7

ROC curves of the training and testing sets for the 3 different models. The red points on the ROC curves of the training set are the optimal cutoff points (threshold) determined by maximizing the Youden index using the training set. ROC, receiver operating characteristic; AUC, area under the curve.

Figure 8

t-SNE visualization for the training and testing sets of all 3 models. t-SNE, t-distributed stochastic neighbor embedding; iROA, incident radiographic knee osteoarthritis.

Figure 9

GLCM texture maps of representative participants. The top and bottom are from a case and a control, respectively. GLCM, gray-level cooccurrence-matrix.