TRANSLATION OF X-RAY TO MRI: DIAGNOSTIC PERFORMANCE OF MRI-DEFINED SIMULATED KELLGREN-LAWRENCE GRADING

Abstract

INTRODUCTION

While it has been acknowledged that mild-to-moderate radiographic disease severity of knee osteoarthritis (OA), i.e. knees with grades 2 and 3 on the Kellgren-Lawrence (KL) scale – reflect a wide spectrum of tissue damage, it is unknown whether a knee MRI can easily be translated into a specific radiographic (r) KL grade (KLG). In order to potentially use MRI as a single screening tool for eligibility in clinical trials, it is necessary to define which knees correspond to the current inclusion criteria of rKLG 2 and 3.

OBJECTIVE

The aim of this study was to assess the diagnostic performance of a priori-determined definitions of MRI-assessed KLG based on osteophytes (OPs) and cartilage damage in the tibiofemoral joint (TFJ).

METHODS

We included MRI readings from the following Osteoarthritis Initiative substudies: FNIH Biomarker consortium, POMA and BEAK. Included are visits with centrally read rKLG and available MOAKS readings. In order to match the anteroposterior (a.p.) radiograph, four locations for OPs assessed in the coronal plane (central medial femur, central medial tibia, central lateral femur, central lateral tibia) were considered. Eight subregions were considered for cartilage damage to mirror the weight bearing tibiofemoral joints on X-ray: anterior medial tibia, central medial tibia, posterior medial tibia, central medial femur, anterior lateral tibia, central lateral tibia, posterior lateral tibia and central lateral femur. Cartilage damage was classified as minor: focal damage only (MOAKS 0, 1.0, 1.1); moderate: damage with no advanced full thickness wide-spread damage (MOAKS 2.0, 2.1, 3.0, 3.1); and severe: full thickness wide-spread damage (MOAKS 2.2, 3.2, 3.3).

The definitions were derived based on expert consensus opinion as follows:

MRI KL0: no OP (=grade 0 in all 4 locations), minor cartilage damage only

MRI KL1: grade 1 OP in at least 1 of 4 TFJ locations, maximum OP grade 1, minor cartilage damage only

MRI KL2: grade 1, 2 or 3 OP in at least 1 of 4 TFJ locations, moderate cartilage damage

MRI KL2a (“atrophic”): no OP (=grades 0 in all 4 TFJ locations), moderate cartilage damage

MRI KL 3: grade 1, 2 or 3 OP in at least 1 of 4 TFJ locations, severe cartilage damage in at least 1 of 8 subregions.

MRI KL3a (“atrophic”): no OP (=grades 0 in all 4 TFJ locations), severe cartilage damage in at least 1 of 8 subregions

MRI KL 4: grade 1, 2 or 3 OP in at least 1 of 4 TFJ locations, severe cartilage damage in at least 2 of 4 corresponding subregions medially or laterally or both.

Sensitivity, specificity, negative and positive predictive values were determined using radiographic KLG as the reference.

RESULTS

In total, the dataset includes 4924 visits from 1981 participants contributing 2276 knees for up to 4 timepoints. The rKL distribution for the sample is KL 0 n=1463 (29.7%), KL1 n=1457 (29.6%), KL2 n= 1282 (26.0%), KL3 n= 703 (14.3%) and KL4 n=19 (0.4%). Sensitivities of the different MRI KLG to diagnose the corresponding rOA KLG ranged between 14.3% (MRI KL1) to 66.5% (MRI KL0), specificities ranged from 79.3% (MRI KL0) to 96.7% (MRI KL4), NPV ranged from 71.2% (MRI KL1) to 99.8 % (MRI KL4) and PPV from 6.4% (MRI KL4) 57.6% (MRI KL0). Details are shown in Table 1. Numbers were comparable when excluding knees with an “atrophic” manifestation of KL2 or 3. Figure 1 illustrates the percentages of each MRI KLG within the different rKLGs

CONCLUSION

MRI-defined KLG shows moderate performance when used as a diagnostic instrument to simulate radiographic KLG. Reasons are multifold but mainly include the wide range of cartilage damage and OP severity within each rKLG. This was particularly relevant for simulating rKL1. Given MRI is the more sensitive tool to diagnose OPs and cartilage damage cannot be evaluated by X-ray directly, likely X-ray scoring based on KL grading does not adequately reflect OP or cartilage status and should be omitted from eligibility screening in clinical trials of knee OA.