Objectives

To study the natural history of new horizontal meniscal tears and their association with progression of cartilage degeneration in individuals at risk for or with mild to moderate knee osteoarthritis over 4 years.

Methods

Individuals who developed a new meniscal tear in the right knee over 2 years were selected from the Osteoarthritis Initiative 3T MRI studies. Knee structural changes were analyzed at the time of tear appearance (baseline), and after 4 years using a modified Whole-Organ Magnetic Resonance Imaging Score (WORMS). Meniscal tears were classified as either horizontal tears or non-horizontal tears. Individuals without a meniscal tear were 1:3 frequency matched according to BMI, gender, race, and age and served as the control group. Linear regression analysis was used to compare cross-sectional and longitudinal changes in cartilage WORMS scores.

Results

Forty-one subjects developed horizontal tears, including one indiviudal who developed a tear in both menisci, and 34 developed non-horizonal tears. We found that (29/41 (70.7%)) of horizontal and (20/34 (58.8%)) of non-horizonatal tears were stable during follow-up (p = 0.281). Although knees with an incident tear had higher than controls WORMS MAX total knee scores at baseline (coef. = 0.47, p = 0.044, 95% CI = 0.01 to 0.93), there were no significant differences between the horizontal subgroup and knees without tears in overall cartilage scores at baseline and in progression over 4 years of follow-up.

Conclusions

New horizontal meniscal tears tended to be stable over 4 years and presented no significant differences in progression of cartilage degeneration when compared with knees without tears.

Key points

• Most of horizonal meniscal tears were stable over 4 years. • There were no statistically significant differences in overall progression of cartilage degenerative changes between knees with horizonal meniscal tears and control knees without tears • Horizontal tears most often occurred at the posterior horn of the medial meniscus and at the body of the lateral meniscus.

Background A multitask deep learning model might be useful in large epidemiologic studies wherein detailed structural assessment of osteoarthritis still relies on expert radiologists' readings. The potential of such a model in clinical routine should be investigated. Purpose To develop a multitask deep learning model for grading radiographic hip osteoarthritis features on radiographs and compare its performance to that of attending-level radiologists. Materials and Methods This retrospective study analyzed hip joints seen on weight-bearing anterior-posterior pelvic radiographs from participants in the Osteoarthritis Initiative (OAI). Participants were recruited from February 2004 to May 2006 for baseline measurements, and follow-up was performed 48 months later. Femoral osteophytes (FOs), acetabular osteophytes (AOs), and joint-space narrowing (JSN) were graded as absent, mild, moderate, or severe according to the Osteoarthritis Research Society International atlas. Subchondral sclerosis and subchondral cysts were graded as present or absent. The participants were split at 80% (n = 3494), 10% (n = 437), and 10% (n = 437) by using split-sample validation into training, validation, and testing sets, respectively. The multitask neural network was based on DenseNet-161, a shared convolutional features extractor trained with multitask loss function. Model performance was evaluated in the internal test set from the OAI and in an external test set by using temporal and geographic validation consisting of routine clinical radiographs. Results A total of 4368 participants (mean age, 61.0 years ± 9.2 [standard deviation]; 2538 women) were evaluated (15 364 hip joints on 7738 weight-bearing anterior-posterior pelvic radiographs). The accuracy of the model for assessing these five features was 86.7% (1333 of 1538) for FOs, 69.9% (1075 of 1538) for AOs, 81.7% (1257 of 1538) for JSN, 95.8% (1473 of 1538) for subchondral sclerosis, and 97.6% (1501 of 1538) for subchondral cysts in the internal test set, and 82.7% (86 of 104) for FOS, 65.4% (68 of 104) for AOs, 80.8% (84 of 104) for JSN, 88.5% (92 of 104) for subchondral sclerosis, and 91.3% (95 of 104) for subchondral cysts in the external test set. Conclusion A multitask deep learning model is a feasible approach to reliably assess radiographic features of hip osteoarthritis. © RSNA, 2020 Online supplemental material is available for this article.