PurposeTo evaluate preoperative soft tissue balance for total knee arthroplasty (TKA), varus/valgus stress radiographs has been used in previous studies. While the joint line of femur and tibia is almost parallel in healthy and postoperative knees, osteoarthritis (OA) knees exhibit articular cartilage wear that causes the joint line tilting even in a non‐stress condition. Therefore, the exact angle of the joint line might mislead to understand the joint laxity in OA knees. The purpose of this study was to evaluate soft tissue balance in varus OA knees using preoperative stress radiographs under three different constant loads, taking the articular cartilage wear into consideration. MethodsOne hundred and eighteen varus‐deformed OA knees in 102 patients were investigated before primary TKA. Preoperative knee radiographs were obtained in the anteroposterior view with no stress (defined as the neutral condition) and with varus and valgus stresses (5, 10, and 15 kg) in extension. Two different types of joint line angle (JLA), the absolute JLA (an exact angle of joint line) and the relative JLA (the absolute JLA minus the JLA in the neutral condition), were compared for the same load with the paired t test. ResultsThe absolute JLA was 7.9 ± 1.2°/− 1.5 ± 2.2° under varus/valgus 15 kg stress, 6.7 ± 2.4°/− 0.3 ± 2.1° under varus/valgus 10 kg stress, and 4.7 ± 2.4°/1.1 ± 2.2° under varus/valgus 5 kg stress. Significant differences in the numerical values of the absolute JLA were observed between varus and valgus stresses for each load. The neutral JLA was 3.2 ± 2.0°. The relative JLA was 4.8 ± 2.1°/− 4.7 ± 1.8° under varus/valgus 15 kg stress, 3.5 ± 2.0°/− 3.5 ± 1.8° under varus/valgus 10 kg stress, and 1.5 ± 1.9°/− 2.1 ± 1.8° under varus/valgus 5 kg stress. No significant differences in the numerical values of the relative JLA were observed between varus and valgus stresses for each load. ConclusionsConsideration of cartilage wear allowed knee laxity to be evaluated more precisely in this study than in previous reports. It was shown that medial soft tissue contracture did not always exist, even in varus OA knees. Regarding clinical relevance, surgeons should be aware that underestimating medial soft tissue laxity due to reliance on the absolute JLA might lead to excessive medial tissue release and result in postoperative instability and lower patient satisfaction. Level of evidenceIV.
Background X-ray images are commonly used to assess the bone destruction of rheumatoid arthritis. The purpose of this study is to propose an automatic-bone-destruction-evaluation system fully utilizing deep neural networks (DNN). This system detects all target joints of the modified Sharp/van der Heijde score (SHS) from a hand X-ray image. It then classifies every target joint as intact (SHS = 0) or non-intact (SHS ≥ 1). Methods We used 226 hand X-ray images of 40 rheumatoid arthritis patients. As for detection, we used a DNN model called DeepLabCut. As for classification, we built four classification models that classify the detected joint as intact or non-intact. The first model classifies each joint independently, whereas the second model does it while comparing the same contralateral joint. The third model compares the same joint group (e.g., the proximal interphalangeal joints) of one hand and the fourth model compares the same joint group of both hands. We evaluated DeepLabCut’s detection performance and classification models’ performances. The classification models’ performances were compared to three orthopedic surgeons. Results Detection rates for all the target joints were 98.0% and 97.3% for erosion and joint space narrowing (JSN). Among the four classification models, the model that compares the same contralateral joint showed the best F-measure (0.70, 0.81) and area under the curve of the precision-recall curve (PR-AUC) (0.73, 0.85) regarding erosion and JSN. As for erosion, the F-measure and PR-AUC of this model were better than the best of the orthopedic surgeons. Conclusions The proposed system was useful. All the target joints were detected with high accuracy. The classification model that compared the same contralateral joint showed better performance than the orthopedic surgeons regarding erosion.
Background: X-ray images are commonly used for assessing presence of bone destruction of rheumatoid arthritis. The purpose of this study is to propose an automatic-bone-destruction-evaluation system fully utilizing deep neural networks (DNN). This system detects all target joints of the modified Sharp/van der Heijde score (SHS) from a hand X-ray image. It then classifies every target joint as intact (SHS = 0) or non-intact (SHS ≥ 1).Methods: We used 226 hand X-ray images of 40 rheumatoid arthritis patients. As for detection, we used a DNN model called DeepLabCut. As for classification, we built four classification models that classify the detected joint as intact or non-intact. First, each joint is independently classified; second, the same contralateral joint is compared; third, the same joint group (e.g., the proximal interphalangeal joints) of one hand are compared; fourth, the same joint group of both hands are compared. We evaluated DeepLabCut’s detection performance and classification models’ performances. The classification models’ performances were compared to three orthopedic surgeons.Results: Detection rates for all the target joints were 98.0% and 97.3% for erosion and joint space narrowing (JSN). Among the four classification models, the model that compares the same contralateral joint showed the best F-measure (0.70, 0.81) and area under the curve of the precision-recall curve (PR-AUC) (0.73, 0.85) regarding erosion and JSN. As for erosion, the F-measure and PR-AUC of this model were better than the best of the orthopedic surgeons.Conclusions: The proposed system was useful. All the target joints were detected with high accuracy. The classification model that compared the same contralateral joint showed better performance than the orthopedic surgeons regarding erosion.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.