METHODS: Knee image is first oversegmented to produce homogeneous superpixels. Then, a ranking model is developed to rank the superpixels according to their affinities to standard priors, wherein background superpixels would have lower ranking values. Finally, seed labels are generated on the background superpixel using Fuzzy C-Means method.
RESULTS: SAGE has achieved better interobserver DSCs of 0.94 ± 0.029 and 0.93 ± 0.035 in healthy and OA knee segmentation, respectively. Good segmentation performance has been reported in femoral (Healthy: 0.94 ± 0.036 and OA: 0.93 ± 0.034), tibial (Healthy: 0.91 ± 0.079 and OA: 0.88 ± 0.095) and patellar (Healthy: 0.88 ± 0.10 and OA: 0.84 ± 0.094) cartilage segmentation. Besides, SAGE has demonstrated greater mean readers' time of 80 ± 19 s and 80 ± 27 s in healthy and OA knee segmentation, respectively.
CONCLUSIONS: SAGE enhances the efficiency of segmentation process and attains satisfactory segmentation performance compared to manual and random walks segmentation. Future works should validate SAGE on progressive image data cohort using OA biomarkers.
OBJECTIVES:: To test the hypothesis that toe-out gait will reduce second peak knee adduction moment further and increase fall risk when combined with knee brace and laterally wedged insole in knee osteoarthritis patients.
STUDY DESIGN:: Single visit study with repeated measures.
METHODS:: First and second peak knee adduction moments, fall risk and comfort level. First and second peak knee adduction moments were determined from three-dimensional gait analysis, completed under six randomized conditions: (1) natural, (2) knee brace, (3) knee brace + toe-out gait, (4) laterally wedged insole, (5) laterally wedged insole + toe-out gait, and (6) knee brace + laterally wedged insole + toe-out gait. Fall risk was assessed by Biodex Balance System using three randomized stability settings: (1) static, (2) moderate dynamic setting (FR12), and (3) high dynamic setting (FR8).
RESULTS:: The reduction in first peak knee adduction moment and second peak knee adduction moment was greatest (7.16% and 25.55%, respectively) when toe-out gait combine with knee brace and laterally wedged insole. Significant increase in fall risk was observed with knee brace + laterally wedged insole + toe-out gait (42.85%) at FR12. Similar significant balance reductions were found at FR8 condition for knee brace + toe-out gait (35.71%), laterally wedged insole + toe-out gait (28.57%), and knee brace + laterally wedged insole + toe-out gait (50%) as compared to natural. However, knee brace decreased fall risk at FR12 by 28.57%.
CONCLUSION:: There is a synergistic effect of toe-out when combined with knee brace and laterally wedged insole concurrently in second peak knee adduction moment reduction but with a greater degree of fall risk. Simultaneous use of conservative treatments also decreases comfort level.
CLINICAL RELEVANCE: Patients with mild and moderate knee osteoarthritis are usually prescribed conservative treatment techniques. This study will provide an insight whether or not a combination of these techniques have a synergistic effect in reducing knee joint load.