RESUMO
Objectives: Diagnosis and treatment of osteoporosis are instrumental in obtaining good outcomes of hip surgery. Measuring bone mineral density (BMD) using dual-energy X-ray absorptiometry (DXA) is the gold standard for diagnosing osteoporosis. However, due to limited access to DXA, there is a need for a screening tool to identify patients at a higher risk of osteoporosis. We analyzed the potential utility of the Osteoporosis Self-assessment Tool for Asians (OSTA) as a screening tool for osteoporosis. Methods: A total of 1378 female patients who underwent hip surgery at 8 institutions were analyzed. For each patient, the BMD of the proximal femoral region was measured by DXA (DXA-BMD), and the correlation with OSTA score (as a continuous variable) was assessed. Receiver operating characteristic (ROC) curve analysis was performed to assess the ability of OSTA score to predict osteoporosis. Lastly, the OSTA score was truncated to yield an integer (OSTA index) to clarify the percentage of patients with osteoporosis for each index. Results: DXA-BMD showed a strong correlation with OSTA (r = 0.683; P < 0.001). On ROC curve analysis, the optimal OSTA score cut-off value of -5.4 was associated with 73.8% sensitivity and 80.9% specificity for diagnosis of osteoporosis (area under the curve: 0.842). A decrease in the OSTA index by 1 unit was associated with a 7.3% increase in the probability of osteoporosis. Conclusions: OSTA is a potentially useful tool for screening osteoporosis in patients undergoing hip surgery. Our findings may help identify high-risk patients who require further investigation using DXA.
RESUMO
PURPOSE: Progression of hip osteoarthritis (hip OA) leads to pain and disability, likely leading to surgical treatment such as hip arthroplasty at the terminal stage. The severity of hip OA is often classified using the Crowe and Kellgren-Lawrence (KL) classifications. However, as the classification is subjective, we aimed to develop an automated approach to classify the disease severity based on the two grades using digitally-reconstructed radiographs from CT images. METHODS: Automatic grading of the hip OA severity was performed using deep learning-based models. The models were trained to predict the disease grade using two grading schemes, i.e., predicting the Crowe and KL grades separately, and predicting a new ordinal label combining both grades and representing the disease progression of hip OA. The models were trained in classification and regression settings. In addition, the model uncertainty was estimated and validated as a predictor of classification accuracy. The models were trained and validated on a database of 197 hip OA patients, and externally validated on 52 patients. The model accuracy was evaluated using exact class accuracy (ECA), one-neighbor class accuracy (ONCA), and balanced accuracy. RESULTS: The deep learning models produced a comparable accuracy of approximately 0.65 (ECA) and 0.95 (ONCA) in the classification and regression settings. The model uncertainty was significantly larger in cases with large classification errors ( P < 6 e - 3 ). CONCLUSIONS: In this study, an automatic approach for grading hip OA severity from CT images was developed. The models have shown comparable performance with high ONCA, which facilitates automated grading in large-scale CT databases and indicates the potential for further disease progression analysis. Classification accuracy was correlated with the model uncertainty, which would allow for the prediction of classification errors. The code will be made publicly available at https://github.com/NAIST-ICB/HipOA-Grading .