基于人工智能的胸腰椎骨密度测定系统及其校准研究

Background ?As China's aging population continues to growthe incidence of osteoporosis has been steadily increasingposing a significant health challenge for the elderly population. Furthermorethe high cost of diagnosing and treating osteoporosis highlights the importance of early diagnosis as a key strategy to reduce both patient suffering and healthcare expenses. Objective ?The objective of this study is to develop a chest and abdominal bone mineral densityBMDmeasurement model using conventional chest and abdominal CT scanswith deep neural networks and machine learning algorithms. The abdominal BMD model is subsequently employed to calibrate the chest BMD measurementswith the goal of enabling automated BMD measurement and the diagnosis of osteoporosis. Methods ?This retrospective study collected 702 patients from Suining Central Hospital in Sichuan Province who underwent both chest CT scans and QCT examinations during the period from March 2022 to June 2023spanning approximately one yearas research subjects.. Among them532 patients were randomly divided into a training set426 cases80%and a validation set106 cases20%. An additional 170 patients were included in the internal testing set. This study uses the diagnostic results of quantitative CTQCTas the reference standard and employs machine learning methods such as logistic regressionstochastic gradient descentand random forest to construct osteoporosis classification models and bone density regression models for the chest and abdomenthe established model was also tested internally. The performance of the classification models was evaluated using sensitivityspecificityaccuracyprecisionand area under the receiver operating characteristic curveAUCwhile regression model performance was assessed using mean absolute errorMAEroot mean square errorRMSEand R-squared. Results ?The results showed that the AUC values for the osteoporosis classification models in the validation set were 0.948 for the chest model and 0.968 for the abdominal model. The mean absolute errors of the BMD regression models were 10.534 and 9.449respectively. In the internal testing setthe AUC values for the classification models were 0.905 and 0.926and the MAE for the regression models were 9.255 and 7.924respectively. After calibrationthe AUC and MAE of the chest BMD measurement model in the validation set improved to 0.967 and 10.511respectively. Conclusion ?The AI-based chest and abdominal BMD measurements demonstrate a high correlation and consistency with QCT measurementseffectively diagnosing osteoporosis. The calibrated chest BMD measurement model further enhances diagnostic performance and offers significant potential for the application of chest CT scans in opportunistic osteoporosis screening.