This study aimed to develop and validate a fully automated system that quantifies proximal femoral bone mineral density (BMD) from CT images. The study analyzed 978 pairs of hip CT and dual-energy X-ray absorptiometry (DXA) measurements of the proximal femur (DXA-BMD) collected from three institutions. From the CT images, the femur and a calibration phantom were automatically segmented using previously trained deep-learning models. The Hounsfield units of each voxel were converted into density (mg/cm3). Then, a deep-learning model trained by manual landmark selection of 315 cases was developed to select the landmarks at the proximal femur to rotate the CT volume to the neutral position. Finally, the CT volume of the femur was projected onto the coronal plane, and the areal BMD of the proximal femur (CT-aBMD) was quantified. CT-aBMD correlated to DXA-BMD, and a receiver operating characteristic (ROC) analysis quantified the accuracy in diagnosing osteoporosis.Aims
Methods
Assessment of bone mineral density (BMD) with dual-energy X-ray absorptiometry (DXA) is a well-established clinical technique, but it is not available in the acute trauma setting. Thus, it cannot provide a preoperative estimation of BMD to help guide the technique of fracture fixation. Alternative methods that have been suggested for assessing BMD include: 1) cortical measures, such as cortical ratios and combined cortical scores; and 2) aluminium grading systems from preoperative digital radiographs. However, limited research has been performed in this area to validate the different methods. The aim of this study was to investigate the evaluation of BMD from digital radiographs by comparing various methods against DXA scanning. A total of 54 patients with distal radial fractures were included in the study. Each underwent posteroanterior (PA) and lateral radiographs of the injured wrist with an aluminium step wedge. Overall 27 patients underwent routine DXA scanning of the hip and lumbar spine, with 13 undergoing additional DXA scanning of the uninjured forearm. Analysis of radiographs was performed on ImageJ and Matlab with calculations of cortical measures, cortical indices, combined cortical scores, and aluminium equivalent grading.Aims
Methods
