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
The clinical utility of routine cross sectional imaging of the
abdomen and pelvis in the screening and surveillance of patients
with primary soft-tissue sarcoma of the extremities for metastatic
disease is controversial, based on its questionable yield paired
with concerns regarding the risks of radiation exposure, cost, and
morbidity resulting from false positive findings. Through retrospective review of 140 patients of all ages (mean
53 years; 2 to 88) diagnosed with soft-tissue sarcoma of the extremity
with a mean follow-up of 33 months (0 to 291), we sought to determine
the overall incidence of isolated abdominopelvic metastases, their
temporal relationship to chest involvement, the rate of false positives, and
to identify disparate rates of metastases based on sarcoma subtype.Objectives
Methods
