Enhancement of Prediction for Hip Fractures Using Stochastic Assessment of Bone Mineral Density Distribution From DXA Images

Hip fractures are among the most common types of osteoporotic fractures that affect one in three women and one in six men over the age of 50 [1]. It is well known that loss of bone mass, quantified by bone mineral density using Dual-energy X-ray Absorptiometry (DXA), is associated with the increasing risk of bone fractures. However, bone mineral density (BMD) alone cannot fully explain changes in fracture risks [2, 3]. In particular, BMD is not able to predict fracture risks for women with osteopenia, in which a BMD T-score is between −1.0 and −2.5. This suggests additional factors (i.e., bone quality) should be considered in predicting fracture risks [4].