Magnetic resonance imaging (MRI) has been proposed as a complimentary method to measure bone quality and assess fracture risk. However, manual segmentation of MR images of bone is time-consuming, limiting the use of MRI measurements in the clinical practice. The purpose of this paper is to present an automatic proximal femur segmentation method that is based on deep convolutional neural networks (CNNs). This study had institutional review board approval and written informed consent was obtained from all subjects. A dataset of volumetric structural MR images of the proximal femur from 86 subjects were manually-segmented by an expert. We performed experiments by training two different CNN architectures with multiple number of initial feature maps, layers and dilation rates, and tested their segmentation performance against the gold standard of manual segmentations using four-fold cross-validation. Automatic segmentation of the proximal femur using CNNs achieved a high dice similarity score of 0.95 ± 0.02 with precision = 0.95 ± 0.02, and recall = 0.95 ± 0.03. The high segmentation accuracy provided by CNNs has the potential to help bring the use of structural MRI measurements of bone quality into clinical practice for management of osteoporosis.

Osteoporosis is a disease of weak bone and increased fracture risk caused by low bone mass and microarchitectural deterioration of bone tissue. The standard-of-care test used to diagnose osteoporosis, dual-energy x-ray absorptiometry (DXA) estimation of areal bone mineral density (BMD), has limitations as a tool to identify patients at risk for fracture and as a tool to monitor therapy response. Magnetic resonance imaging (MRI) assessment of bone structure and microarchitecture has been proposed as another method to assess bone quality and fracture risk in vivo. MRI is advantageous because it is noninvasive, does not require ionizing radiation and can evaluate both cortical and trabecular bone. In this review article, we summarize and discuss research progress on MRI of bone structure and microarchitecture over the last decade, focusing on in vivo translational studies. Single center, in vivo studies have provided some evidence for the added value of MRI as a biomarker of fracture risk or treatment response. Larger, prospective, multicenter studies are needed in the future to validate the results of these initial translational studies.

No abstract