Abstract #3986

Automatic Segmentation of MR Images of the Proximal Femur Using Deep Learning

Spencer Hallyburton^1,2, Gregory Chang³, Stephen Honig⁴, Kyunghyun Cho⁵, and Cem M Deniz^1,6

¹Department of Radiology, Center for Advanced Imaging Innovation and Research (CAI2R) and Bernard and Irene Schwartz Center for Biomedical Imaging, New York University Langone Medical Center, New York, NY, United States, ²Harvard College, Cambridge, MA, United States, ³Department of Radiology, Center for Musculoskeletal Care, New York University Langone Medical Center, New York, NY, United States, ⁴Osteoporosis Center, Hospital for Joint Diseases, New York University Langone Medical Center, New York, NY, United States, ⁵Courant Institute of Mathematical Science & Centre for Data Science, New York University, New York, NY, United States, ⁶The Sackler Institute of Graduate Biomedical Sciences, New York University School of Medicine, New York, NY, United States

Magnetic resonance imaging (MRI) of bones has added value for fracture risk assessment in osteoporosis, a disease of weak bones. However, manual segmentation of bone images is time-intensive, causing slow throughput for test results and inefficient risk assessment for patients. In this work, we implemented an automatic proximal femur segmentation algorithm by modeling a convolutional neural network (CNN) as a pixel-wise binary classification. The accuracy of automatic segmentation was investigated by analyzing similarity between automatic and manual ground-truth segmentation. In addition, we compared the time required for manual fine-tuning of the CNN segmentation with original manual segmentation.

This abstract and the presentation materials are available to members only; a login is required.

Join Here