Shimadzu Review Vol.76[3・4](2019)
Medical Imaging Technologies


Development of Smart BMD AI Assist, Femur Segmentation Using Deep Learning

by Erzhong Hu, Ph.D.1Tomohiro Nakaya1Shota Oshikawa1and Wataru Takahashi2

Shimadzu Review 76[3・4] (2019.12)


With the Smart BMD bone mineral density measurement application for SONIALVISION G4, bone mineral density measurements are implemented in the applicable bone region based on the results of an automatic segmentation of regions. Accurate bone region segmentation is required for accurate measurements and to improve reproducibility in follow-ups. With conventional image processing however, if automatic extraction is difficult, it may be necessary for the user to modi-fy the bone regions by manual editing, and measurements can take considerable time. Smart BMD AI Assist, femur      segmentation using deep learning, has now been developed for images of the femur, aiming for labor savings and height-ened efficiency in bone mineral density examinations by Smart BMD. 

Keywords: Bone mineral density, Dual energy X-Ray absorptiometry, Femur segmentation, Deep learning 

1Research and Development Department, Medical Systems Division, Shimadzu Corporation, Kyoto, Japan
2AI Solution Unit, Technology Research Laboratory, Shimadzu Corporation, Kyoto, Japan

*The information contained in Shimadzu Review has not been modified since the original publication date. Please be aware that in some cases, products mentioned within the articles are no longer available.