Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs using an Adaptation of the Genant Semiquantitative Criteria.

Journal: Academic radiology
Published Date: Mar 26, 2022

Abstract

RATIONALE AND OBJECTIVES: Osteoporosis affects 9% of individuals over 50 in the United States and 200 million women globally. Spinal osteoporotic compression fractures (OCFs), an osteoporosis biomarker, are often incidental and under-reported. Accurate automated opportunistic OCF screening can increase the diagnosis rate and ensure adequate treatment. We aimed to develop a deep learning classifier for OCFs, a critical component of our future automated opportunistic screening tool.

Authors

  • Qifei Dong
    Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, Washington.
  • Gang Luo
    Department of Biomedical Informatics and Medical Education, University of Washington UW Medicine South Lake Union, 850 Republican Street, Building C, Box 358047 Seattle, WA 98195, USA, luogang@uw.edu.
  • Nancy E Lane
    Department of Medicine, University of California - Davis, Sacramento, California.
  • Li-Yung Lui
    Research Institute, California Pacific Medical Center, San Francisco, California.
  • Lynn M Marshall
    Epidemiology Programs, Oregon Health and Science University-Portland State University School of Public Health, Portland, Oregon.
  • Deborah M Kado
    Department of Medicine, Stanford University, Stanford, California; Geriatric Research Education and Clinical Center (GRECC), Veterans Administration Health System, Palo Alto, CA 94304, USA.
  • Peggy Cawthon
    California Pacific Medical Center Research Institute, Department of Epidemiology and Biostatistics, University of California - San Francisco, San Francisco, California.
  • Jessica Perry
    Department of Biostatistics, University of Washington, Seattle, Washington, USA.
  • Sandra K Johnston
    Department of Radiology, University of Washington, Seattle, Washington.
  • David Haynor
    Department of Radiology, University of Washington, Seattle, Washington.
  • Jeffrey G Jarvik
    Comparative Effectiveness, Cost and Outcomes Research Center, University of Washington, Seattle, WA, USA. jarvikj@uw.edu.
  • Nathan M Cross
    Department of Radiology, University of Washington, 1959 NE Pacific Street Box 357115, Seattle, Washington 98195-7115. Electronic address: nmcross@uw.edu.

Keywords

External Resources

Popular Topics
Recent Journals