Editor's Choice| Volume 45, ISSUE 3, P175-181, March 2020

Convolutional Neural Network for Second Metacarpal Radiographic Osteoporosis Screening

Published:January 17, 2020DOI:


      Osteoporosis and osteopenia are extremely common and can lead to fragility fractures. The purpose of this study was to determine whether a computer learning system could classify whether a hand radiograph demonstrated osteoporosis based on the second metacarpal cortical percentage.


      We used the second metacarpal cortical percentage as the osteoporosis predictor. A total of 4,000 posteroanterior (PA) radiographs of the hand were standardized through laterality correction, vertical alignment correction, segmentation, proxy osteoporosis predictor, and full pipeline. Laterality was classified using a LeNet convolutional neural network (CNN). Vertical alignment classification used 2,000 PA x-rays to determine vertical alignment of the second metacarpal. We employed segmentation to determine which pixels belong to the second metacarpal from 1,000 PA x-rays using the FSN-8 CNN. The full pipeline was tested on 265 previously unseen PA x-rays.


      Laterality classification accuracy was 99.62%, with a specificity of 100% and sensitivity of 99.3%. Rotation of the hand within 10° of vertical was accurate in 93.2% of films. Segmentation was 94.8% accurate. Proxy osteoporosis predictor was 88.4% accurate. Full pipeline accuracy was 93.9%. In the testing data set, the CNN had a sensitivity of 82.4% and specificity of 95.7%. In the balanced data set, 6 of 39 osteoporotic films were classified as nonosteoporotic; sensitivity was 82.4% and specificity, 94.3%.


      We have created a series of CNN that can accurately identify osteoporosis from non-osteoporosis. Furthermore, our CNN is able to make adjustments to images based on laterality and vertical alignment.

      Clinical relevance

      Convolutional neural network and computer learning can be used as an adjunct to dual-energy x-ray absorptiometry scans or to screen and make appropriate referrals for further workup in patients with suspected osteoporosis.

      Key words

      JHS Podcast

      March 2, 2020

      JHS Podcast Episode 48

      Dr Graham interviews Dr. Warren Hammert, senior author of the lead article for March 2020, “Convolutional Neural Network for Second Metacarpal Radiographic Osteoporosis Screening”.

      Loading ...
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Journal of Hand Surgery
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Burge R.
        • Dawson-Hughes B.
        • Solomon D.H.
        • Wong J.B.
        • King A.
        • Tosteson A.
        Incidence and economic burden of osteoporosis-related fractures in the United States, 2005-2025.
        J Bone Miner Res. 2007; 22: 465-475
        • Tosi L.L.
        • Gliklich R.
        • Kannan K.
        • Koval K.J.
        The American Orthopaedic Association's “Own the Bone” initiative to prevent secondary fractures.
        J Bone Joint Surg Am. 2008; 90: 163-173
        • Rozental T.D.
        • Makhni E.C.
        • Day C.S.
        • Bouxsein M.L.
        Improving evaluation and treatment for osteoporosis following distal radial fractures: a prospective randomized intervention.
        J Bone Joint Surg Am. 2008; 90: 953-961
        • Webber T.
        • Patel S.P.
        • Pensak M.
        • Fajolu O.
        • Rozental T.D.
        • Wolf J.M.
        Correlation between distal radial cortical thickness and bone mineral density.
        J Hand Surg Am. 2015; 40: 493-499
        • Schreiber J.J.
        • Kamal R.N.
        • Yao J.
        Simple assessment of global bone density and osteoporosis screening using standard radiographs of the hand.
        J Hand Surg Am. 2017; 42: 244-249
        • Liu T.
        • Guo Q.
        • Lian C.
        • et al.
        Automated detection and classification of thyroid nodules in ultrasound images using clinical-knowledge-guided convolutional neural networks.
        Med Image Anal. 2019; 58: 101555
        • Zhang Z.
        • Sejdić E.
        Radiological images and machine learning: trends, perspectives, and prospects.
        Comput Biol Med. 2019; 108: 354-370
        • Lecun Y.
        • Bottou L.
        • Bengio Y.
        • Haffner P.
        Gradient-based learning applied to document recognition.
        Proc IEEE. 1998; 86: 2278-2324
        • Shelhamer E.
        • Long J.
        • Darrell T.
        Fully convolutional networks for semantic segmentation.
        IEEE Trans Pattern Anal Mach Intell. 2017; 39: 640-651
        • Everingham M.
        • Gool L.V.
        • Williams C.K.I.
        • Winn J.
        • Zisserman A.
        The PASCAL Visual Object Classes (VOC) challenge.
        Int J Computer Vis. 2010; 88: 303-338
        • Melton III, L.J.
        • Chrischilles E.A.
        • Cooper C.
        • Lane A.W.
        • Riggs B.L.
        Perspective: how many women have osteoporosis?.
        J Bone Miner Res. 1992; 7: 1005-1010
        • Lafage R.
        • Pesenti S.
        • Lafage V.
        • Schwab F.J.
        Self-learning computers for surgical planning and prediction of postoperative alignment.
        Eur Spine J. 2018; 27: 123-128
        • Wright N.
        • Looker A.
        • Saag K.
        • et al.
        The recent prevalence of osteoporosis and low bone mass in the United States based on bone mineral density at the femoral neck or lumbar spine.
        J Bone Miner Res. 2014; 19: 2520-2526
        • Cadarette S.
        • Jaglal S.
        • Raman-Wilms L.
        • Beaton D.
        • Paterson J.
        Osteoporosis quality indicators using healthcare utilization data.
        Osteoporo Int. 2011; 22: 1335-1342