Automatic Identification of Osteoporosis from Phalanges Computed Radiography Images Based on CNN

• HATANO Kazuhiro

  Kyushu Institute of Technology

• MURAKAMI Seiichi

  University of Occupational and Environmental Health

• UEMURA Tomoki

  Kyushu Institute of Technology

• LU Huimin

  Kyushu Institute of Technology

• KIM Hyoungseop

  Kyushu Institute of Technology

• AOKI Takatoshi

  University of Occupational and Environmental Health

Bibliographic Information

Other Title

• CNNを用いた指骨CR画像からの骨粗しょう症の自動識別
• Automatic identification of bone erosions in rheumatoid arthritis from hand radiographs based on deep convolutional neural network

Abstract

Osteoporosis is the main disease of bone. Although image diagnosis for osteoporosis is effective, there are concerns about increased burdens on doctors and variations in diagnostic results due to experience differences of doctors and undetected lesions. Therefore, in this paper, we propose a diagnostic support method to classify osteoporosis from Computed Radiography (CR) images of the phalanges and present classification results to doctors. In the proposed method, we constructed classifiers using Residual Network (ResNet), which is one type of convolution neural network, and classified the presence or absence of osteoporosis. For the input image to ResNet, we used the image generated from CR images. In this paper, we proposed three kinds of input images and conducted training and classification evaluation on each image. In the experiment, the proposed method was applied to 101 cases and evaluated using the Area Under the Curve (AUC) value on the Receiver Operating Characteristics (ROC) curve, the maximum value of which was 0.931.

Journal

• Medical Imaging Technology

  Medical Imaging Technology 37 (2), 107-115, 2019-03-25

  The Japanese Society of Medical Imaging Technology

Keywords

• Computer aided diagnosis
• Computed radiography
• Osteoporosis
• Convolutional neural network

Details

• CRID: 1390564238083641088
• NII Article ID: 130007633096
• DOI: 10.11409/mit.37.107
• DOI: 10.1007/s11042-017-5449-4
• ISSN: 21853193
• ISSN: 15737721
• ISSN: 0288450X
• ISSN: 13807501
• Web Site: http://link.springer.com/article/10.1007/s11042-017-5449-4/fulltext.html
• Web Site: http://link.springer.com/content/pdf/10.1007/s11042-017-5449-4.pdf
• Web Site: https://search.jamas.or.jp/link/ui/2019250336
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed