Automated classification of hip fractures using deep convolutional neural networks with orthopedic surgeon-level accuracy: ensemble decision-making with antero-posterior and lateral radiographs

Authors

  • Satoshi Maki Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Japan
  • Yutoku Yamada Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Japan; Department of Orthopaedic Surgery, Seirei Sakura Citizen Hospital
  • Shunji Kishida Department of Orthopaedic Surgery, Seirei Sakura Citizen Hospital
  • Haruki Nagai Department of Orthopaedic Surgery, Seirei Sakura Citizen Hospital
  • Junnosuke Arima Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Japan; Department of Orthopaedic Surgery, Oyumino Central Hospital
  • Nanako Yamakawa Department of Orthopaedic Surgery, Seirei Sakura Citizen Hospital
  • Yasushi Iijima Department of Orthopaedic Surgery, Seirei Sakura Citizen Hospital
  • Yuki Shiko Biostatistics Section, Clinical Research Center, Chiba University Hospital
  • Yohei Kawasaki Biostatistics Section, Clinical Research Center, Chiba University Hospital
  • Toshiaki Kotani Department of Orthopaedic Surgery, Seirei Sakura Citizen Hospital
  • Yasuhiro Shiga Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Japan
  • Kazuhide Inage Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Japan
  • Sumihisa Orita Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Japan; Center for Frontier Medical Engineering, Chiba University
  • Yawara Eguchi Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Japan
  • Hiroshi Takahashi Department of Orthopaedic Surgery, Toho University Sakura Medical Center, Japan
  • Takeshi Yamashita Department of Orthopaedic Surgery, Oyumino Central Hospital
  • Shohei Minami Department of Orthopaedic Surgery, Seirei Sakura Citizen Hospital
  • Seiji Ohtori Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Japan

DOI:

https://doi.org/10.1080/17453674.2020.1803664

Abstract

Background and purpose — Deep-learning approaches based on convolutional neural networks (CNNs) are gaining interest in the medical imaging field. We evaluated the diagnostic performance of a CNN to discriminate femoral neck fractures, trochanteric fractures, and non-fracture using antero-posterior (AP) and lateral hip radiographs.

Patients and methods — 1,703 plain hip AP radiographs and 1,220 plain hip lateral radiographs were included in the total dataset. 150 images each of the AP and lateral views were separated out and the remainder of the dataset was used for training. The CNN made the diagnosis based on: (1) AP radiographs alone, (2) lateral radiographs alone, or (3) both AP and lateral radiographs combined. The diagnostic performance of the CNN was measured by the accuracy, recall, precision, and F1 score. We further compared the CNN’s performance with that of orthopedic surgeons.

Results — The average accuracy, recall, precision, and F1 score of the CNN based on both anteroposterior and lateral radiographs were 0.98, 0.98, 0.98, and 0.98, respectively. The accuracy of the CNN was comparable to, or statistically significantly better than, that of the orthopedic surgeonsregardless of radiographic view used. In the CNN model, the accuracy of the diagnosis based on both views was significantly better than the lateral view alone and tended to be better than the AP view alone.

Interpretation — The CNN exhibited comparable or superior performance to that of orthopedic surgeons to discriminate femoral neck fractures, trochanteric fractures, and non-fracture using both AP and lateral hip radiographs.

Downloads

Download data is not yet available.

Downloads

Additional Files

Published

2020-08-12

How to Cite

Maki, S. ., Yamada, Y. ., Kishida, S. ., Nagai, H. ., Arima, J. ., Yamakawa, N. ., Iijima, Y. ., Shiko, Y. ., Kawasaki , Y. ., Kotani, T. ., Shiga, Y. ., Inage, K. ., Orita, S. ., Eguchi, Y. ., Takahashi, H. ., Yamashita, T. ., Minami, S. ., & Ohtori, S. . (2020). Automated classification of hip fractures using deep convolutional neural networks with orthopedic surgeon-level accuracy: ensemble decision-making with antero-posterior and lateral radiographs. Acta Orthopaedica, 91(6), 699–704. https://doi.org/10.1080/17453674.2020.1803664