Using Deep Neural Networks for Predicting Age and Sex in Healthy Adult Chest Radiographs

DOI Web Site 2 Citations
  • Chung-Yi Yang
    School of Medicine, College of Medicine, I-Shou University, Kaohsiung 82445, Taiwan
  • Yi-Ju Pan
    Department of Psychiatry, Far Eastern Memorial Hospital, New Taipei City 22060, Taiwan
  • Yen Chou
    Division of Medical Image, Far Eastern Memorial Hospital, New Taipei City 22060, Taiwan
  • Chia-Jung Yang
    Department of Radiology, Taitung MacKay Memorial Hospital, Taitung 95054, Taiwan
  • Ching-Chung Kao
    AI Lab, Quanta Computer Inc., Taoyuan City 33377, Taiwan
  • Kuan-Chieh Huang
    AI Lab, Quanta Computer Inc., Taoyuan City 33377, Taiwan
  • Jing-Shan Chang
    AI Lab, Quanta Computer Inc., Taoyuan City 33377, Taiwan
  • Hung-Chieh Chen
    School of Medicine, National Yang-Ming Chiao-Tung University, Taipei 11267, Taiwan
  • Kuei-Hong Kuo
    Division of Medical Image, Far Eastern Memorial Hospital, New Taipei City 22060, Taiwan

Description

<jats:p>Background: The performance of chest radiography-based age and sex prediction has not been well validated. We used a deep learning model to predict the age and sex of healthy adults based on chest radiographs (CXRs). Methods: In this retrospective study, 66,643 CXRs of 47,060 healthy adults were used for model training and testing. In total, 47,060 individuals (mean age ± standard deviation, 38.7 ± 11.9 years; 22,144 males) were included. By using chronological ages as references, mean absolute error (MAE), root mean square error (RMSE), and Pearson’s correlation coefficient were used to assess the model performance. Summarized class activation maps were used to highlight the activated anatomical regions. The area under the curve (AUC) was used to examine the validity for sex prediction. Results: When model predictions were compared with the chronological ages, the MAE was 2.1 years, RMSE was 2.8 years, and Pearson’s correlation coefficient was 0.97 (p < 0.001). Cervical, thoracic spines, first ribs, aortic arch, heart, rib cage, and soft tissue of thorax and flank seemed to be the most crucial activated regions in the age prediction model. The sex prediction model demonstrated an AUC of >0.99. Conclusion: Deep learning can accurately estimate age and sex based on CXRs.</jats:p>

Journal

Citations (2)*help

See more

Details 詳細情報について

Report a problem

Back to top