Development of a deep-learning algorithm for age estimation on CT images of the vertebral column

Ikuo Kawashita; Wataru Fukumoto; Hidenori Mitani; Keigo Narita; Keigo Chosa; Yuko Nakamura; Masataka Nagao; Kazuo Awai

doi:10.1016/j.legalmed.2024.102444

Development of a deep-learning algorithm for age estimation on CT images of the vertebral column

Leg Med (Tokyo). 2024 Apr 7:69:102444. doi: 10.1016/j.legalmed.2024.102444. Online ahead of print.

Authors

Ikuo Kawashita¹, Wataru Fukumoto², Hidenori Mitani¹, Keigo Narita¹, Keigo Chosa¹, Yuko Nakamura¹, Masataka Nagao³, Kazuo Awai⁴

Affiliations

¹ Department of Diagnostic Radiology, Graduate School of Biomedical and Health Science, Hiroshima University 1-2-3 Kasumi, Minamiku, Hiroshima 734-8551, Japan.
² Department of Diagnostic Radiology, Graduate School of Biomedical and Health Science, Hiroshima University 1-2-3 Kasumi, Minamiku, Hiroshima 734-8551, Japan; Center for Cause of Death Investigation Research, Graduate School of Biomedical and Health Science, Hiroshima University 1-2-3 Kasumi, Minamiku, Hiroshima 734-8551, Japan. Electronic address: wfukumoto@hiroshima-u.ac.jp.
³ Center for Cause of Death Investigation Research, Graduate School of Biomedical and Health Science, Hiroshima University 1-2-3 Kasumi, Minamiku, Hiroshima 734-8551, Japan.
⁴ Department of Diagnostic Radiology, Graduate School of Biomedical and Health Science, Hiroshima University 1-2-3 Kasumi, Minamiku, Hiroshima 734-8551, Japan; Center for Cause of Death Investigation Research, Graduate School of Biomedical and Health Science, Hiroshima University 1-2-3 Kasumi, Minamiku, Hiroshima 734-8551, Japan.

PMID: 38604090
DOI: 10.1016/j.legalmed.2024.102444

Abstract

Purpose: The accurate age estimation of cadavers is essential for their identification. However, conventional methods fail to yield adequate age estimation especially in elderly cadavers. We developed a deep learning algorithm for age estimation on CT images of the vertebral column and checked its accuracy.

Method: For the development of our deep learning algorithm, we included 1,120 CT data of the vertebral column of 140 patients for each of 8 age decades. The deep learning model of regression analysis based on Visual Geometry Group-16 (VGG16) was improved in its estimation accuracy by bagging. To verify its accuracy, we applied our deep learning algorithm to estimate the age of 219 cadavers who had undergone postmortem CT (PMCT). The mean difference and the mean absolute error (MAE), the standard error of the estimate (SEE) between the known- and the estimated age, were calculated. Correlation analysis using the intraclass correlation coefficient (ICC) and Bland-Altman analysis were performed to assess differences between the known- and the estimated age.

Results: For the 219 cadavers, the mean difference between the known- and the estimated age was 0.30 years; it was 4.36 years for the MAE, and 5.48 years for the SEE. The ICC (2,1) was 0.96 (95 % confidence interval: 0.95-0.97, p < 0.001). Bland-Altman analysis showed that there were no proportional or fixed errors (p = 0.08 and 0.41).

Conclusions: Our deep learning algorithm for estimating the age of 219 cadavers on CT images of the vertebral column was more accurate than conventional methods and highly useful.

Keywords: CT; Cadaver; Deep learning; Spine.