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. 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. 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). 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.

中文翻译：

---

开发脊柱 CT 图像年龄估计的深度学习算法


准确估计尸体的年龄对于尸体的识别至关重要。然而，传统方法无法产生足够的年龄估计，特别是对于老年尸体。我们开发了一种深度学习算法，用于脊柱 CT 图像年龄估计，并检查其准确性。为了开发我们的深度学习算法，我们纳入了 140 名患者每个年龄段 8 个年龄段的 1,120 个脊柱 CT 数据。基于Visual Geometry Group-16（VGG16）的回归分析深度学习模型通过bagging提高了估计精度。为了验证其准确性，我们应用深度学习算法来估计 219 具接受尸检 CT (PMCT) 的尸体的年龄。计算已知年龄和估计年龄之间的平均差和平均绝对误差 (MAE)、估计标准误差 (SEE)。使用组内相关系数 (ICC) 和 Bland-Altman 分析进行相关分析，以评估已知年龄和估计年龄之间的差异。对于 219 具尸体，已知年龄与估计年龄之间的平均差异为 0.30 岁； MAE 为 4.36 年，SEE 为 5.48 年。 ICC (2,1) 为 0.96（95% 置信区间：0.95–0.97，p < 0.001）。 Bland-Altman 分析表明不存在比例误差或固定误差（p = 0.08 和 0.41）。我们的深度学习算法根据脊柱 CT 图像估算 219 具尸体的年龄，比传统方法更准确，而且非常有用。