基于数据挖掘实现成人喉软骨和舌骨CT图像重组的年龄推断  

Adult Age Estimation of CT Image Reconstruction of the Laryngeal Cartilages and Hyoid Bone Based on Data Mining

作　　者：范飞[1] 戴鑫华 占梦军 李媛[1] 张奎[1] 邓振华[1] FAN Fei;DAI Xin-hua;ZHAN Meng-jun;LI Yuan;ZHANG Kui;DENG Zhen-hua(West China School of Basic Medical Sciences&Forensic Medicine,Sichuan University,Chengdu 610041,China)

机构地区：[1]四川大学华西基础医学与法医学院,四川成都610041

出　　处：《法医学杂志》2021年第1期15-20,共6页Journal of Forensic Medicine

基　　金：国家自然科学基金面上资助项目(81971801)。

摘　　要：目的运用数据挖掘技术探索喉软骨和舌骨CT图像重组用于成人年龄推断的可行性。方法收集413例颈部薄层CT图像,样本年龄范围18~<80岁,将样本随机分为测试集和训练集。参照TURK等的分级方法,对所有样本进行全方位综合阅片分级,将甲状软骨骨化过程分为6级,环状软骨骨化过程分为5级,舌骨大角和舌骨体的骨性结合分为3级。采用scikit-learn 0.17机器学习工具包(Python语言)建立成人年龄推断的多元线性回归模型、支持向量回归模型和贝叶斯岭回归模型。应用留一交叉验证和测试集评估模型性能。结果所有指标与年龄的相关性均呈中等或较差。男性样本应用支持向量回归模型的准确性最高,平均绝对误差为8.67岁,明显优于多元线性回归模型和贝叶斯岭回归模型;女性应用支持向量回归模型准确性最高,平均绝对误差为12.69岁,但与其他两种模型准确性的差异无统计学意义。结论应用数据挖掘技术有助于提高推断成人年龄的准确性,但基于喉软骨和舌骨的成人年龄推断误差仍较大,实际应用中应结合其他指标综合推断年龄。Objective To explore the feasibility of the CT image reconstruction of laryngeal cartilage and hyoid bone in adult age estimation using data mining methods.Methods The neck thin slice CT scans of 413 individuals aged 18 to<80 years were collected and divided into test set and train set,randomly.According to grading methods such as TURK et al.,all samples were graded comprehensively.The process of thyroid cartilage ossification was divided into 6 stages,the process of cricoid cartilage ossification was divided into 5 stages,and the synosteosis between the greater horn of hyoid and hyoid body was divided into 3 stages.Multiple linear regression model,support vector regression model,and Bayesian ridge regression model were developed for adult age estimation by scikit-learn 0.17 machine learning kit(Python language).Leave-one-out cross-validation and the test set were used to further evaluate performance of the models.Results All indicators were moderately or poorly associated with age.The model with the highest accuracy in male age estimation was the support vector regression model,with a mean absolute error of 8.67 years,much higher than the other two models.The model with the highest accuracy in female adult age estimation was the support vector regression model,with a mean absolute error of 12.69 years,but its accuracy differences with the other two models had no statistical significance.Conclusion Data mining technology can improve the accuracy of adult age estimation,but the accuracy of adult age estimation based on laryngeal cartilage and hyoid bone is still not satisfactory,so it should be combined with other indicators in practice.

关 键 词：法医人类学 法医影像学 年龄测定 骨骼 喉软骨 舌骨 计算机体层成像 重组 数据挖掘 

分 类 号：DF795.6[医药卫生—法医学]