Age estimation based on machine learning and thin-layer CT of sternal end of clavicle / 中国法医学杂志

Objective The Kellinghaus grading method was used to manually read and grade the thin-layer CT of sternal end of clavicle,and a variety of traditional statistical methods as well as machine learning methods were used to construct age estimation models for adolescents and adults in early adulthood,to explore the value of the application of machine learning technology in the study of age estimation of the Han Chinese population in Sichuan.Methods Thin-section CT images of the chest were retrospectively collected from 491 individuals aged 10～30 years,and the collected samples were assigned a reading grade with reference to the Kellinghaus grading method.10%of the xases were randomly selected as the test set,and the remaining data were used as the training set to construct a variety of traditional statistical regression models and machine learning models for estimating the age of adolescents and adults in early adulthood,and the performance of the models was evaluated by using the mean absolute error(MAE).Results The statistical regression model with the best efficacy was the cubic regression model,with an MAE value of 1.34 for males and 1.57 for females;of the three machine learning models,the Random Forest model had the best predictive efficacy for males,with an MAE value of 1.39,and the Support Vector model had the best predictive efficacy for females,with an MAE value of 1.51.Conclusion In the construction of age estimation models for sternal end of clavicle,the machine learning model has a certain improvement in the accuracy of age prediction,but there is no obvious advantage compared with the traditional statistical regression model,and the use of the machine learning method in age estimation based on sternal end of clavicle still needs further exploration.

Adult Age Estimation of CT Image Reconstruction of the Laryngeal Cartilages and Hyoid Bone Based on Data Mining / 法医学杂志

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.

Research Progress of Adult Age Determination with Imaging Methods / 法医学杂志

Adult age determination plays an important role in individual identification, criminal investigation and social welfare. The most popular adult age determination indicators are pubic symphysis, iliac auricular surface, costal cartilage, cranial sutures, teeth, laryngeal cartilage, etc. In recent years, with the progress of CT imaging and 3D reconstruction technology, the adult age determination study gradually has transferred from a time-consuming general observation of bones with complex pre-processing in the past to the non-destructive, convenient, time-saving and easy to store image analysis technology. To explore more accurate, rapid and convenient adult age determination methods, multiple imaging methods and artificial intelligence have been applied in adult age determination. This paper reviews the common methods and research progress of adult age determination at home and abroad, infers the development direction of adult age determination, in order to provide reference for the improvement and optimization of forensic adult age determination.

Estimation of Sex from Patella Measurements in Sichuan Han Population Based on CT-Three-Dimensional Volume Reconstruction Technique / 法医学杂志

Objective To estimate sex based on patella measurements of Sichuan Han population by computed tomography three-dimensional volume reconstruction technique, and to explore the application value of patella in sex estimation. Methods CT three-dimensional volume reconstruction images of patella of 250 individuals were collected, the four measurement indicators including patellar length, patellar width, patellar thickness, and patellar volume were measured. The t-test was used to determine measurement indicators with sex differences. Fisher discriminant analysis was used to establish the sex discriminant function and the prediction accuracy was calculated by leave-one-out cross validation. Results The sex differences of the four measurement indicators had a statistical significance （P<0.05）. The accuracy rate of the univariate discriminant function established by the patellar length was the highest （82.0%）. The accuracy rates of the all indicators discriminant function and the stepwise discriminant function were 80.4% and 81.6%, respectively. Conclusion It is feasible and accurate to estimate sex of Sichuan Han population by patella measurements with CT three-dimensional volume reconstruction technique. The method may be used as an alternative for sex estimation of Sichuan Han population when other bones with higher accuracy are not available.

Forensic Imaging for Causal Investigation of Death

A 63-year-old man was found in the street after overrun by a car. Postmortem CT revealed multiple bone fractures, but surprisingly all without any relevant hemorrhage which would have been expected under such circumstances. A round radiopaque formation was found in the duodenum, which was reminiscent of ingested tablets. The toxicological analysis revealed high concentrations of zopiclone and alcohol. By combining radiologic and forensic results, zopiclone and alcohol intoxication were concluded as the cause of death, followed by a postmortem overrun accident.