Sex Estimation of Medial Aspect of the Ischiopubic Ramus in Adults Based on Deep Learning / 法医学杂志

OBJECTIVES@#To investigate the reliability and accuracy of deep learning technology in automatic sex estimation using the 3D reconstructed images of the computed tomography (CT) from the Chinese Han population.@*METHODS@#The pelvic CT images of 700 individuals (350 males and 350 females) of the Chinese Han population aged 20 to 85 years were collected and reconstructed into 3D virtual skeletal models. The feature region images of the medial aspect of the ischiopubic ramus (MIPR) were intercepted. The Inception v4 was adopted as the image recognition model, and two methods of initial learning and transfer learning were used for training. Eighty percent of the individuals' images were randomly selected as the training and validation dataset, and the remaining were used as the test dataset. The left and right sides of the MIPR images were trained separately and combinedly. Subsequently, the models' performance was evaluated by overall accuracy, female accuracy, male accuracy, etc.@*RESULTS@#When both sides of the MIPR images were trained separately with initial learning, the overall accuracy of the right model was 95.7%, the female accuracy and male accuracy were both 95.7%; the overall accuracy of the left model was 92.1%, the female accuracy was 88.6% and the male accuracy was 95.7%. When the left and right MIPR images were combined to train with initial learning, the overall accuracy of the model was 94.6%, the female accuracy was 92.1% and the male accuracy was 97.1%. When the left and right MIPR images were combined to train with transfer learning, the model achieved an overall accuracy of 95.7%, and the female and male accuracies were both 95.7%.@*CONCLUSIONS@#The use of deep learning model of Inception v4 and transfer learning algorithm to construct a sex estimation model for pelvic MIPR images of Chinese Han population has high accuracy and well generalizability in human remains, which can effectively estimate the sex in adults.

Sex Estimation of Han Adults in Western China Based on Three-Dimensional Cranial CT Reconstruction / 法医学杂志

OBJECTIVES@#To examine the reliability and accuracy of Walker's model for estimating the sex of Han adults in western China by using cranium three-dimensional (3D) CT reconstruction, and to study the suitable cranial sex estimation model for Han people in western China.@*METHODS@#A total of 576 cranial CT 3D reconstructed images from Hanzhong Hospital in Shaanxi Province from 2017 to 2021 were collected. These images were divided into the experimental group with 486 samples and the validation group with 90 samples. Walker's model was used by observer 1 to estimate the sex of experimental group samples. The logistic function applicable to Han people in western China was corrected by observer 1. The 90 samples in the validation group were scored and substituted into the modified logistic function to complete the back substitution test by observer 1, 2 and 3.@*RESULTS@#The accuracy of sex estimation of Han adults in western China was 63.2%-77.2% by applying Walker's model. The accuracy of modified logistic function was 82.9%. The accuracy of sex estimation through back substitution test by 3 observers was 75.6%-91.1%, with a Kappa value of 0.689 (P<0.05) for inter-observer consistency and 0.874 (P<0.05) for intra-observer consistency.@*CONCLUSIONS@#There are great differences in bone characteristics among people from different regions. The modified logistic function can achieve higher accuracy in Han adults in western China.

Application of Artificial Intelligence Automatic Diatom Identification System in Practical Cases / 法医学杂志

Objective To discuss the application of artificial intelligence automatic diatom identification system in practical cases, to provide reference for quantitative diatom analysis using the system and to validate the deep learning model incorporated into the system. Methods Organs from 10 corpses in water were collected and digested with diatom nitric acid; then the smears were digitally scanned using a digital slide scanner and the diatoms were tested qualitatively and quantitatively by artificial intelligence automatic diatom identification system. Results The area under the curve （AUC） of the receiver operator characteristic （ROC） curve of the deep learning model incorporated into the artificial intelligence automatic diatom identification system, reached 98.22% and the precision of diatom identification reached 92.45%. Conclusion The artificial intelligence automatic diatom identification system is able to automatically identify diatoms, and can be used as an auxiliary tool in diatom testing in practical cases, to provide reference to drowning diagnosis.