Sex Estimation of Medial Aspect of the Ischiopubic Ramus in Adults Based on Deep Learning.

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.

Research Progress on Molecular Changes in Pulmonary Hypoxia and Cause of Death Identification in Mechanical Asphyxia.

Lung is the largest organ of the respiratory system. During hypoxia, pulmonary cells undergo rapid damage changes and activate the self-rescue pathways, thus leading to complex biomacromolecule modification. Death from mechanical asphyxia refers to death due to acute respiratory disorder caused by mechanical violence. Because of the absence of characteristic signs in corpse, the accurate identification of mechanical asphyxia has always been the difficulty in forensic pathology. This paper reviews the biomacromolecule changes under the pulmonary hypoxia condition and discusses the possibility of application of these changes to accurate identification of death from mechanical asphyxia, aiming to provide new ideas for related research.

Comparison of Three Methods for Skeleton Age Estimation.

OBJECTIVES: To find the appropriate method for age estimation for different ages and sexes. METHODS: The costal cartilage, sternum and pubic symphysis of 91 unknowns from 2000 to 2020 from the Forensic Department of the Criminal Investigation Team of Shanghai Public Security Bureau were collected. Costal cartilage, sternal and pubic symphysis inferences were used to estimate the age, and the consistency between the estimated results and the actual physiological age of the unknowns was tested. The accuracy of age estimation of different samples was compared, and the relationship between accuracy and age and sex was analyzed. RESULTS: Using the costal cartilage method, the inference errors of males, females and the whole population under 40 years old were (0.608±2.298) years, (0.429±1.867) years and (0.493±2.040) years, while those over 40 years old were (-1.707±3.770) years, (-3.286±4.078) years and (-2.625±4.029) years. The differences between different age groups in these three populations were statistically significant (P<0.05). Using the sternum method, the inference errors of males and females under the age of 40 were (0.921±3.019) years and (0.452±1.451) years, while those over the age of 40 were (-5.903±5.088) years and (-1.429±2.227) years. The differences between different age groups in males and females were statistically significant (P<0.05). Using the pubic symphysis method, the inference errors of males and females under 40 years old were (-0.204±1.876) years and (0.238±2.477) years, while those over 40 years old were (1.500±2.156) years and (-2.643±4.270) years. The differences between different age groups in males and females were statistically significant (P<0.05). Using the sternum method and pubic symphysis method for age estimation of over 40 years old, the difference between different sexes was statistically significant (P<0.05). CONCLUSIONS: All three methods of age estimation are stable and effective and more accurate for people under 40 years old. For age estimation of unknowns over 40 years old, the pubic symphysis method is preferred in males and the sternum method is preferred in females.

Forensic Examination of Six Homicide Injection Cases.

OBJECTIVES: To retrospectively analyze homicide cases of death after injection and provide reference for forensic identification. METHODS: Six homicide cases of death after injection which were investigated by the Criminal Investigation Team of Shanghai Public Security Bureau were collected and analyzed, including case situation, scene investigation, autopsy and other materials. RESULTS: The 6 cases were premeditated crimes, 5 cases took place in private spaces, and 5 cases involved the victims approached by suspects' decoy. There were no obvious abnormalities at the scene of the 6 cases. In 6 cases, the victim's body surface injury was mild or no, lividity color was abnormal, and the needlestick injury showed different manifestations from conventional medical measures. CONCLUSIONS: Death after injection is a highly concealed crime and easy to be ignored. For the suspected injection injury found in autopsy, it is necessary to carefully examine, identify and analyze, be alert to the situation of injecting poison (drug) and do a good job in evidence fixation and material extraction.