Identification of unknown cadavers is an important task for forensic scientists. Forensic scientists attempt to identify skeletal remains based on factors including age, sex, and dental treatment remains. Forensic scientists commonly consider skull or pelvic shape to evaluate the sex; however, these evaluations require sufficient experience and knowledge and lack objectivity and reproducibility. To ensure objectivity and reproducibility for sex evaluation, we applied a gated attention-based multiple-instance learning model to three-dimensional (3D) skull images reconstructed from postmortem head computed tomography scans. We preprocessed the images, trained with 864 training data, validated the model with 124 validation data, and evaluated the performance of our model in terms of accuracy with 246 test data. Furthermore, three forensic scientists evaluated the 3D skull images, and their performances were compared with those of the model. Our model showed an accuracy of 0.93, which was higher than that of the forensic scientists. Our model primarily focused on the entire skull owing to visualization but focused less on the areas often investigated by forensic scientists. In summary, our model may serve as a supportive tool to identify cadaver sex based on skull shape. Further studies are required to improve the model’s performance.

Although age estimation upon death is important in the identification of unknown cadavers for forensic scientists, to the best of our knowledge, no study has examined the utility of deep neural network (DNN) models for age estimation among cadavers. We performed a postmortem computed tomography (CT) examination of 1000 and 500 male and female cadavers, respectively. These CT slices were converted into 3-dimensional images, and only the thoracolumbar region was extracted. Eighty percent of them were categorized as training datasets and the others as test datasets for both sexes. We fine-tuned the ResNet152 models using the training datasets. We conducted 4-fold cross-validation, and the mean absolute error (MAE) of the test datasets was calculated using the ensemble learning of four ResNet152 models. Consequently, the MAE of the male and female models was 7.25 and 7.16, respectively. Our study shows that DNN models can be useful tools in the field of forensic medicine.

(1) Background: While decreasing bone mineral density (BMD) with age in living people has been well documented, a correlation between age and bone mineral density in deceased people has only been reported in a few studies. A correlation between age and BMD in deceased people was investigated as an objective tool for age estimation of unidentified remains. (2) Methods: The Bone Area Ratio (BAR) was measured in 402 autopsy cases (143 females and 259 males over the age of 20). (3) Results: The correlation coefficient in the females was r = −0.5476, and the correlation coefficient in the males was r = −0.2166, indicating a stronger correlation in females than in males. A comparison of the BAR values in the deceased females for each age group with that in live females found no significant differences in the BAR values. BAR values in the deceased were similar to in live individuals, and this did not change with duration of the postmortem interval. (4) Conclusions: Measuring the BAR value based on bone mass using ultrasonic waves is rapid and easy, even for those lacking forensic training, and may be used to estimate the age of an individual and the likelihood of fracture due to trauma.

Ketoacidosis is one of the common diseases that sometimes result in death. In forensic autopsy cases, the measuring of ketone bodies, especially β-hydroxybutyrate (BHB), is useful in diagnosing postmortem ketoacidosis as a cause of death. However, increased BHB values are not always indicative of ketoacidosis. Other causes of death, such as hypothermia, are known to increase BHB values. In addition, sometimes, we experience cases of increased BHB values that are unlikely to be associated with the pathophysiology or the cause of death resulting in an increase in BHB values. In this study, autopsies were performed to determine the relationship between blood BHB values and the postmortem interval (PMI). The patients were divided into four groups: PMI ≤ 24 h, PMI ≤ 48 h, PMI ≤ 72 h, and PMI > 72 h. The BHB values for each group were then compared. Based on the analysis, patients with a PMI ≤ 72 h and those with a PMI > 72 h had significantly higher BHB values than patients with a PMI ≤ 24 h. In conclusion, there remains a possibility that the BHB values increase after death. Forensic pathologists should consider PMI when diagnosing ketoacidosis as the cause of death.