ABSTRACT
Age at death estimation has always been a crucial yet challenging part of identification process in forensic field. The use of human skeletons have long been explored using the principle of macro and micro-architecture change in correlation with increasing age. The clavicle is recommended as the best candidate for accurate age estimation because of its accessibility, time to maturation and minimal effect from weight. Our study applies pre-trained convolutional neural network in order to achieve the most accurate and cost effective age estimation model using clavicular bone. The total of 988 clavicles of Thai population with known age and sex were radiographed using Kodak 9000 Extra-oral Imaging System. The radiographs then went through preprocessing protocol which include region of interest selection and quality assessment. Additional samples were generated using generative adversarial network. The total clavicular images used in this study were 3,999 which were then separated into training and test set, and the test set were subsequently categorized into 7 age groups. GoogLeNet was modified at two layers and fine tuned the parameters. The highest validation accuracy was 89.02% but the test set achieved only 30% accuracy. Our results show that the use of medial clavicular radiographs has a potential in the field of age at death estimation, thus, further study is recommended.
ABSTRACT
Sex estimation is one of the crucial procedures in the biological profile identification of human skeletal remains. Knowing sex of unknown case can lead to accurate and appropriate methods for predicting age, stature, ancestry, or even personal identification. Skull is one of the most reliable one among other skeletons and it is usually retained for both archaeological and forensic contexts. Although many morphological features and metric measurements of skull have been studied for sexing, but to the best of our knowledge is no study on maxillary suture length for sex estimation. Therefore, this study aims to develop a new sex estimation method for a Thai population by determining three maxillary suture lengths: anterior, transverse, and posterior maxillary suture, by computerizing amount of pixel obtained from photographs of these sutures. The present study was conducted on 190 Thai bone samples of which 96 were males and 94 were females. Independent t test revealed statistically significant difference (P < 0.01) between males and females in all maxillary suture measurements. Equations derived from prediction model, which required three maxillary suture lengths gave 76.8421% accuracy from the leave-one-out cross validation in estimating sex percentage accuracies in predicting sex from these equations, which were relatively moderate. This study provides a novel and objective sex estimation method for Thais. It suggests that maxillary suture length can be applied for sex estimation. The new computerized technique will contribute basis knowledge and method for sex estimation, especially when only base of skull is available in forensic circumstance.
Subject(s)
Female , Humans , Male , Asian People , Cranial Sutures , Methods , Sex Determination Analysis , Skeleton , Skull , Skull Base , Sutures , ThailandABSTRACT
Sex determination is an important step in biological identification from skeletal remains, especially in forensic circumstances. Many authors suggested that the morphological study was more subjective than the metric. There are various craniometric studies in different populations. They revealed that there was population-specific for the sex discriminant equation derived from each population. Thus, the present study aimed to evaluate sexual dimorphism and develop the discriminant function from 200 Thai skulls. Twenty-five standard cranial measurements were examined. The results revealed that males' cranium were statistically significant larger than females' in all measurements (P<0.05), except for minimum breadth of nasal bone. Sexual dimorphism index also expressed relatively high male/female ratio indicating great sexual dimorphism. The best practical equation for sex determination with six measurements (maximum cranial length, bizygomatic breadth, biauricular breadth, nasal height, biorbital breadth and right mastoid length) was derived from a stepwise discriminant method. This equation with 90.6% accuracy (91.1% in male and 90.0% in female) can provide valuable application utilizing in sex determination from skull in a Thai population.