Artificial intelligence in age and sex determination using maxillofacial radiographs: A systematic review.

In the past few years, there has been an enormous increase in the application of artificial intelligence and its adoption in multiple fields, including healthcare. Forensic medicine and forensic odontology have tremendous scope for development using AI. In cases of severe burns, complete loss of tissue, complete or partial loss of bony structure, decayed bodies, mass disaster victim identification, etc., there is a need for prompt identification of the bony remains. The mandible, is the strongest bone of the facial region, is highly resistant to undue mechanical, chemical or physical impacts and has been widely used in many studies to determine age and sexual dimorphism. Radiographic estimation of the jaw bone for age and sex is more workable since it is simple and can be applied equally to both dead and living cases to aid in the identification process. Hence, this systematic review is focused on various AI tools for age and sex determination in maxillofacial radiographs. The data was obtained through searching for the articles across various search engines, published from January 2013 to March 2023. QUADAS 2 was used for qualitative synthesis, followed by a Cochrane diagnostic test accuracy review for the risk of bias analysis of the included studies. The results of the studies are highly optimistic. The accuracy and precision obtained are comparable to those of a human examiner. These models, when designed with the right kind of data, can be of tremendous use in medico legal scenarios and disaster victim identification.

Are computed tomography images of the mandible useful in age and sex determination? A forensic science meta-analysis.

OBJECTIVES: This meta-analysis addresses the use of mandibular computed tomography (CT) scans for age and/or sex determination in forensic science. METHODS: Six databases were searched until June 2023, using the keyword "mandible" combined with keywords related to "multislice computed tomography" (MCT) or "cone-beam computed tomography" (CBCT) and keywords related to "skeletal age determination" or "sex determination analysis." MAIN RESULTS: Among the 23 studies included, 11 used MCT and 12 used CBCT to perform forensic assessments. Age determination was the aim of a single study, sex and agedeterminations were the objective of five studies, and the other studies investigated the determination of sex only. Metaanalysis could be performed only for sex determination. CONCLUSIONS: Mandible measurements are useful in sex determination, as the bicondylar and bigonial breadth are larger in males than in females. For the mandible angle, the meta-analysis results confirm sex dimorphism in CBCT scans but not in MCT scans. For age estimation, further studies are needed to prove that the mandible hole is a reliable parameter for age estimation. PROSPERO registration number: CRD42021260967.

The utility of sternum in creating a biological profile: A review and future directions.

This review delves into the forensic utility of the sternum in creating a biological profile, focusing on sex, stature, and age estimation. Emphasizing the sternum's significance in challenging scenarios, the study supports the combined length of the manubrium and sternal body as a crucial indicator in sex and stature estimation. However, it highlights the need for caution in applying findings across diverse populations and questions the reliability of Hyrtl's law. Age estimation, primarily based on morphological changes and ossification ages, is explored, with one study showing promise but requiring further validation. While acknowledging the sternum's advantages, the review underscores potential limitations and the absence of specific studies on ancestry estimation, leaving this aspect open for future research. In conclusion, the review provides a comprehensive overview of the sternum's forensic applications, urging continued research to enhance accuracy and applicability.

No Bones About It: Sex Is Binary.

Anthropologists have led the way in formulating techniques that reveal skeletal differences between males and females. Understanding of physical differences in the pelvis related to childbirth, hormonal impacts on bones, and extensive comparative studies have provided anthropologists with an array of traits and measurements that help them estimate sex using just bones. Forensic anthropologists and bioarcheologists are improving their ability to differentiate males and females by increasing research on a variety of postcranial bones and through the use of molecular data, especially new methods called proteomics, to identify sex in prepubescent juveniles. As remains from more cultures and time periods are studied, sex identification will continue to improve, because skeletal sex differences are in large part biologically determined. Yet, anthropologists have also been at the forefront of arguing that sex lies on a spectrum. Anthropologists who view sex as on a spectrum may deter sex identification progress; from their perspective, an individual of an undetermined sex may just be a nonbinary individual. Anthropologists who consider sex is on a spectrum are coming to this conclusion in part because they are looking for anatomical ideals, mistaking pathology for variation, and confusing independent variables with dependent variables. Nonetheless, anthropologists need to continue to improve sex identification techniques to reconstruct the past accurately, which may reveal less strict sex roles than previously presumed and help with the identification of crime victims. Forensic anthropologists should also increase their efforts to identify whether individuals have undergone medical procedures intended to change one's gender due to the current rise in transitioning individuals.

Sex estimation in the South-East Asian population: A systematic review.

INTRODUCTION: Sex estimation is crucial in forensic anthropology. In situations such as mass disasters, and forensic anthropology cases, sex estimation is a very important initial step in the disaster victim identification process. Literature has acknowledged that sex estimation is population-specific. However, sex estimation standards in South-East Asian populations are limited, leading to the usage of most Thais discriminant function equations on sex estimation by other South-East Asian countries including Malaysia. This systematic review was conducted to summarise the findings of sex estimation studies in South-East Asian countries. MATERIALS AND METHODS: A systematic literature search was performed through the SCOPUS database and Web of Science (WOS) database for relevant studies between 2014 and 2022. All published articles that are related to sex estimation from different types of bone, methods, landmarks, and sample sources (i.e., photographs, dry bones, and CT images) were included in this review. The main inclusion criteria were studies on (i) sex estimation; (ii) in South-East Asian populations; (iii) between the years 2014 and 2022; and (iv) in English. RESULTS: The literature search identified 30 potentially relevant studies, of which 15 publications met all the inclusion criteria. From those research, 13 studies were related to the Thai population and two to the Malaysian population. Only one study was based on morphological traits, while the rest were based on a morphometric approach. CONCLUSION: All studies found that sex estimation is populationspecific. Therefore, further research is recommended to explore more on population-specific sex estimation using different parts of bone.

Estimation of ancestry from cranial measurements based on MDCT data acquired in a Japanese and Western Australian population.

The estimation of ancestry is important not only towards establishing identity but also as a required precursor to facilitating the accurate estimation of other attributes such as sex, age at death, and stature. The present study aims to analyze morphological variation in the crania of Japanese and Western Australian individuals and test predictive models based on machine learning for their potential forensic application. The Japanese and Western Australian samples comprise computed tomography (CT) scans of 230 (111 female; 119 male) and 225 adult individuals (112 female; 113 male), respectively. A total of 18 measurements were calculated, and machine learning methods (random forest modeling, RFM; support vector machine, SVM) were used to classify ancestry. The two-way unisex model achieved an overall accuracy of 93.2% for RFM and 97.1% for SVM, respectively. The four-way sex and ancestry model demonstrated an overall classification accuracy of 84.0% for RFM and 93.0% for SVM. The sex-specific models were most accurate in the female samples (♀ 95.1% for RFM and 100% for SVM; ♂91.4% for RFM and 97.4% for SVM). Our findings suggest that cranial measurements acquired in CT images can be used to accurately classify Japanese and Western Australian individuals into their respective population. This is the first study to assess the feasibility of ancestry estimation using three-dimensional CT images of the skull.

Estimation of sex using dimensions around the metatarsal diaphyseal nutrient foramen: Application of discriminant function analysis and logistic regression models.

Sex estimation equations are population-specific, and a wider use of multiple bones to generate equations will increase the accuracy of sex estimation in forensic settings. The metatarsal bones have been used previously, however the dimensions around the diaphyseal nutrient foramen have not been utilised in sex estimation. The current study aimed to determine the utility of the dimensions around the nutrient foramen of metatarsal bones in estimating sex in the South Africans of European descent (SAED). Five measurements around the nutrient foramen were taken from a total of 876 metatarsal bones (first to fifth) from 186 individual skeletons (99 males, 87 females) obtained from the Raymond A. Dart Modern Skeletal Collection. Measurements subjected to direct and stepwise discriminant function (DFA) and logistic regression (LRA) analyses included total length, distance from proximal end to nutrient foramen, circumference, and mediolateral and dorsoplantar diameters at the level of the nutrient foramen. The original classification accuracies for multivariable functions of the stepwise and direct DFA ranged from 83.1-88.3% to 85.5-88.3%, respectively. The original classification accuracies for multivariable functions of the stepwise and direct LRA ranged from 83.3%-88.7% to 86.2%-88.3%, respectively. The cross-validation classifications showed a drop of 0-2.4% for DFA and 0.2-1.1% for LRA. The width measurements were better predictors of sex than length. The dimensions around the metatarsal bone nutrient foramen exhibit sexual dimorphism in the SAED. The generated DFA and LRA functions produced high average classification accuracies which are useful in sex estimation during forensic human identification.

The influence of age on greater sciatic notch morphology: testing the Walker method in an Australian population.

Sex estimation is an integral aspect of a forensic biological profile. The pelvis, being the most dimorphic part of the skeleton, has been studied in considerable detail relative to morphological and metric variation. However, empirical data on the effect of age on pelvic morphology relative to sex-specific morphological variation is limited, especially in regard to the estimation of skeletal sex. This study assesses whether there are age-related differences in the distribution of the Walker (2005) morphological scores for the greater sciatic notch (GSN) in an Australian population. Three-dimensional volumetric reconstructions derived from multi-detector computed tomography (MDCT) scans of 567 pelves of 258 females and 309 males aged 18 to 96 years were scored following Walker (2005). Differences in score distributions and means by sex and age group were tested using Pearson's chi-squared test and ANOVA, respectively. The accuracy of sex estimates derived from logistic regression equations was explored using leave-one-out cross-validation. Significant differences were found in score distribution and means among age groups in females, but not in males. There was a tendency toward higher scores in older females. The overall sex estimation accuracy was 87.5%. When comparing age groups 18-49 and 70 + years, estimation accuracy decreased in females (99% vs. 91%), while the opposite was found for males (79% vs. 87%). These findings suggest that age affects GSN morphology. Higher mean scores in older females imply that, on average, the GSN becomes narrower with increasing age. It is thus recommended due consideration of estimated age when assessing sex based on the GSN in unidentified human remains.

Accuracy of sex estimation by morphometric evaluation of foramen magnum using computed tomography - a systematic review and meta-analysis.

The objective of this study is to determine whether the morphometric evaluation of the foramen magnum using computed tomography can be used as an accurate tool in estimating the sex of an individual. An extensive search of the databases, PubMed, ProQuest, Google Scholar, and Scopus, was carried out to procure articles that fulfilled the inclusion criteria. The AQUA tool was used to assess the quality of the included studies. A random effects model was used for the meta-analysis of the eligible studies using the STATA software, version 16, 2019 at 95% CI and p ≤ 0.05. Eleven eligible articles that measured the transverse and sagittal diameters of the foramen magnum using computed tomography were included in this study. The sagittal diameter of the foramen magnum was greater than the transverse diameter, and both the diameters were greater in males than in females. Meta-analysis revealed that both transverse and sagittal diameters were more reliable for male sex estimation. Since there is a dimensional variation between the male and female foramen magnum, it can be used for initial sex identification and also as an auxiliary to other advanced methods of sex estimation.

Demonstrating the empirical effect of population specificity of anthropological standards in a contemporary Australian population.

The ability to differentiate individuals based on their biological sex is essential for the creation of an accurate anthropological assessment; it is therefore crucial that the standards that facilitate this are likewise accurate. Given the relative paucity of population-specific anthropological standards formulated specifically for application in the contemporary Australian population, forensic anthropological assessments have historically relied on the application of established methods developed using population geographically and/or temporally disparate. The aim of the present paper is, therefore, to assess the accuracy and reliability of established cranial sex estimation methods, developed from geographically distinct populations, as applied to the contemporary Australian population. Comparison between the original stated accuracy and sex bias values (where applicable) and those achieved after application to the Australian population provides insight into the importance of having anthropological standards optimised for application in specific jurisdictions. The sample analysed comprised computed tomographic (CT) cranial scans of 771 (385 female and 386 male) individuals collected from five Australian states/territories. Cranial CT scans were visualised as three-dimensional volume-rendered reconstructions using OsiriX®. On each cranium, 76 cranial landmarks were acquired, and 36 linear inter-landmark measurements were calculated using MorphDB. A total of 35 predictive models taken from Giles and Elliot (1963), Iscan et al. (1995), Ogawa et al. (2013), Steyn and Iscan (1998) and Kranioti et al. (2008) were tested. Application to the Australian population resulted in an average decrease in accuracy of 21.2%, with an associated sex bias range between - 64.0 and 99.7% (average sex bias value of 29.6%), relative to the original studies. The present investigation has highlighted the inherent inaccuracies of applying models derived from geographically and/or temporally disparate populations. It is, therefore, imperative that statistical models developed from a population consistent with the decedent be used for the estimation of sex in forensic casework.

Morphometric evaluation of the orbital region for sex determination in a Saudi Arabian population using 3DCT images.

In forensic anthropology, the analysis of variations in the orbitometric features plays a crucial role in identifying the sex of a skull detached from its skeleton. Therefore, it is essential to create population-specific values to maximize the accuracy rate of sex estimation. The objective of this study was to evaluate the orbital region morphometrically for sex determination in a Saudi Arabian population using CT scan images. This study included 456 CT images (228 males and 228 females; age range, 18-58 years). Six orbital measurements and the orbital index of both sides were evaluated to determine sexual dimorphism and laterality using an independent t-test. Sex was estimated using discriminant function analysis. Based on the orbital index, the orbit was classified into megasemes, mesosemes, and microsemes. All the measurements were significantly greater in males than females, but the orbital index showed no significant sexual dimorphism. No significant asymmetry was found in all orbital dimensions. The univariate discriminant function of the orbital measurements showed an accuracy rate between 83.8 and 70%. The multivariate analysis classified the orbital dimensions into male (93%) and female (92.1%) to the highest level of accuracy. In Saudis, the megaseme category was the most prevalent form of orbit. The right orbit height (83.8%), left orbit height (80.7%), right orbit width (79.4%), and left orbit height (79.4%) were the most reliable variables that could be used in sex determination. According to multivariate analysis, the overall accuracy rate for determining sex was 92.1%. While the present study data may not be used alone for sexing a complete skull, there must be various occasions in which this new standard will contribute to determining sex in forensic contexts.

Testing the discrepancy between physical and virtual linear measurements.

Virtual calculations of bone morphology are increasingly becoming the golden standard in anthropological sciences, gradually replacing the performance of direct physical measurements. Nevertheless, the potential discrepancy between the two approaches is rarely addressed. Here, we address this question focusing on the second thoracic vertebrae of 24 well-preserved individuals from the skeletal collection of the Forensic Anthropology Unit of Medical School at the National and Kapodistrian University of Athens, Greece. Following traditional osteometric methods, a series of measurements were taken on the vertebral body, both directly (using a digital caliper) as well as on high-resolution 3D surface models. The arithmetic results of the two measuring techniques were then compared through a number of statistical analyses evaluating inter-method precision (Bland-Altman plots, TEM, %TEM and Wilcoxon test). Moreover, the values obtained from each approach were used to develop discriminant function equations for sex determination to evaluate if both approaches provide the same assessment. Both intraobserver and interobserver tests were performed. Although most statistical analyses showed a significant difference between the two measuring techniques, the discriminant function equations for sex determination provided the same assessment. Overall, the results of this experiment support the use of virtual linear measurements, also suggesting that a refinement of digital measuring protocols could improve their level of agreement with traditional direct osteometry.

Comparing morphological (os coxae) and metric (long bone length) sex estimation methods in archaeological collections.

Objectives: The aim of this study is to evaluate the internal consistency of sex estimation using metric (long bone length) and morphological (os coxae) methodologies from different bones and across different archaeological populations from different regions. Materials and Methods: Sex was estimated using characteristics of the pelvis and compared with sex estimations using long bone length. Portuguese (659 females; 906 males) and English (141 females; 277 males) archaeological collections were analysed in this study. A set of long bone length functions were developed using one of the archaeological collections (531 females; 600 males) and its coincidence with sex estimated from the pelvis was compared to the coincidence between the pelvis and long bone length sex estimations using functions developed from contemporary collections. Intra- and inter-observer errors were calculated, as well as the sexual dimorphism index for each bone and osteological collection. Results: The accuracy of the developed functions and the other methods tested is highly variable, ranging between 25 and 100%. The accuracy of the standard forensic methods varied between collections and analysed bones. Discussion: This study reinforces that long bone length is highly population-specific, even between samples of close chronology and geography. Metric methods are good options to strengthen the sex estimations, but they need to be carefully chosen and always report the estimated probability of being male or female in either forensic or archaeological analysis.

Sex estimation of frontal sinus volume from computed tomography scans in a Western Australian adult population.

With the increasing use of radiological three-dimensional imaging, different metric and morphological aspects of the frontal sinuses (FS) have been examined relative to their potential to aid human identification, including sex estimation. The aim of this study is to assess the validity of the metric analysis of the FS volume for estimating sex in a Western Australian (WA) adult population, following the Michel et al. (2015) method. The right, left and total frontal sinus volume (TFSV) from 99 computed tomography scans (47 males and 52 females) of WA individuals aged 18-40 years were three-dimensionally reconstructed using OsiriX® and their volumes acquired in mm3. Sexual dimorphism in the TFSV was tested, and the accuracy of the Michel et al. (2015) formulae was calculated. Population-specific regression equations were also produced. There was a significant difference between the mean TFSV in males and females. The classification accuracy derived from the Michel et al. (2015) formulae was 59.6%. The WA-specific logistic regression analysis yielded an accuracy of 57.2%. The low accuracy rates preclude the use of the sex estimation method in the WA population, but the volume analysis confirmed the individual variability of the frontal sinuses, which may be useful for personal identification.

Sex Estimation From Measurements of the Mastoid Triangle and Volume of the Mastoid Air Cell System Using Classical and Machine Learning Methods: A Comparative Analysis.

ABSTRACT: Previous studies on the sexual dimorphism of the mastoid triangle have typically focused on linear and area measurements. No studies in the literature have used mastoid air cell system volume measurements for direct anthropological or forensic sex determination. The aims of this study were to investigate the applicability of mastoid air cell system volume measurements and mastoid triangle measurements separately and combined for sex estimation, and to determine the accuracy of sex estimation rates using machine learning algorithms and discriminant function analysis of these data. On 200 computed tomography images, the distances constituting the edges of the mastoid triangle were measured, and the area was calculated using these measurements. A region-growing algorithm was used to determine the volume of the mastoid air cell system. The univariate sex determination accuracy was calculated for all parameters. Stepwise discriminant function analysis was performed for sex estimation. Multiple machine learning methods have also been used. All measurements of the mastoid triangle and volumes of the mastoid air cell system were higher in males than in females. The accurate sex estimation rate was determined to be 79.5% using stepwise discriminant function analysis and 88.5% using machine learning methods.

DSP2 for sex determination of miscegenated contemporary hip bones.

The bones of the human pelvis are used in sexual diagnosis generating a high level of accuracy for this type of identification. Morphological and/or morphometric methods are used in the identification of sex. Sexual dimorphism may be affected by ethnic differences in the population. One of the methods for determining sex using hip bone is the 'Diagnose Sexuelle Probabiliste (DSP)' or Probabilistic Sexual Diagnosis (DSP) method. The method presents a new version (Probabilistic Sexual Diagnosis v.2-DSP2) more advisable to be used because it has a more up-to-date database. The objective of this study is to investigate the applicability of the DSP2 method in a population in the Northeast region of Brazil. We used 128 hip bones, 50 female and 78 males, aged between 17 and 101 years, belonging to the Laboratory of Human Identification and Forensic Osteology of the University Federal Government of Pernambuco. The research was conducted between 2019 and 2020 and approved by the Research Ethics Committee of the Federal University of Pernambuco no. 43228015.0.0000.5208. The probability equal to or greater than 0.95 was used as the limit for the determination of sex, and the results were compared with the actual sex of each bone. In the Brazilian collection study, it was observed that the percentage of sex estimation provided by the DSP2 tool using all reference samples was 71.09%, and accuracy was 64.06%. In the analysis of the gender estimate, 82.0% and 78% were obtained for females and males, respectively. Regarding accuracy, it was 64.10% and 55.13% for females and males, respectively. In the contemporary osteological collection of the Northeast region of Brazil, which presents immigrant peoples, we obtained a high index of assertiveness in the DSP2 method. The study concluded that the DSP2 method is important for determining the sex of human skeletons in a miscegenated population.

Sex determination using the clavicle by deep learning in a Thai population.

Determining sex is a critical process in estimating biological profiles from skeletal remains. The clavicle is interesting in studying sex determination because it is durable to the environment, slow to decay, challenging to destroy, making the clavicle useful in autopsies and identification which can then lead to verification. The goal of this study was to use deep learning in determining sex from clavicles within the Thai population and obtain the accuracies for the validation set using a convolutional neural network (GoogLeNet). A total of 200 pairs of clavicles were obtained from 200 Thai persons (100 males and 100 females) as part of a training group. For the deep learning approach, the clavicle was photographed, and each clavicle image was submitted to the training model for sex determination. Training groups of 200 samples were made. Images of the same size were input into the training model. The percentage of the validation set accuracy was calculated from the MATLAB program. GoogLeNet was the best training model and get the result of validation set accuracy. The results of this study found accuracies for a validation set with the highest overall right lateral view of the clavicle with an accuracy of 95%. Accuracy from the validation set of each view of the clavicle can demonstrate the forensic value of sex determination. A deep learning approach with clavicles can determine the sex and is simple to utilize for forensic anthropology professionals.

Sex estimation from the hyoid bone measurements in an adult Eastern Turkish population using 3D CT images, discriminant function analysis, support vector machines, and artificial neural networks☆.

The hyoid bone is one of the bones in the human body that shows sexual dimorphism. The anthropological and anthropometric characteristics that determine sexual dimorphism are influenced by demographic differences. The aim of this study was to investigate the rate of sexual dimorphism of the hyoid bone in the adult Eastern Turkish population from the examination of the 3D computed tomography images of 240 patients, using discriminant function analysis (DFA), support vector machines (SVM), and artificial neural networks (ANN). These evaluations were based on eight hyoid measurements that have been frequently used in previous CT studies. The results showed that all eight measurements were higher in males than in females (p = 0.000). It was determined that sex could be estimated accurately at up to 93.3 % using DFA, 93.8 % using SVM and 95.4 % using ANN. The maximum accuracy rate achieved to 94.2 % in males using SVM, and 95.8 % in females using ANN. These high rates of sexual dimorphism found using DFA, SVM, and ANN in this study indicate that characteristics of the hyoid bone can be utilized to determine sex in the Eastern Turkish population.

How reliable is the application of the sex classifier based on exocranial surface (Musilová et al., 2016) for geographically and temporally distant skull series.

Sex estimation is one of the crucial trends in cases of findings of unknown skeletal remains in forensics and bioarchaeology. The changing nature of sexual dimorphism (population specificity, secular trend, other external and internal factors influence) brings challenges to developing new methods; and there are new aims to be independent of these changes such, as the method by Musilová et al. (2016). These methods need to be evaluated on different datasets to determine if they are truly reliable among populations from different places and times, in the case of bioarchaeology. This study assessed the application of the aforementioned method on non-European contemporary and ancient populations to identify the reliability of the method on this separate dataset. The study sample consisted of 96 CT scans of skulls from contemporary Egyptians and 54 3D models of skulls from the Egyptian Old Kingdom Period (2700-2180 BC). The classifier method, previously tested on both Czech and French populations, yielded high accuracies (over 90 %) for sex estimation. For the contemporary Egyptian skull sample, the classifier was able to determine males versus females with an 89.59 % accuracy rate and an AUC value (area under the curve - a measure of the combined specificity and sensitivity of the test) of 0.99; this proves that the classifier is reliable even with a lower degree of accuracy. Conversely, the Old Kingdom Period sample yielded a lower level of accuracy at around 70 % (61.11 %, precisely), although with an AUC value of 0.92, the result is not considered reliable.

Sex determination using mandibular ramus flexure in South Indian population - A retrospective study.

Sex determination or sex estimation from a single or fragment of bone is always difficult in the absence of other bones from the same individual. The current study was an attempt to estimate the sex of an individual from the posterior ramus of mandible or the mandibular ramus flexure. A retrospective study was conducted using orthopantomographs (OPGs) of 200 males and 200 females between the age group of 20 - 70 years. Each radiographic image was examined for the presence of a flexure or notching on the posterior border of the ramus in relation to occlusal plane as the method followed by Loth & Henneberg 1996.The study resulted in samples that were correctly classified as females 59.5% and males 57.5 %. The overall correct sex estimation was achieved in 58.5% of the cases. The predictive accuracy or assessment was higher for females compared to males. Consequently, the posterior ramus of mandible or mandibular ramus flexure can be considered as supplementary rather than a definitive means of sex determination. Hence, it is preferable to include as many parameters as possible to attain optimal accuracy.