Data mining for sex estimation based on cranial measurements

Developing a fully applicable machine learning (ML) based sex classification model using linear cranial dimensions

Recent advances in artificial intelligence (AI) and machine learning (ML) applications have elevated accomplishments in various scientific fields, primarily those that benefit the economy and society. Contemporary threats, such as armed conflicts, natural and man-made disasters, and illegal immigration, often require fast and innovative but reliable identification aids, in which forensic anthropology has a significant role. However, forensic anthropology has not yet exploited new scientific advances but instead relies on traditionally used methods. The rare studies that employed AI and ML in developing standards for sex and age estimation did not go beyond the conceptual solutions and were not applied to real cases. In this study, on the example of Croatian populations' cranial dimensions, we demonstrated the methodology of developing sex classification models using ML in conjunction with field knowledge, resulting in sex estimation accuracy of more than 95%. To illustrate the necessity of applying scientific results, we developed a web app, CroCrania ( https://crocrania.onrender.com ), that can be used for sex estimation and method validation.

Sex estimation techniques based on skulls in forensic anthropology: A scoping review

BACKGROUND

Sex estimation is an essential topic in the field of individual identification in forensic anthropology. Recent studies have investigated a growing range of techniques for estimating sex from human skulls.

OBJECTIVES

This study aims to provide a scoping review of the literature on techniques used in skull-based sex estimation, serving as a valuable reference for researchers.

SOURCES OF EVIDENCE

The literature search was performed using PubMed, Scopus, and Web of Science from January 2020 to February 2024.

ELIGIBILITY CRITERIA

Eligible studies have investigated issues of interest to forensic anthropology about sex estimation using skull samples.

CHARTING METHODS

A total of 73 studies met the inclusion criteria and were categorized and analyzed based on the anatomic sites, modalities, trait types, and models. Their accuracy in estimating sex was subsequently examined, and the results were charted.

RESULTS AND CONCLUSIONS

Our review highlights that the 3D medical imaging technique has enhanced the efficiency and stability of skull-based sex estimation. It is anticipated that advancements in 3D imaging and computer vision techniques will facilitate further breakthroughs in this field of research.

Enhancing Sex Estimation Accuracy with Cranial Angle Measurements and Machine Learning

The development of current sexing methods largely depends on the use of adequate sources of data and adjustable classification techniques. Most sex estimation methods have been based on linear measurements, while the angles have been largely ignored, potentially leading to the loss of valuable information for sex discrimination. This study aims to evaluate the usefulness of cranial angles for sex estimation and to differentiate the most dimorphic ones by training machine learning algorithms. Computed tomography images of 154 males and 180 females were used to derive data of 36 cranial angles. The classification models were created by support vector machines, naïve Bayes, logistic regression, and the rule-induction algorithm CN2. A series of cranial angle subsets was arranged by an attribute selection scheme. The algorithms achieved the highest accuracy on subsets of cranial angles, most of which correspond to well-known features for sex discrimination. Angles characterizing the lower forehead and upper midface were included in the best-performing models of all algorithms. The accuracy results showed the considerable classification potential of the cranial angles. The study demonstrates the value of the cranial angles as sex indicators and the possibility to enhance the sex estimation accuracy by using them.

Artificial Intelligence in Forensic Sciences: A Systematic Review of Past and Current Applications and Future Perspectives

The aim of this study is to review the available knowledge concerning the use of artificial Intelligence (AI) in general in different areas of Forensic Sciences from human identification to postmortem interval estimation and the estimation of different causes of death. This paper aims to emphasize the different uses of AI, especially in Forensic Medicine, and elucidate its technical part. This will be achieved through an explanation of different technologies that have been so far employed and through new ideas that may contribute as a first step to the adoption of new practices and to the development of new technologies. A systematic literature search was performed in accordance with the Preferred Reported Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines in the PubMed Database and Cochrane Central Library. Neither time nor regional constrictions were adopted, and all the included papers were written in English. Terms used were MACHINE AND LEARNING AND FORENSIC AND PATHOLOGY and ARTIFICIAL AND INTELIGENCE AND FORENSIC AND PATHOLOGY. Quality control was performed using the Joanna Briggs Institute critical appraisal tools. A search of 224 articles was performed. Seven more articles were extracted from the references of the initial selection. After excluding all non-relevant articles, the remaining 45 articles were thoroughly reviewed through the whole text. A final number of 33 papers were identified as relevant to the subject, in accordance with the criteria previously established. It must be clear that AI is not meant to replace forensic experts but to assist them in their everyday work life.

Evaluation of the Anatomical and Radiological Morphometry of Optic Nerve and Cranium in Healthy Individuals

This paper determined the morphometric measurements' reference values and relationship of the optic nerve and cranium in Turkish healthy individuals according to age and sex. Five hundred fifty-nine (280 females and 279 males) patients aged from 2 to 90 years were included in this study. The measurements were taken from patients having brain magnetic resonance images in sagittal, axial, and coronal sections in the radiology department. Eyeball transverse diameter, optic nerve sheath thickness (ONST), optic chiasm length, optic chiasm width, and cranium morphometric measurements of all individuals who participated in the study were taken. Except for the width of the optic chiasm, all measurements showed significant differences between the sexes (P < 0.05). In contrast, all measurement values were higher in males than females, except for the clival angle. According to the result of Pearson correlation analysis, in which the existence of a relationship between ONST and craniometric measurements was evaluated, a low but significant correlation was found between ONST and craniometric measurements (r < 0.4; P < 0.05). In the post hoc test performed to compare the decades, it was seen that the most significant changes in our measurements were in the 2 to 10 age range and the measurement values decreased in old age. We think that revealing the age and sex-related changes in the optic nerve and cranium morphometry of our population anatomically and radiologically will be an important source in terms of creating reference values for our population.

Comparison of decision tree and naïve Bayes algorithms in detecting trace residue of gasoline based on gas chromatography-mass spectrometry data

Fire debris analysis aims to detect and identify any ignitable liquid residues in burnt residues collected at a fire scene. Typically, the burnt residues are analysed using gas chromatography-mass spectrometry (GC-MS) and are manually interpreted. The interpretation process can be laborious due to the complexity and high dimensionality of the GC-MS data. Therefore, this study aims to compare the potential of classification and regression tree (CART) and naïve Bayes (NB) algorithms in analysing the pixel-level GC-MS data of fire debris. The data comprise 14 positive (i.e. fire debris with traces of gasoline) and 24 negative (i.e. fire debris without traces of gasoline) samples. The differences between the positive and negative samples were first inspected based on the mean chromatograms and scores plots of the principal component analysis technique. Then, CART and NB algorithms were independently applied to the GC-MS data. Stratified random resampling was applied to prepare three sets of 200 pairs of training and testing samples (i.e. split ratio of 7:3, 8:2, and 9:1) for estimating the prediction accuracies. Although both the positive and negative samples were hardly differentiated based on the mean chromatograms and scores plots of principal component analysis, the respective NB and CART predictive models produced satisfactory performances with the normalized GC-MS data, i.e. majority achieved prediction accuracy >70%. NB consistently outperformed CART based on the prediction accuracies of testing samples and the corresponding risk of overfitting except when evaluated using only 10% of samples. The accuracy of CART was found to be inversely proportional to the number of testing samples; meanwhile, NB demonstrated rather consistent performances across the three split ratios. In conclusion, NB seems to be much better than CART based on the robustness against the number of testing samples and the consistent lower risk of overfitting.

A Geometric Morphometric Study on Sexual Dimorphism in Viscerocranium

The level of sexual dimorphism manifested by human bones is an important factor for development of effective sex estimation methods. The aim of the study was to investigate the sexual dimorphism in the size and shape of the viscerocranium using geometric morphometric techniques. It also aimed to explore the sex differences in distinct viscerocranial regions and to establish the most dimorphic region with regard to size and shape. Computed tomography images of 156 males and 184 females were used in the study. Three-dimensional coordinates of 31 landmarks were acquired. Five landmark configurations were constructed from the viscerocranium and its orbital, nasal, maxillary, and zygomatic region. Generalized Procrustes superimposition, principal component analysis, and discriminant analysis were applied to each configuration. The significance of the sex differences in size and shape was assessed and significant differences were found in all configurations. The highest accuracy was obtained from both shape and size of the whole viscerocranium. Based on size only, the highest accuracy was achieved by the nasal region. The accuracy based on shape was generally low for all configurations, but the highest result was attained by the orbital region. Hence, size is a better sex discriminator than shape.

Sexual dimorphism in shape and size of the neurocranium

Sex identification is a primary step in forensic analysis of skeletal remains. The accuracy of sex estimation methods greatly depends on the sexual dimorphism manifested by the target anatomical region. The study aims to evaluate the sexual dimorphism in shape and size of the neurocranium and to compare the potential of shape and size of different cranial regions to classify correctly the male and female crania. The study was carried out on computed tomography images of 373 Bulgarian adults (161 males and 212 females). Three-dimensional coordinates of 32 landmarks were acquired. The landmarks were arranged in 4 configurations: neurocranium, frontal bone, parietotemporal region, and occipital bone. For each configuration, the presence of significant sex differences in shape and size was tested. Principal component analysis (PCA) was applied to explore the shape variation. The classification power of size and shape was tested using discriminant analysis and k-means clustering. The neurocranium shows significant sex differences in shape and size. The parietotemporal region is the most dimorphic neurocranial part in size and the frontal bone is the most differing one in shape. The size of the parietotemporal region and frontal bone classifies correctly more than 80% of the crania. The discrimination ability based on shape is rather low as the highest values of about 70% are obtained for the frontal and occipital bone. The PCA plots show large overlapping of the male and female crania. It can be inferred that the sex-specific size differences in the neurocranium are more important than the shape differences.

Estimation of sex from computed tomography images of skull measurements in an adult Turkish population

BACKGROUND

Nowadays, data on the anthropometric measurements of populations is needed in many areas, especially forensic and legal. Using various methods, researchers obtain various data such as race, sex, and age, and thus provide identification of the material used. Morphological or metric methods are often used for identification.

PURPOSE

To evaluate the usefulness of the results of skull measurements using computed tomography (CT) to determine sex in a Turkish population.

MATERIAL AND METHODS

We analyzed 300 male and 300 female CT images of Turkish individuals with an age range of 21-50 years. Maximum cranial length, maximum cranial breadth, bimastoid diameter, bizygomatic diameter, and bigonial breadth were measured by CT tomography. All data were subjected to discriminant function analyses for estimating sex. Intra-observer and inter-observer variances of the measurements were examined using intraclass correlation coefficient analysis.

RESULTS

Discriminant function analysis indicated that there was a significant difference between male and female with 88% accuracy. Discriminant function for estimation of sex was obtained with satisfactory accuracy rates for the parameters used.

CONCLUSION

This study confirms that skull measurements show sexual dimorphism in the Turkish population, and also suggests that it may be useful to use CT to assess skull anthropometric measurements.

Sex classification of first molar teeth in cone beam computed tomography images using data mining

OBJECTIVE

The teeth have been used as a supplementary tool for sex differentiation as they are resistant to post-mortem degradation. The present study aimed to develop a new novel informatics framework for predicting sex from linear tooth dimension measurements achieved from cone beam computed tomography (CBCT) images.

METHOD AND MATERIALS

A clinical workflow using different machine learning methods was employed to predict the sex in the present study. The CBCT images of 485 subjects (245 men and 240 women) were evaluated for sex differentiation. Nine parameters were measured in both buccolingual and mesiodistal aspects of the teeth. We applied our dataset to Naïve Bayesian (NB), Random Forest (RF), and Support Vector Machine (SVM) as classifiers for prediction. Genetic feature selection was used to discover real features associated with sex classification.

RESULTS

The 10-fold cross-validation results indicated that NB had higher accuracy than SVM and RF for sex classification. The genetic algorithm (GA) indicated that the model could fit the data without using the enamel thickness and pulp height. The average classification accuracy of our clinical workflow was 92.31 %.

CONCLUSION

The results showed that NB was the best method for sex classification. The application of the first molar teeth in sex prediction indicated an acceptable level of sexual classification. Therefore, these odontometric parameters can be applied as an additional tool for sex determination in forensic anthropology.

Machine learning approaches for sex estimation using cranial measurements

The aim of the present study is to apply support vector machines (SVM) and artificial neural network (ANN) as sex classifiers and to generate useful classification models for sex estimation based on cranial measurements. Besides, the performance of the generated sub-symbolic machine learning models is compared with models developed through logistic regression (LR). The study was carried out on computed tomography images of 393 Bulgarian adults (169 males and 224 females). The three-dimensional coordinates of 47 landmarks were acquired and used for calculation of the cranial measurements. A total of 64 measurements (linear distances, angles, triangle areas and heights) and 22 indices were calculated. Two datasets were assembled including the linear measurements only and all measurements and index, respectively. An additional third dataset comprising all possible interlandmark distances between the landmarks was constructed. Two machine learning algorithms-SVM and ANN and a traditional statistical analysis LR-were applied to generate models for sex estimation. In addition, two advanced attribute selection techniques (Weka BestFirst and Weka GeneticSearch) were used. The classification accuracy of the models was evaluated by means of 10 × 10-fold cross-validation procedure. All three methods achieved accuracy results higher than 95%. The best accuracy (96.1 ± 0.5%) was obtained by SVM and it was statistically significantly higher than the best results achieved by ANN and LR. SVM and ANN reached higher accuracy by training on the full datasets than the selection datasets, except for the sample described by the interlandmark distances, where the reduction of attributes by the GeneticSearch algorithm improved the accuracy.