Age Estimation Studies Research Articles

A review of artificial intelligence-based brain age estimation and its applications for related diseases.

The study of brain age has emerged over the past decade, aiming to estimate a person's age based on brain imaging scans. Ideally, predicted brain age should match chronological age in healthy individuals. However, brain structure and function change in the presence of brain-related diseases. Consequently, brain age also changes in affected individuals, making the brain age gap (BAG)-the difference between brain age and chronological age-a potential biomarker for brain health, early screening, and identifying age-related cognitive decline and disorders. With the recent successes of artificial intelligence in healthcare, it is essential to track the latest advancements and highlight promising directions. This review paper presents recent machine learning techniques used in brain age estimation (BAE) studies. Typically, BAE models involve developing a machine learning regression model to capture age-related variations in brain structure from imaging scans of healthy individuals and automatically predict brain age for new subjects. The process also involves estimating BAG as a measure of brain health. While we discuss recent clinical applications of BAE methods, we also review studies of biological age that can be integrated into BAE research. Finally, we point out the current limitations of BAE's studies.

A Pilot Study of Age Estimation and Cause of Death: Insights into Skeletal Aging

Background/Objectives: Forensic anthropological age estimations are often limited by a lack of diversity in reference samples, imprecision, and, for certain populations, inaccuracy. This study aims to explore the relationship between health, as indicated by cause of death, and skeletal age estimation, with the goal of determining whether including health information can improve accuracy and precision in age estimation. Methods: Skeletal age data were collected from the Maxwell Museum Documented Skeletal Collection using the Lovejoy et al. method for the auricular surface and the Suchey-Brooks method for the pubic symphysis. All individuals had a known cause of death, which was categorized into two broad groups: disease-related and trauma-related. Cause of death category served as a proxy for health status. Results: Individuals who died from disease-related causes often fell within the upper end of the age ranges for both the auricular surface and pubic symphysis methods. In contrast, those who died from trauma-related causes tended to fall within the lower end of these age ranges. Conclusions: These results indicate that incorporating factors such as health into existing forensic age estimation methods could enhance the precision of age estimates, particularly by addressing the influence of environmental and lifestyle factors on skeletal aging.

Effect of impaction on third molar development and age estimation – A study in a female black South African population

The impact of impaction on the development of third molars remains a subject of debate within the scientific literature, given the lack of consensus. Simultaneously, there has been a call for dental age estimation studies to consider population-specific factors. This research was conducted with the objective of examining the influence of impaction on the formation of third molars in a cohort of female individuals of black South African descent. The study population comprised 428 panoramic radiographs, focusing on females within the age range of 15 to 23.9 years. Within this sample, mandibular third molars were categorized based on their positioning into two groups: non-impacted and impacted. Dental development stages were assessed and classified according to Demirjian’s 8-level staging system. Descriptive statistics were performed. The outcomes of the independent t-test revealed statistically significant differences in developmental stages, specifically stage G for tooth #38 and stage F for tooth #48, suggesting that impaction had an impact on dental development, albeit not consistently across all developmental stages. Nonetheless, it's noteworthy that the minimum and mean ages across all developmental stages were higher among impacted teeth. In summary, our findings support the conclusion that mineralization of impacted mandibular third molars in South African female subjects proceeds at a slower pace compared to their non-impacted counterparts. Consequently, when estimating dental age in the context of South African females, it is advisable to prioritize non-impacted third molars whenever feasible.

Dental color measurement to estimate age in adults: a systematic review and meta-analysis.

Age estimation is a major challenge in anthropology and forensic odontology laboratories, as well as in judicial settings, as one of the tools used in human identification. The aim of this study was to evaluate the usefulness of age estimation methods based on the accurate measurement of tooth color changes. A systematic review was carried out following the recommendations of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses and in compliance with Cochrane criteria recommendations (PROSPERO registration number CRD 42022343371). An electronic search was performed in the following databases: Pubmed, Web of Science, Medline, Current Contents Connect, SciELO, KCI-Korean Journal Database, Derwent Innovations Index and Russian Citation Index. The search strategy yielded a total of 18 articles. A randomized meta-analysis model of the results for the CIE L*a*b* color variables stratified by age (less than 30 years, 30-60 years, 60 years and older) was performed with 9 of the 18 studies included in this systematic review. According to our results, sex and location of color measurement are the most influential factors in color estimation. All studies were carried out in healthy anterior teeth by spectrophotometry as the most commonly used method for color measurement, with CIE L*a*b* being the most commonly analyzed parameters. Studies based on age as a dependent variable showed R2 values between 0.28 and 0.56, being higher in ex vivo teeth. Studies based on age as an independent variable showed R2 values ranging from 0.10 to 0.48. The random model showed high heterogeneity for the L*, a* and b* parameters in all age groups, which is explained by discrepancies in age range and non-standardized conditions for color measurement. This systematic review highlights the need to protocolize age estimation studies that measure tooth color, in order to apply this method in different forensic settings.

Dental Age Estimation Methods Tested in a Sample of the Pakistani Population: Cross-Sectional Study

Forensic dentistry is still an emerging field in Pakistan. The lack of scientific literature on the topic may lead to difficulties in situations where age estimation has a significant part such as in criminal and civil litigation. In mass disasters such as earthquakes and accidents, the correct investigation of the chronological age can be less troublesome if population-specific evidence is available. This is the rationale that justifies dedicated dental age estimation studies. This cross-sectional study aimed to test the time efficiency, validity and applicability of four dental age estimation methods: two invasive (Bang and Ramm and Lamendin) and two non-invasive (Kvaal and Cameriere) in an adult Pakistani population. A total of 37 teeth collected from a dental hospital in Islamabad, Pakistan, were used. Teeth included the central and lateral incisors, canines, and first and second premolars of males and females. Results were calculated using a Microsoft Office 2007 excel spreadsheet. Overall, Kvaal’s method mean absolute error between chronological and estimated ages (MAE: 12.33) showed the highest variation and Bang and Ramm showed more accurate results in comparison with other methods (MAE: 4.80). It was both time-efficient and practical to use. It can be stated that these were preliminary cross-sectional outcomes and that studies with larger samples are necessary.

The applications of MicroCT in studying age-related tooth morphological change and dental age estimation: A scoping review.

Conventional dental age estimation relies on destructive methods such as sectioning and staining, which are unpreferable when the tooth is required for evidential or archeological preservation. MicroCT is a non-destructive, high-resolution imaging technique that allows for accurate morphometrical measurement. Although microCT technology has been applied in a variety of dental studies, studies focusing on dental age-related change and dental age estimation based on microCT imaging remain lacking. Based on the question: "How has microCT technology been applied in studying human age-related tooth morphological change and dental age estimation studies?", the authors conducted a scoping review in accordance with the Arksey and O'Malley (2005) and the PRISMA-ScR guidelines. A literature search using five major scientific databases identified 452 articles, with 11 full-text articles being eligible to be included in the scoping review. Furthermore, 6 out of the 11 studies performed dental age estimation modeling. An overview of the parameters used in the selected articles revealed a variety of tooth characteristics, such as pulp cavity to whole tooth volume ratio, secondary dentin, as well as the diameter of root canal orifice. The findings of this scoping review highlight the extent microCT is used in studying dental age-related changes, as well as the effectiveness of microCT in dental age estimation studies. This review serves as a guide for future forensic odontology age estimation studies.

Root Dentin Translucency based Dental Age Estimation in Adults: A Systematic Review

Background: In Forensic practice and research, the Gustafson technique is the most popular dental age estimation method that uses six variables, among which Root Dentin Translucency (RDT) is considered to be the best single parameter for dental age estimation as it is the least affected by environmental and pathological factors. Dental age estimation by RDT has been tested on different geographic groups in order to determine its applicability and it has been found that there was an under/overestimation of the age of the subjects in different populations. No systematic review of these studies has yet been published to check the reliability and accuracy of this novel method in estimating chronological age. Objective: To assess the accuracy and reliability of RDT-based dental age estimation in different academic and forensic scenarios by qualitatively summarising the results of RDT-based dental age estimation studies in diverse population samples. Evidence Review: Studies were searched in the Medline, Embase, Directory of open access journals, Cochrane library and Google Scholar databases up to December 2019 with previously defined inclusion and exclusion criteria. The outcome of interest was the difference between chronological age and the age estimated from RDT. Results and Conclusion: A total of 1754 subjects from 16 published studies were included in the final review. Our findings proved that the RDT method tends to overestimate chronological age for both sexes in most of the study population. The overestimated dental age ranges from 2.24 to 15.1 years.

Age estimation through facial images using Deep CNN Pretrained Model and Particle Swarm Optimization

There has been a lot of recent study on age estimates utilizing different optimization techniques, architecture models, and diverse strategies with some variations. However, accuracy improvement in age estimation studies remains a challenge due to the inability of traditional approaches to effectively capture complex facial features and variations. Therefore, this study investigates the usage of Particle Swarm Optimization in Deep CNN models to improve accuracy. The focus of the study is on exploring different feature extractors for the age estimation task, utilizing pre-trained CNN models such as VGG16, VGG19, ResNet50, and Xception. The proposed approach utilizes PSO to optimize the hyperparameters of a custom output layer for age detection in regression. The PSO algorithm searches for the optimal combination of model hyperparameters that minimize the age estimation error. This study shows that fine-tuning a model can lead to improvements in its performance, with the VGG19 model achieving the best performance after fine-tuning. Additionally, the PSO process was able to find sets of hyperparameters that were on par or even better than the initial hyperparameters. The best result can be seen in VGG19 architecture with loss of 86.181, MAE of 6.693, and MAPE of 38.462. Out of the twelve experiments conducted, it was observed that the utilization of Particle Swarm Optimization (PSO) offered distinct advantages in terms of achieving better results for age estimation. However, it is important to note that the execution time for these experiments was considerably longer when employing PSO.

Computed tomographic age estimation from the pubic symphysis using the Suchey-Brooks method: A Systematic Review and Meta-analysis

Forensic age estimation is routinely applied in investigations involving identification of individuals. Over the past century a myriad of methods have been devised for age estimation. One such method, proposed by Suchey and Brooks in 1990, groups the observed changes occurring in the pubic symphysis into six phases, each defined by a corresponding age range. The present study was piloted with the focussed question being to empirically determine the accuracy of the Suchey-Brooks method in computed tomographic age estimation by analysing morphological changes occurring in the pubic symphysis. Original articles pertaining to the use of the Suchey-Brooks method for CT based age estimation were extracted from four different databases- PubMed, CENTRAL, Google Scholar and ScienceDirect. Research papers which were answering the focussed question were selected for data analysis. After assessing the risk of bias of the selected articles, the data was subjected to Meta-analysis. Pooled analysis of correctly/accurately aged individuals/remains using the random and fixed effect models yielded a prediction percentage of 78% and 86%, respectively. Higher percentages were obtained for phase-wise and subgroup analysis, indicating that the Suchey-Brooks method is a reliable method for age estimation.

Study of age estimation from epiphyseal union of long bones of knee joint by radiography

Study of age estimation from epiphyseal union of long bones of knee joint by radiography

A study of age estimation from digital X-ray of shoulder joint in south Gujarat region

A study of age estimation from digital X-ray of shoulder joint in south Gujarat region

A Survey on Deep Learning Face Age Estimation Model: Method and Ethnicity

Face age estimation is a type of study in computer vision and pattern recognition. Designing an age estimation or classification model requires data as training samples for the machine to learn. Deep learning method has improved estimation accuracy and the number of deep learning age estimation models developed. Furthermore, numerous datasets availability is making the method an increasingly attractive approach. However, face age databases mostly have limited ethnic subjects, only one or two ethnicities and may result in ethnic bias during age estimation, thus impeding progress in understanding face age estimation. This paper reviewed available face age databases, deep learning age estimation models, and discussed issues related to ethnicity when estimating age. The review revealed changes in deep learning architectural designs from 2015 to 2020, frequently used face databases, and the number of different ethnicities considered. Although model performance has improved, the widespread use of specific few multi-races databases, such as the MORPH and FG-NET databases, suggests that most age estimation studies are biased against non-Caucasians/non-white subjects. Two primary reasons for face age research’s failure to further discover and understand ethnic traits effects on a person’s facial aging process: lack of multi-race databases and ethnic traits exclusion. Additionally, this study presented a framework for accounting ethnic in face age estimation research and several suggestions on collecting and expanding multi-race databases. The given framework and suggestions are also applicable for other secondary factors (e.g. gender) that affect face age progression and may help further improve future face age estimation research.

Enhanced Cycle Generative Adversarial Network for Generating Face Images of Untrained Races and Ages for Age Estimation

The datasets used in recent age estimation studies largely consist of two races (i.e., Asians or Westerners), and despite the large amount of data available, the problems regarding age–class imbalances still arise, owing to different age distributions. This causes overfitting in training process, reducing the generality of the age estimation. This problem typically occurs in homogeneous datasets, e.g., using the same Asian database for training and testing or using a database with the same age range for training and testing. Consequently, the problems arise in heterogeneous datasets, e.g., using an Asian database in training and a Westerner database in testing or using databases of different age ranges in training and testing, and the accuracy inevitably degrades when heterogeneous datasets are used for training and testing. To solve these problems, we proposes an enhanced cycle generative adversarial network (CycleGAN)-based heterogeneous race and age image transformation technique, which can transform the images of one race and age range to those of different race and age range. The encoder and decoder of the generator in the proposed enhanced CycleGAN include residual connections, thereby preventing information loss as much as possible as the layer deepens. In addition, the generator of the enhanced CycleGAN uses identity loss and age loss functions between the generator-produced image and a multi-channel input image obtained through 3D one-hot encoding. Through this, the training is directed to increasing the similarity not only between the images but also between the age class labels. And the enhanced CycleGAN uses a second discriminator in addition to the existing discriminator, thereby addressing a problem in which training is not properly performed when the discriminator converges too fast relative to the generator in a conventional CycleGAN. Experiments with three open databases demonstrated that our method outperforms state-of-the-art methods for facial image transformation and age estimation.

Age Estimation from Computed Tomography of Cranial Suture Closure in a Thai Population

Age estimation from human skeletal remains is an important step to reconstruct a biological profile. Cranial suture has long been studied for its age-related closure. However, until now, forensic anthropologists still attempt to investigate the best way of estimating age at death from cranial suture closure because skull is usually found at the crime scene due to its easy recognised-appearance and persistence to post-mortem insults. For these reasons, a study of age estimation from cranial suture closure in a Thai population was conducted, which focussed to study the appearance and visibility of facial suture closure using computed tomography (CT). CT image series of 140 cases were obtained in order to investigate ectocranial closure of the selected facial sutures. The results from CT image analysis revealed that nasomaxillary provided the most consistent examination of suture closure (52%) while frontonasal delivered the lowest consistency in suture closure examination (29%). The inconsistency mostly occurred in assigning the closure score of 1 and 2. Thus, it could be suggested that a 3-scale scoring system of closure: open, closing, and closed, could be an appropriate method of evaluating degree of ectocranial closure of facial sutures obtained from CT imaging. This fundamental information of facial suture closure from CT images could serve as a starting point on development of age estimation technique from suture closure by utilising CT images.

A Study of Age Estimation by Radiological Assessment of Ossification Centers at Hand Wrist and Elbow Joint at a Tribal Teaching Medical College of Adilabad

Background: Radiological assessment of the skeletal ages is an important tool for the estimation of age inthe living. Such data can be very useful for forensic practitioners especially in developing countries some ofthe population is uneducated where the birth records are not present.Methods: This retrospective study was conducted in the Department of Forensic Medicine and Toxicology,Rajiv Gandhi Institute of Medical Sciences [RIMS], Adilabad. A total of n=26 males and n=46 females caseswere examined for the ossification at 4 areas which include left-Hand epiphyses (the distal end of radius andulna), Base of the first metacarpal and Conjoint Epiphyses. The assessment of radiographic images of handand elbow joints was based on the revised method for epiphyseal union assessment.Results: The mean ages at ossification for stage I in males were found to be 12.90 years. At stage II we foundthe mean age of 15.18 years. In stage III we found the mean age of 16.15 years and stage IV the mean agevalue at all ossification centers was 19.18 years. Similarly for females the mean values of all ossificationcenters at the stage I estimated the age of 14.12 years. In stage II the mean age estimated was 15.27 yearsand stage III the mean age estimated was 16.29 years and stage IV mean age estimated was 17.96 years.Conclusion: Within the constraints of the present study we found that hand wrist and elbow joint radiographsare very useful for estimation of bone age in cases up to 18 years of age. We used digital radiographs alongstages for determining the degree of ossification which has a greater degree of reproducibility and reliability.

Distribution Cognisant Loss for Cross-Database Facial Age Estimation With Sensitivity Analysis.

Existing facial age estimation studies have mostly focused on intra-database protocols that assume training and test images are captured under similar conditions. This is rarely valid in practical applications, where we typically encounter training and test sets with different characteristics. In this article, we deal with such situations, namely subjective-exclusive cross-database age estimation. We formulate the age estimation problem as the distribution learning framework, where the age labels are encoded as a probability distribution. To improve the cross-database age estimation performance, we propose a new loss function which provides a more robust measure of the difference between ground-truth and predicted distributions. The desirable properties of the proposed loss function are theoretically analysed and compared with the state-of-the-art approaches. In addition, we compile a new balanced large-scale age estimation database. Last, we introduce a novel evaluation protocol, called subject-exclusive cross-database age estimation protocol, which provides meaningful information of a method in terms of the generalisation capability. The experimental results demonstrate that the proposed approach outperforms the state-of-the-art age estimation methods under both intra-database and subject-exclusive cross-database evaluation protocols. In addition, in this article, we provide a comparative sensitivity analysis of various algorithms to identify trends and issues inherent to their performance. This analysis introduces some open problems to the community which might be considered when designing a robust age estimation system.

IMPLICATION OF PERIO IN FORENSIC ODONTOLOGY

Forensic research pertaining to dentistry has taken several turns and reached a crossroad where every separate branch has an entity to contribute to support identification of the deceased. Periodontics is utilized for identification of individuals through morphology and pathology of periodontium and is also utilized for age estimation studies which include periodontal ligament attachment level, root transparency and root length . The prime focus of this literature is to highlight how a periodontist can contribute to the field of forensic odontology by associating the following parameters of his domain, to unravel a crime scene. This literature aims to summarize the findings of studies that reported periodontal associations or potential associations that could play a role in forensic research.

Femoral histomorphometric age-at-death studies: The issue of sample size and standard error.

Extant histomorphometric aging methods based on the analysis of the femoral cortex generally report small samples (N<100) and highly variable standard error of the estimate (SEE) values (±1.51‒16.98 years). The present paper reviews the published literature on femoral histomorphometry for age-at-death estimation in order to examine the relationship between sample size and SEE values, and makes recommendations for minimum reporting requirements for age-at-death studies based on statistical data. The SEE from a total of 33 studies are analysed. Sample size and confidence intervals are explored using Hennig and Cooper's simulation modelling. Analysis of effect size through a fixed-effect model is performed on 5/33 studies to examine the relationship between sample size and effect size. The pooled sex formulae from Nor etal., Martrille etal. and Thompson and the two sex-specific formulae of Pfeiffer are examined, as they report mean and standard deviation values for both chronological and estimated ages. The results of these analyses support sampling theory, specifically wide variation in SEE when N<100, narrowing as the sample size increases, and lower effect sizes in the larger of the five studies examined. The findings provide some support for a minimum threshold of 100‒150 individuals for histomorphometric age-at-death estimation. Analysis of effect size is suggested for future investigation in meta-analyses of forensic anthropological age-estimation studies. To ensure increased precision and meaningful comparison, large samples should be used for histomorphometry, and authors should report SEE and discrete statistics (e.g. n, mean, standard deviation) for both chronological age and estimated age.

Magnetic resonance imaging for forensic age estimation in living children and young adults: a systematic review.

The use of MRI in forensic age estimation has been explored extensively during the last decade. The authors of this paper synthesized the available MRI data for forensic age estimation in living children and young adults to provide a comprehensive overview that can guide age estimation practice and future research. To do so, the authors searched MEDLINE, Embase and Web of Science, along with cited and citing articles and study registers. Two authors independently selected articles, conducted data extraction, and assessed risk of bias. They considered study populations including living subjects up to 30years old. Fifty-five studies were included in qualitative analysis and 33 in quantitative analysis. Most studies had biases including use of relatively small European (Caucasian) populations, varying MR approaches and varying staging techniques. Therefore, it was not appropriate to pool the age distribution data. The authors found that reproducibility of staging was remarkably lower in clavicles than in any other anatomical structure. Age estimation performance was in line with the gold standard, radiography, with mean absolute errors ranging from 0.85years to 2.0years. The proportion of correctly classified minors ranged from 65% to 91%. Multifactorial age estimation performed better than that based on a single anatomical site. The authors found that more multifactorial age estimation studies are necessary, together with studies testing whether the MRI data can safely be pooled. The current review results can guide future studies, help medical professionals to decide on the preferred approach for specific cases, and help judicial professionals to interpret the evidential value of age estimation results.

A comparative study of human facial age estimation: handcrafted features vs. deep features

In recent times, the topic of human facial age estimation attracted much attention. This is due to its ability to improve biometrics systems. Recently, several applications that are based on the demographic attributes estimation have been developed. These include law enforcement, re-identification in videos, planed marketing, intelligent advertising, social media, and human-computer interaction. The main contributions of the paper are as follows. Firstly, it extends some handcrafted models that are based on the Pyramid Multi Level (PML) face representation. Secondly, it evaluates the performance of two different kinds of features that are handcrafted and deep features. It compares handcrafted and deep features in terms of accuracy and computational complexity. The proposed scheme of study includes the following three main steps: 1) face preprocessing; 2) feature extraction (two different kinds of features are studied: handcrafted and deep features); 3) feeding the obtained features to a linear regressor. In addition, we investigate the strengths and weaknesses of handcrafted and deep features when used in facial age estimation. Experiments are run on three public databases (FG-NET, PAL and FACES). These experiments show that both handcrafted and deep features are effective for facial age estimation.