Dental Radiography in Age Determination: Contemporary Methods and Trends DOI Open Access

Pornpattra Chulamanee,

Wannakamon Panyarak

Oral Sciences Reports, Journal Year: 2023, Volume and Issue: 44(3), P. 54 - 76

Published: Nov. 16, 2023

The determination of an individual's age assumes paramount significance in forensic and legal contexts, necessitating the utilization diverse techniques. Dental radiography emerges as a non-invasive approach for determining age-related dental changes. This method grants comprehensive analysis various features to identify individual’s precise age, place them within designated ranges, or define whether they exceed subordinate specific thresholds. review summarizes estimation methodologies using conducts investigations into contemporary trends by reviewing relevant studies published Pubmed between 2020 2023. Age categorization delineates three distinct phases: pre-natal, neo-natal, post-natal; childhood adolescence; adulthood. Panoramic becomes predominant radiographic modality, with Demirjian is more commonly known initial two phases. In contrast, adulthood relies on anatomical Significantly, artificial intelligence (AI) technology has recently attracted attention estimation, yielding promising results. AI demonstrates potential enhance accuracy conventional methodologies, diminishing human errors mitigating associated workload burdens, offering inventive ground future advancements.

Language: Английский

Deep Learning for Age Estimation from Panoramic Radiographs: A Systematic Review and Meta-Analysis DOI
Rata Rokhshad, Fatemeh Nasiri,

Naghme Saberi

et al.

Journal of Dentistry, Journal Year: 2025, Volume and Issue: unknown, P. 105560 - 105560

Published: Jan. 1, 2025

Language: Английский

Citations

4
Performance of Artificial Intelligence Models Designed for Automated Estimation of Age Using Dento-Maxillofacial Radiographs—A Systematic Review DOI Creative Commons
Sanjeev B. Khanagar, Farraj Albalawi, Aram Alshehri

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(11), P. 1079 - 1079

Published: May 22, 2024

Automatic age estimation has garnered significant interest among researchers because of its potential practical uses. The current systematic review was undertaken to critically appraise developments and performance AI models designed for automated using dento-maxillofacial radiographic images. In order ensure consistency in their approach, the followed diagnostic test accuracy guidelines outlined PRISMA-DTA this review. They conducted an electronic search across various databases such as PubMed, Scopus, Embase, Cochrane, Web Science, Google Scholar, Saudi Digital Library identify relevant articles published between years 2000 2024. A total 26 that satisfied inclusion criteria were subjected a risk bias assessment QUADAS-2, which revealed flawless both arms patient-selection domain. Additionally, certainty evidence evaluated GRADE approach. technology primarily been utilized through tooth development stages, bone parameters, measurements, pulp–tooth ratio. employed studies achieved remarkably high precision 99.05% 99.98% stages respectively. application additional tool within realm demonstrates promise.

Language: Английский

Citations

6
Fully automated deep learning approach to dental development assessment in panoramic radiographs DOI Creative Commons
Seung-Hwan Ong, Hyuntae Kim, Ji‐Soo Song

et al.

BMC Oral Health, Journal Year: 2024, Volume and Issue: 24(1)

Published: April 6, 2024

Abstract Background Dental development assessment is an important factor in dental age estimation and maturity evaluation. This study aimed to develop evaluate the performance of automated staging system based on Demirjian’s method using deep learning. Methods The included 5133 anonymous panoramic radiographs obtained from Department Pediatric Dentistry database at Seoul National University Hospital between 2020 2021. proposed methodology involves a three-step procedure for staging: detection, segmentation, classification. data were randomly divided into training validating sets (8:2), YOLOv5, U-Net, EfficientNet trained employed each stage. models’ performance, along with Grad-CAM analysis EfficientNet, was evaluated. Results mean average precision (mAP) 0.995 segmentation achieved accuracy 0.978. classification showed F1 scores 69.23, 80.67, 84.97, 90.81 Incisor, Canine, Premolar, Molar models, respectively. In analysis, model focused apical portion developing tooth, crucial feature according method. Conclusions These results indicate that learning approach can serve as supportive tool dentists, facilitating rapid objective

Language: Английский

Citations

5
Dental age estimation: A comparative study of convolutional neural network and Demirjian's method DOI
Mustan Barış SİVRİ, Shahram Taheri,

Rukiye Gözde Kırzıoğlu Ercan

et al.

Journal of Forensic and Legal Medicine, Journal Year: 2024, Volume and Issue: 103, P. 102679 - 102679

Published: March 21, 2024

Language: Английский

Citations

4
Künstliche Intelligenz in der forensisch-radiologischen Altersdiagnostik DOI
Maria L. Hahnemann, Andreas Heinrich,

Hans-Joachim Mentzel

et al.

Rechtsmedizin, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 27, 2025

Citations

0
Applications of Artificial Intelligence and Machine Learning for Orthodontic Diagnosis DOI Creative Commons
Soukaina Sahim,

Moncef Boutissante,

Farid El Quars

et al.

IntechOpen eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 28, 2025

Over the past two decades, artificial intelligence (AI) and machine learning (ML) have undergone significant progress. With advances in digital technology new possibilities emerged to improve orthodontic diagnosis process. AI makes it possible create a virtual patient by assembling all of patient’s clinical data. This is applied identify cephalometric landmarks, analyze CBCT determine degree maturation biological age. Thanks AI, certain diagnoses are increasingly simple develop, namely assessment upper airways, analysis temporomandibular joints TMJ others. enables more precise analysis, efficient planning thus improved treatment results. Artificial offers many opportunities diagnosis. However, must be used as decision support tool; expertise human evaluation remain essential make informed decisions regarding treatment. chapter highlights different applications for while assessing accuracy efficiency this technology.

Language: Английский

Citations

0
Pre-trained VGG16 Model for Forensic Dental Age Estimation DOI

Valon Nushi,

Rui Santos, Hrvoje Brkić

et al.

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 3, 2025

Abstract Background A practical utilization of Machine Learning in Forensic Odontology is yet underexplored, especially the field Age Estimation. Estimation essential legal proceedings to protect rights individuals without proper documentation, whether for seeking asylum or when caring a found child. This study aimed utilize VGG16 model read, analyze, and provide classification tooth development stages third molars. Specifically, molars 38 48 were used classify into age groups based on thresholds 16, 18, 21 years old. The goal was compare accuracy traditional estimation methods established by Demirjian, Moorrees, Funning, Hunt, with CNN-based approach. Method total sample 876 orthopantomograms (OPGs) from Portuguese population collected ULS Hospital Santa Maria, University Lisbon. comprised 447 OPGs male patients 429 female patients, aged 10 25 calculated manually using Demirjian Moorrees. Furthermore, we trained stages, afterwards evaluated through overall accuracy, recall, precision, F-Score. Results provided excellent results cropped images only (38 48) captured very well patterns features so obtained more than 90%. However, analyze Hunt faced some limitations due insufficient OPGs. Conclusion teeth demonstrated promising high degree accuracy. limited size constrained model's ability effectively differentiate between numerous development. To enhance reliability, larger diverse dataset necessary better capture nuances each developmental stage.

Language: Английский

Citations

0
Detection of C-shaped mandibular second molars on panoramic radiographs using deep convolutional neural networks DOI
Jin Long,

Wenyuan Zhou,

Ying Tang

et al.

Clinical Oral Investigations, Journal Year: 2024, Volume and Issue: 28(12)

Published: Nov. 18, 2024

Language: Английский

Citations

2
Testing the accuracy of Foti’s dental age estimation methods on a London UK sample DOI Creative Commons
Nurul Zeety Azizi,

Janet Davies,

Helen M. Liversidge

et al.

Forensic Science International Reports, Journal Year: 2023, Volume and Issue: 8, P. 100330 - 100330

Published: July 31, 2023

Tooth development and eruption are widely used in assessing dental age estimation, one of the methods using tooth is Foti's method. However, population original study was French. Therefore, aim this to test accuracy four estimation regression models against East London population, mainly Bangladeshi Caucasion ethnicity. These count number erupted teeth germs a radiograph (Foti 1), absence 2), maxillary 3) mandibular 4). The sample archived panoramic radiographs 754 healthy patients aged 6-20 years (380 males 374 females). difference between chronological ages tested t-test. mean absolute also calculated for all models. most accurate method defined as smallest difference, standard deviation (SD) ages. Foti model 2 with 0.11 year (SD 1.70 year) 1.33 years. Models 3 (maxillary teeth) 4 (mandibular were marginally less accurate, whilst 1 (radiograph) over-estimated on average by more than 5 Our findings show that estimating erupting (least bias).

Language: Английский

Citations

0
The Influence of Integrating Sex as a Feature in Deep Learning-Based Dental Age Estimation using Panoramic Radiographs DOI
Witsarut Upalananda, Sangsom Prapayasatok, Sakarat Na Lampang

et al.

Published: Oct. 28, 2023

Forensic dental age estimation based on panoramic radiographs (orthopantomogram, OPG) is commonly used to assess the of children and young adolescents. Recent advances in deep learning techniques have shown that it possible accurately determine individual from these OPG images. Traditionally, sex has been considered a predictive parameter for estimation. Surprisingly, most studies not included as feature their models. This study aims investigate impact including models estimating age. Two learning-based methods were developed compared: first method only image input, while second integrated both information. Our dataset 1734 images Thai population aged between 8 23 years, along with corresponding chronological sex. A pretrained EfficientNet-B0, convolutional neural network model, was estimate results indicate there no statistical difference error groups 15 years when comparing two methods. However, individuals using information resulted statistically lower compared image. mean absolute (MAE) 11 days, which might be clinically insignificant. finding suggests development model could accomplished one input without significantly affecting accuracy.

Language: Английский

Citations

0