Automated Identification from Dental Data (AutoIDD): A new development in digital forensics

Dental Identification System in Public Health: Innovations and Ethical Challenges: A Narrative Review

Dental identification systems (DISs) encompass various techniques used for forensic identification, serving as alternatives or complements to genetic methods. Technologies such as microchip implants, prosthetic inscriptions, microSD cards, and identification plaques have been proposed to address limitations in comparative methods, offering streamlined processes for forensic experts. This study reviews current and potential DIS implementations, emphasizing cost-effectiveness and community benefits. Literature analysis from PubMed (2008-2024) yielded 17 relevant articles on implantable DISs, enabling direct subject identification via teeth or prostheses. The integration of DIS aims to enhance accuracy and speed in personal profiling and legal identification, promoting technology transfer in dentistry. It will be necessary to develop strict privacy regulations to protect patient data and establish ethical guidelines for their use. The study's aim is to highlight that the universal adoption of DISs could mitigate healthcare disputes and facilitate data exchange in clinical settings, which is particularly beneficial for vulnerable populations.

Digital Dental Biometrics for Human Identification Based on Automated 3D Point Cloud Feature Extraction and Registration

BACKGROUND

Intraoral scans (IOS) provide precise 3D data of dental crowns and gingival structures. This paper explores an application of IOS in human identification.

METHODS

We propose a dental biometrics framework for human identification using 3D dental point clouds based on machine learning-related algorithms, encompassing three stages: data preprocessing, feature extraction, and registration-based identification. In the data preprocessing stage, we use the curvature principle to extract distinguishable tooth crown contours from the original point clouds as the holistic feature identification samples. Based on these samples, we construct four types of local feature identification samples to evaluate identification performance with severe teeth loss. In the feature extraction stage, we conduct voxel downsampling, then extract the geometric and structural features of the point cloud. In the registration-based identification stage, we construct a coarse-to-fine registration scheme in order to realize the identification task.

RESULTS

Experimental results on a dataset of 160 individuals demonstrate that our method achieves a Rank-1 recognition rate of 100% using complete tooth crown contours samples. Utilizing the remaining four types of local feature samples yields a Rank-1 recognition rate exceeding 96.05%.

CONCLUSIONS

The proposed framework proves effective for human identification, maintaining high identification performance even in extreme cases of partial tooth loss.

A Novel Algorithm for Forensic Identification Using Geometric Cranial Patterns in Digital Lateral Cephalometric Radiographs in Forensic Dentistry

Lateral cephalometric radiographs are crucial in dentistry and orthodontics for diagnosis and treatment planning. However, their use in forensic identification, especially with burned bodies or in mass disasters, is challenging. AM (antemortem) and PM (postmortem) radiographs can be compared for identification. This study introduces and evaluates a novel algorithm for extracting cranial patterns from digital lateral cephalometric radiographs for identification purposes. Due to the unavailability of AM cephalograms from deceased individuals, the algorithm was tested using pre- and post-treatment cephalograms of living individuals from an orthodontic archive, considered as AM and PM data. The proposed algorithm encodes cranial patterns into a database for future identification. It matches PM cephalograms with AM records, accurately identifying individuals by comparing cranial features. The algorithm achieved an accuracy of 97.5%, a sensitivity of 97.7%, and a specificity of 95.2%, correctly identifying 350 out of 358 cases. The mean similarity score improved from 91.02% to 98.10% after applying the Automatic Error Reduction (AER) function. Intra-observer error analysis showed an average Euclidean distance of 3.07 pixels (SD = 0.73) for repeated landmark selections. The proposed algorithm shows promise for identity recognition based on cranial patterns and could be enhanced with artificial intelligence (AI) algorithms in future studies.

Digital intraoral and radiologic records in forensic identification: Match with disruptive technology

While clinical dentistry has seamlessly integrated the digital revolution, there is a gap in the technological capabilities of forensic dentistry.The study aimed to compare the superimposition accuracy of two different three-dimensional record formats, namely the intraoral scanner and cone beam computer tomography, in the context of forensic identification.The sample consisted of randomly selected adults (n=10) of both sexes aged between 20 and 50 years. Following the acquisition of data using the Medit i700 wireless scanner and the iCAT Tomograph with InVivo software, the records were analysed and compared through superimposition using Medit Scan Clinic software to assess the technical precision of anatomical identification details.The results obtained through the superimposition of dental and bone records following intra- and inter-observer analysis enabled an accurate comparison and identification of an individual. This method can differentiate between positive and negative matches, achieving exclusion results and offering a potential solution to overcoming the absence of a standardisation procedure in human identification.

3D superimposition of human dentition contours in personal identification: A preliminary study

The human permanent dentition has been commonly used for personal identification due to its uniqueness. Limited research, however, is conducted using 3D digital dental models. We propose to develop a new 3D superimposition method using the contours of human dentition and to further evaluate its feasibility. A total of 270 intraoral scan models were collected from 135 subjects. After a one-year interval, 52 subjects were chosen at random and the secondary intraoral scan models were obtained. The dentition contours of the first and secondary models were extracted to form a resource dataset and a test dataset. Through the application of the iterative nearest point (ICP) algorithm, the test dataset was registered with the resource dataset, and the root mean square error (RMSE) values of the point-to-point distances were calculated. 104 genuine pairs and 13,936 imposter pairs were generated, and in this study, the registration accuracy was 100%. The difference between mean RMSE values for the genuine pair (0.20 ± 0.06 mm) and the minimum RMSE value for the imposter pair (0.83 ± 0.06 mm) was significant in the maxillary arch (p < 0.05). Similarly, in the mandibular arch, the difference between mean RMSE values for the genuine pair (0.22 ± 0.07 mm) and the minimum RMSE value for the imposter pair (0.85 ± 0.08 mm) was significant (p < 0.05). The difference between the RMSE value for the genuine pair in the maxillary and the mandibular arch was significant (p < 0.05). This study indicated the feasibility of dentition contour-based model superimposition and could be considered for personal identification in the future.

Advances in Technologies in Crime Scene Investigation

Crime scene investigation (CSI) is the complex act of reconstructing the dynamics that led to a crime and the circumstances of its perpetration. Crystallizing the CSI is a difficult task for the forensic pathologist; however, it is often requested by the public prosecutor and many judicial cases remain unsolved precisely for this reason. Recent years have seen an improvement in the ability of 3D scanning technology to obtain dense surface scans of large-scale spaces, for surveying, engineering, archaeology, and medical purposes such as forensics. The applications of this new technology are growing every day: forensic measurement of wounds in clinical reports, for example, reconstruction of traffic accidents, bullet trajectory studies in gunshot wounds, and 3D bloodstain pattern analysis. A retrospective analysis was conducted across all crime scene investigations performed by the forensic staff of the Department of Forensic Pathology of the University of Catania from January 2019 to June 2022. Inclusion criteria were the use of a laser scanner (LS), the use of a camera, a full investigative scene, and collection of circumstantial data thanks to the help of the judicial police. Cases in which the LS was not used were excluded. Out of 200 CSIs, 5 were included in the present study. In case number 1, the use of the LS made it possible to create a complete scale plan of the crime scene in a few hours, allowing a ship to be quickly returned to the judicial police officer. In case 2 (fall from a height), the LS clarified the suicidal intent of the deceased. In case number 3 it was possible to reconstruct a crime scene after many years. In case 4, the LS provided a great contribution in making a differential diagnosis between suicide and homicide. In case 5, the LS was fundamental for the COVID team in planning the study of COVID-19 pathways and areas within a hospital with the aim of reduction of nosocomial transmission. In conclusion, the use of the LS allowed the forensic staff to crystallize the investigative scene, making it a useful tool.

3D-3D dentition superimposition for individual identification: A study of an Eastern Chinese population

Recently, 3D dental intraoral scanning technology has been developed rapidly and applied widely in everyday dental practice. Since 3D dental scanning could provide valuable personal information, it enabled researchers to develop novel procedures for individual identification through 3D-3D dentition superimposition. This study aimed to test the applicability of this method in an Eastern Chinese population and propose a threshold for personal identification. For this purpose, 40 volunteers were recruited, and the initial 80 (upper and lower) 3D intraoral scans (IOS) were collected. After one year, 80 IOS of these volunteers were repeatedly collected. In addition, the other 120 IOS of 60 patients were extracted from the database. The 3D models were trimmed, aligned, and superimposed via Geomagic Control X software, and then the root mean square (RMS) value of point-to-point distance between the two models was calculated. The superimposition of two IOS belonging to the same individual was considered as a match, and superimposition of two IOS belonging to different individuals was considered as a mismatch. Totally, superimpositions of 80 matches and 3120 mismatches were obtained. Intra- and inter-observer errors were assessed through the calculation of relative technical error of measurement (rTEM). Mann-Whitney U test verified possible statistically significant differences between matches and mismatches (P < 0.05). The rTEM of intra- and inter-observer repeatability analyses was lower than 4.7 %. The range of RMS value was 0.05-0.18 mm in matches and 0.72-2.28 mm in mismatches without overlapping. The percentage of accurate identification reached 100 % in blind test through an arbitrary RMS threshold of 0.45 mm. The results indicated that individual identification through the 3D-3D dentition superimposition was effective in Eastern Chinese population. Successful identification could be achieved with high probability when the RMS value of the point-to-point distance of two dentitions is <0.45 mm.

Texture-Based Neural Network Model for Biometric Dental Applications

BACKGROUND

The aim is to classify dentition using a novel texture-based automated convolutional neural network (CNN) for forensic and prosthetic applications.

METHODS

Natural human teeth (n = 600) were classified, cleaned, and inspected for exclusion criteria. The teeth were scanned with an intraoral scanner and identified using a texture-based CNN in three steps. First, through preprocessing, teeth images were segmented by extracting the front-facing region of the teeth. Then, texture features were extracted from the segmented teeth images using the discrete wavelet transform (DWT) method. Finally, deep learning-based enhanced CNN models were used to identify these images. Several experiments were conducted using five different CNN models with various batch sizes and epochs, with and without augmented data.

RESULTS

Based on experiments with five different CNN models, the highest accuracy achieved was 0.8 and the precision was 0.8 with a loss value of 0.9, a batch size of 32, and 250 epochs. A comparison of deep learning models with different parameters showed varied accuracy between the different classes of teeth.

CONCLUSION

The accuracy of the point-based CNN method was promising. This texture-identification method will pave the way for many forensic and prosthodontic applications and will potentially help improve the precision of dental biometrics.

Dental Radiographic/Digital Radiography Technology along with Biological Agents in Human Identification

The heavy casualties associated with mass disasters necessitate substantial resources to be managed. The unexpectedly violent nature of such occurrences usually remains a problematic amount of victims that urgently require to be identified by a reliable and economical method. Conventional identification methods are inefficient in many cases such as plane crashes and fire accidents that have damaged the macrobiometric features such as fingerprints or faces. An appropriate recognition method for such cases should use features more resistant to destruction. Forensic dentistry provides the most appropriate available method for the successful identification of victims using careful techniques and precise data interpretation. Since bones and teeth are the most persistent parts of the demolished bodies in sudden mass disasters, scanning and radiographs are unrepeatable parts of forensic dentistry. Forensic dentistry as a scientific method of human remain identification has been considerably referred to be efficient in disasters. Forensic dentistry can be used for either "sex and age estimation," "Medical biotechnology techniques," or "identification with dental records," etc. The present review is aimed at discussing the development and implementation of forensic dentistry methods for human identification. For this object, the literature from the last decade has been searched for the innovations in forensic dentistry for human identification based on the PubMed database.

[Automated digital superimposition of the 3D model and archival photographs of full removable dentures in forensic dentistry]

THE AIM THE STUDY

The purpose of the work is to perform automated alignment of two-dimensional archival photographs of the first prosthesis and a digital model of the complete removable prosthesis by superposition in order to determine or deny their possible belonging to one user.

MATERIALS END METHODS

The superposition was carried out in the Exocad program (DentalCAD 3.0 Galway) using the standard 2D-3D alignment algorithm of the «SmileDesign» module; in the same program. In addition, Keynote and Fusion 360, and Autodesk programs were used. Statistical measurements were carried out at the statistically significant level of p<0.05.

RESULTS

A comparison of four different-angle and different-scale photographic images of a removable denture of the upper jaw teeth with a three-dimensional copy of the same version of the prosthesis of the life physician of the royal family E.S. Botkin was made. When superimposing a digital three-dimensional model and a two-dimensional photograph of the original prosthesis with marked anthropometric points (n=51), 21 of them coincided or touched each other (41.2%). Another 26 points were located side by side (distance up to 1.5 mm) (50.9%) and 4 did not coincide (distance >1.5 mm, but no more than 3.5-4 mm) (7.8%). When the reference points were combined, the contours, the configuration of the relief and the peripheral boundaries of all three objects mostly coincided. The linear longitudinal and transverse dimensions of the bases of the prostheses also mostly coincided. The exception was the distal border of the bases, and the level of the cutting edges of the anterior artificial teeth, where complete coincidence was not observed, due to differences in the degree of erasability.

CONCLUSION

Comparison of the original prosthesis from Ipatiev's house and its stereolithographic model was a test for the accuracy of the matching method used. The stereotype of the compared images is proved and the consistency of the possibility of computer combination of three-dimensional and two-dimensional objects is confirmed. The use of traditional methods of forensic identification and evaluation of the results by methods of mathematical statistics allowed us to conclude that the two different complete removable dentures of the upper jaw depicted in the photographs belong to one user.

Three-dimensional superimposition of digital models for individual identification

Dentition is an individualizing structure in humans that may be potentially utilized in individual identification. However, research on the use of three-dimensional (3D) digital models for personal identification is rare. This study aimed to develop a method for individual identification based on a 3D image registration algorithm and assess its feasibility in practice. Twenty-eight college students were recruited; for each subject, a dental cast and an intraoral scan were taken at different time points, and digital models were acquired. The digital models of the dental casts and intraoral scans were assumed as antemortem and postmortem dentition, respectively. Additional 72 dental casts were extracted from a hospital database as a suspect pool together with 28 antemortem models. The dentition images of all of the models were extracted. Correntropy was introduced into the traditional iterative closest point algorithm to compare each postmortem 3D dentition with 3D dentitions in the suspect pool. Point-to-point root mean square (RMS) distances were calculated, and then 28 matches and 2772 mismatches were obtained. Statistical analysis was performed using the Mann-Whitney U test, which showed significant differences in RMS between matches (0.18±0.03mm) and mismatches (1.04±0.67mm) (P<0.05). All of the RMS values of the matched models were below 0.27mm. The percentage of accurate identification reached 100% in the present study. These results indicate that this method for individual identification based on 3D superimposition of digital models is effective in personal identification.

An artificial intelligence system using machine-learning for automatic detection and classification of dental restorations in panoramic radiography

OBJECTIVES

The aim of this study was to develop a computer vision algorithm based on artificial intelligence, designed to automatically detect and classify various dental restorations on panoramic radiographs.

STUDY DESIGN

A total of 738 dental restorations in 83 anonymized panoramic images were analyzed. Images were automatically cropped to obtain the region of interest containing maxillary and mandibular alveolar ridges. Subsequently, the restorations were segmented by using a local adaptive threshold. The segmented restorations were classified into 11 categories, and the algorithm was trained to classify them. Numerical features based on the shape and distribution of gray level values extracted by the algorithm were used for classifying the restorations into different categories. Finally, a Cubic Support Vector Machine algorithm with Error-Correcting Output Codes was used with a cross-validation approach for the multiclass classification of the restorations according to these features.

RESULTS

The algorithm detected 94.6% of the restorations. Classification eliminated all erroneous marks, and ultimately, 90.5% of the restorations were marked on the image. The overall accuracy of the classification stage in discriminating between the true restoration categories was 93.6%.

CONCLUSIONS

This machine-learning algorithm demonstrated excellent performance in detecting and classifying dental restorations on panoramic images.