Digital enhancement of dental enamel microstructure images from intact teeth

Arrieta, Zulieth López; Fogalli, Giovani Bressan; Line, Sérgio Roberto Peres

doi:10.1002/jemt.23070

Cited by 3 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A total of four articles were included in the scoping review: Ramenzoni et al, 2006 [ 7 ], Arrieta and Line, 2017 [ 8 ], Arrieta et al, 2018 [ 10 ], Bressan Fogali et al, 2022 [ 11 ].…”

Section: Resultsmentioning

confidence: 99%

Possible uses of Hunter–Schreger bands of dental enamel for automated personal identification

Dioguardi,

Sanesi,

Sovereto

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

Background Hunter–Schreger bands (HSB) are optical phenomena observed on tooth surfaces under polarized light, resulting from the intersection of enamel prisms. Anthropological studies demonstrate the prevalence of HSB in large mammals, contributing to enamel resistance. Historically, John Hunter and Schreger depicted HSB in dental literature. In dentistry, HSB play a role in non-carious cervical lesions (NCCL) and internal dental perikymata, suggesting their potential for personal identification. Personal identification, crucial in both daily and professional life, involves biometric characteristics, such as fingerprints or facial recognition. The need for non-invasive, rapid, and user-friendly methods has prompted the exploration of using HSB dental images for personal identification. The review aimed to consolidate studies employing HSB for personal identification. Methods The scoping review was carried out strictly following the PRISMA–ScR checklist; the search was carried out on tree databases (PubMed, Scopus, Science Direct,) and a register (Cochrane library). Results The research produced a number of bibliographic sources totaling 410. With the removal of duplicates, 334 were obtained; potentially eligible articles amounted to 14, of which only 4 fully complied with the criteria of eligibility. Conclusions From the data in the literature, we can assert that HSB could be used in personal identification, as they are characteristics that are difficult to change and easily detectable.

show abstract

“…A total of four articles were included in the scoping review: Ramenzoni et al, 2006 [ 7 ], Arrieta and Line, 2017 [ 8 ], Arrieta et al, 2018 [ 10 ], Bressan Fogali et al, 2022 [ 11 ].…”

Section: Resultsmentioning

confidence: 99%

Possible uses of Hunter–Schreger bands of dental enamel for automated personal identification

Dioguardi,

Sanesi,

Sovereto

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

show abstract

“…Some desirable characteristics of biometrics data are to be highly unique, easily obtainable, time-invariant (no significant changes over time), easily transmittable, non-intrusively acquirable and distinguishable by humans without special training [9]. Previous works show that a photograph of a tooth with side lighting enhances the HSB appearance [10] and the digital image of the HSB can be treated to highlight the bands [11]. The light and dark patterns formed by the HSB resembles fingerprints and also seems to be unique for each tooth and between individuals [8].…”

Section: Introductionmentioning

confidence: 99%

Segmentation of tooth enamel microstructure images using classical image processing and U-Net approaches

Fogalli

Line

Baum

2023

Preprint

View full text Add to dashboard Cite

Brackground: Tooth enamel is the hardest tissue in human organism, formed by prism layers in regularly alternating directions. These prisms form the Hunter-Schreger Bands (HSB) pattern when under side illumination, which is composed of light and dark stripes resembling fingerprints. We have shown in previous works that HSB pattern is highly variable, seems to be unique for each tooth and can be used as a biometric method for human identification. Since this pattern cannot be acquired with sensors, the HSB region in the digital photograph must be identified and correctly segmented from the rest of the tooth and background. Although these areas can be manually removed, this process is not reliable as excluded areas can vary according to the individual`s subjective impression. Therefore, the aim of this work was to develop an algorithm that automatically selects the region of interest (ROI), thus, making the entire biometric process straightforward. Results: We used two different approaches: a classical image processing method which we called anisotropy-based segmentation (ABS) and a machine learning method known as U-Net, a convolutional neural network. Both approaches were applied to a set of extracted tooth images. U-Net with some post processing outperformed ABS in the segmentation task with an Intersection Over Union (IOU) of 0.837 against 0.766. Conclusions: Even with a small dataset, U-Net proved to be a potential candidate for fully automated in-mouth application. However, the ABS technique has several parameters which allow a more flexible segmentation with interactive adjustments specific to image properties.

show abstract

“…Some desirable characteristics of biometrics data are their being highly unique, easily obtainable, time-invariant (no significant changes over time), easily transmittable, non-intrusively acquirable, and distinguishable by humans without special training (Shen and Tan, 1999). Previous work has shown that a photograph of a tooth with side lighting enhances the HSB appearance (Arrieta and Line, 2017) and that a digital image of HSBs can be treated to highlight the bands (Arrieta et al, 2018). The light and dark patterns formed by the HSBs resemble fingerprints and seem to be unique for each tooth and between individuals (Ramenzoni and Line, 2006).…”

Section: Introductionmentioning

confidence: 99%

Segmentation of tooth enamel microstructure images using classical image processing and U-Net approaches

Fogalli,

Line,

Baum

2023

Front. Imaging.

Self Cite

View full text Add to dashboard Cite

IntroductionTooth enamel is the hardest tissue in human organism, formed by prism layers in regularly alternating directions. These prisms form the Hunter–Schreger Band (HSB) pattern when under side illumination, which is composed of light and dark stripes resembling fingerprints. We have shown in previous works that HSB pattern is highly variable, seems to be unique for each tooth and can be used as a biometric method for human identification. Since this pattern cannot be acquired with sensors, the HSB region in the digital photograph must be identified and correctly segmented from the rest of the tooth and background. Although these areas can be manually removed, this process is not reliable as excluded areas can vary according to the individual‘s subjective impression. Therefore, the aim of this work was to develop an algorithm that automatically selects the region of interest (ROI), thus, making the entire biometric process straightforward.MethodsWe used two different approaches: a classical image processing method which we called anisotropy-based segmentation (ABS) and a machine learning method known as U-Net, a fully convolutional neural network. Both approaches were applied to a set of extracted tooth images.ResultsU-Net with some post processing outperformed ABS in the segmentation task with an Intersection Over Union (IOU) of 0.837 against 0.766.DiscussionEven with a small dataset, U-Net proved to be a potential candidate for fully automated in-mouth application. However, the ABS technique has several parameters which allow a more flexible segmentation with interactive adjustments specific to image properties.

show abstract

Digital enhancement of dental enamel microstructure images from intact teeth

Cited by 3 publications

References 28 publications

Possible uses of Hunter–Schreger bands of dental enamel for automated personal identification

Possible uses of Hunter–Schreger bands of dental enamel for automated personal identification

Segmentation of tooth enamel microstructure images using classical image processing and U-Net approaches

Segmentation of tooth enamel microstructure images using classical image processing and U-Net approaches

Contact Info

Product

Resources

About