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

Abstract

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.

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

“…A complete description follows. All parameter values chosen were validated across the available data set using the visualization method described by Fogalli et al (2022).…”

“…where W (3,6) is a 3 × 6 integral kernel. Kernel shape and size were selected using the validation approach described previously by Fogalli et al (2022) for determining other parameters. The horizontally elongated kernel reduces the noise in the background that could mimic HSB edges, mainly in regions of the tooth with artifacts from reflected light, while causing virtually no disturbance to the real HSB.…”