Revelation of microcracks as tooth structural element by X-ray tomography and machine learning

High throughput automated characterization of enamel microstructure using synchrotron tomography and optical flow imaging

The remarkable damage-tolerance of enamel has been attributed to its hierarchical microstructure and the organized bands of decussated rods. A thorough characterization of the microscale rod evolution within the enamel is needed to elucidate this complex structure. While prior efforts in this area have made use of single particle tracking to track a single rod evolution to various degrees of success, such a process can be both computationally and labor intensive, limited to the evolution path of a single rod, and is therefore prone to error from potentially tracking outliers. Particle image velocimetry (PIV) is a well-established algorithm to derive field information from image sequences for processes that are time-dependent, such as fluid flows and structural deformation. In this work, we demonstrate the use of PIV in extracting the full-field microstructural distribution of rods within the enamel. Enamel samples from a wild African lion were analyzed using high-energy synchrotron X-ray micro-tomography. Results from the PIV analysis provide sufficient full-field information to reconstruct the growth of individual rods that can potentially enable rapid analysis of complex microstructures from high resolution synchrotron datasets. Such information can serve as a template for designing damage-tolerant bioinspired structures for advanced manufacturing. STATEMENT OF SIGNIFICANCE: Thorough characterization and analysis of biological microstructures (viz. dental enamel) allows us to understand the basis of their excellent mechanical properties. Prior efforts have successfully replicated these microstructures via single particle tracking, but the process is computationally and labor intensive. In this work, optical flow imaging algorithms were used to extract full-field microstructural distribution of enamel rods from synchrotron X-ray computed tomography datasets, and a field method was used to reconstruct the growth of individual rods. Such high throughput information allows for the rapid production/prototyping and advanced manufacturing of damage-tolerant bioinspired structures for specific engineering applications. Furthermore, the algorithms used herein are freely available and open source to broaden the availability of the proposed workflow to the general scientific community.

The exploration of a compound cone-beam CT contrast agent for diagnosis of human extracted cracked tooth

Objectives

This study aims to investigate the use of sodium iodide (NaI), dimethyl sulfoxide (DMSO), ethyl alcohol, and ethyl acetate as cone-beam CT (CBCT) contrast agents for diagnosing cracked teeth. The optimal delay time for detecting the number of crack lines beyond the dentino-enamel junction (Nd), the number of cracks extending from the occlusal surface to the pulp cavity (Np), and the depth of the crack lines was explored.

Methods

14 human extracted cracked teeth were collected, 12 were used for enhanced scanning, and 2 were used for exploring the characteristic of crack lines. The teeth were scanned in 3 CBCT enhanced scanning (ES) modes: ES1 using meglumine diatrizoate (MD); ES2 using NaI and DMSO, ES3 using NaI, DMSO, ethyl alcohol and ethyl acetate. Three delay times (15mins, 30mins, and 60mins) were set for scanning. Nd, Np, and depth of crack lines were evaluated.

Results

There were totally 24 crack lines on 12 cracked teeth. Nd was 10 in ES1 at 60mins, 24 in ES2 at 60mins and 24 in ES3 at 15mins. Np was 1 in ES1 at 60mins, 10 in ES2 at 60mins and 21 in ES3 at 60mins, and there were significantly different among them (p < 0.01). The average depth presented on ES3 was significantly deeper than ES1 and ES2 (p < 0.01).

Conclusion

NaI, DMSO, ethyl alcohol and ethyl acetate show potential as contrast agents for enhanced CBCT scanning in diagnosis of cracked teeth and their depth in vivo. A delay time of 15 min is necessary to confirm the existence of crack lines, while a longer delay time is required to ascertain if these crack lines extend to the pulp cavity.

Semantic segmentation for tooth cracks using improved DeepLabv3+ model

Objective

Accurate and prompt detection of cracked teeth plays a critical role for human oral health. The aim of this paper is to evaluate the performance of a tooth crack segmentation model (namely, FDB-DeepLabv3+) on optical microscopic images.

Method

The FDB-DeepLabv3+ model proposed here improves feature learning by replacing the backbone with ResNet50. Feature pyramid network (FPN) is introduced to fuse muti-level features. Densely linked atrous spatial pyramid pooling (Dense ASPP) is applied to achieve denser pixel sampling and wider receptive field. Bottleneck attention module (BAM) is embedded to enhance local feature extraction.

Results

Through testing on a self-made hidden cracked tooth dataset, the proposed method outperforms four classical networks (FCN, U-Net, SegNet, DeepLabv3+) on segmentation results in terms of mean pixel accuracy (MPA) and mean intersection over union (MIoU). The network achieves an increase of 11.41% in MPA and 12.14% in MIoU compared to DeepLabv3+. Ablation experiments shows that all the modifications are beneficial.

Conclusion

An improved network is designed for segmenting tooth surface cracks with good overall performance and robustness, which may hold significant potential in computer-aided diagnosis of cracked teeth.

Teeth Microcracks Research: Towards Multi-Modal Imaging

This perspective is an overview of the recent advances in teeth microcrack (MC) research, where there is a clear tendency towards a shift from two-dimensional (2D) to three-dimensional (3D) examination techniques, enhanced with artificial intelligence models for data processing and image acquisition. X-ray micro-computed tomography combined with machine learning allows 3D characterization of all spatially resolved cracks, despite the locations within the tooth in which they begin and extend, and the arrangement of MCs and their structural properties. With photoluminescence and micro-/nano-Raman spectroscopy, optical properties and chemical and elemental composition of the material can be evaluated, thus helping to assess the structural integrity of the tooth at the MC site. Approaching tooth samples having cracks from different perspectives and using complementary laboratory techniques, there is a natural progression from 3D to multi-modal imaging, where the volumetric (passive: dimensions) information of the tooth sample can be supplemented by dynamic (active: composition, interaction) image data. Revelation of tooth cracks clearly shows the need to re-assess the role of these MCs and their effect on the structural integrity and longevity of the tooth. This provides insight into the nature of cracks in natural hard materials and contributes to a better understanding of how bio-inspired structures could be designed to foresee crack propagation in biosolids.

3D fractures analysis and conservation assessment of wrought iron javelin through advanced non-invasive techniques

3D imaging is a powerful tool of high resolution and non-destructive imaging technology for the study of ancient weapons and military technology, which reveals the original microstructures and corrosion patterns that threaten these artefacts. Here we report quantitative analysis of the 3D distribution and the orientation of fractures, and uncorroded metal particles within a wrought iron javelin unearthed at the Phoenician-Punic site of Motya, Italy. The study aimed to gain a better understanding of the relationship between corrosion and local stresses within the artifact and to evaluate its manufacturing technology, as well as the effects of post-treatment with Paraloid B72 on concretion and mineralized layers. The cracks were quantified in terms of content, size, and orientation. The condition of artefact storage was evaluated by a multi-analytical approach, including X-ray microscopy, field emission electron microscopy and micro-Raman spectroscopy. The results indicated that a specific technique was used to create a sturdy, lightweight javelin with a central shaft for piercing or thrusting. The fractures appear elongated in the direction of the longitudinal axis of the blade, showing the forging direction of the original metallic block. The study concluded that the artifact had not yet been stabilized due to the presence of lepidocrocite.