Automatic quantification framework to detect cracks in teeth

Abstract

Studies show that cracked teeth are the third most common cause for tooth loss in industrialized countries. If detected early and accurately, patients can retain their teeth for a longer time. Most cracks are not detected early because of the discontinuous symptoms and lack of good diagnostic tools. Currently used imaging modalities like Cone Beam Computed Tomography (CBCT) and intraoral radiography often have low sensitivity and do not show cracks clearly. This paper introduces a novel method that can detect, quantify, and localize cracks automatically in high resolution CBCT (hr-CBCT) scans of teeth using steerable wavelets and learning methods. These initial results were created using hr-CBCT scans of a set of healthy teeth and of teeth with simulated longitudinal cracks. The cracks were simulated using multiple orientations. The crack detection was trained on the most significant wavelet coefficients at each scale using a bagged classifier of Support Vector Machines. Our results show high discriminative specificity and sensitivity of this method. The framework aims to be automatic, reproducible, and open-source. Future work will focus on the clinical validation of the proposed techniques on different types of cracks ex-vivo. We believe that this work will ultimately lead to improved tracking and detection of cracks allowing for longer lasting healthy teeth.

Detection and analysis of enamel cracks by ICG‐NIR fluorescence dental imaging

“…15 Early detection plays an important role in the diagnosis of a crack, which could significantly limit further growth of the crack and save the tooth. 10,13 In our previous pilot studies, we demonstrated the feasibility of ICG-NIRF dental imaging based on both a rat model 40,41,44 and human extracted teeth. 42,43 These results showed the promise of using ICG-NIRF dental imaging for crack detection.…”

“…The inability to image cracks by dental X-ray/CT makes tooth cracks one of the most notoriously difficult dental diseases to be diagnosed at an early stage, even for an experienced dentist, 1,13 which greatly limits the treatment of cracks. 10 Even for severe cracks that extend into both dentin and enamel, the enamel portion of cracks remains unidentifiable in dental X-ray and CT slices. Although existing studies suggest that CBCT could improve the diagnostic accuracy of tooth cracks 10 or that microCT provides even better dental resolution, 23 the cracks were not detectable even with the high resolution of microCT in this study.…”

“…[6][7][8] A cracked tooth, with a partial or complete fracture in both enamel and dentin, is reported as the third most common cause of tooth loss. [9][10][11] According to recent studies, a cracked tooth has an incidence rate of 34-74% in natural teeth, and over 75% of cracks appear in the molars. 1,12 Among the molars, a cracked tooth most commonly happens in the mandibular molars, particularly in the second mandibular molars, followed by the first mandibular molars and then the maxillary premolars.…”

“…23 While microCT has a much higher resolution and enables the visualization of some large cracks, this method is limited to individual extracted teeth only, thereby rendering it unsuitable for clinical use. 10,23 Another problem with X-ray techniques is the use of ionizing radiation. 20,22,[24][25][26] Magnetic resonance imaging, which does not use ionizing radiation, also has drawbacks with imaging small dental structures at a high resolution, including that the 4.0 Tesla magnetic field strength generally used in the laboratory research is not feasible as a clinical imaging tool.…”

Biopolymer Networks: Image Analysis, Reconstruction and Modeling

“…All the wavelets fulfill the conditions from Proposition 2. 3. The mother wavelets are represented at i = 0…”