Automated segmentation of dental CBCT image with prior-guided sequential random forests

Abstract

Purpose: Cone-beam computed tomography (CBCT) is an increasingly utilized imaging modality for the diagnosis and treatment planning of the patients with craniomaxillofacial (CMF) deformities. Accurate segmentation of CBCT image is an essential step to generate 3D models for the diagnosis and treatment planning of the patients with CMF deformities. However, due to the image artifacts caused by beam hardening, imaging noise, inhomogeneity, truncation, and maximal intercuspation, it is difficult to segment the CBCT. Methods: In this paper, the authors present a new automatic segmentation method to address these problems. Specifically, the authors first employ a majority voting method to estimate the initial segmentation probability maps of both mandible and maxilla based on multiple aligned expert-segmented CBCT images. These probability maps provide an important prior guidance for CBCT segmentation. The authors then extract both the appearance features from CBCTs and the context features from the initial probability maps to train the first-layer of random forest classifier that can select discriminative features for segmentation. Based on the first-layer of trained classifier, the probability maps are updated, which will be employed to further train the next layer of random forest classifier. By iteratively training the subsequent random forest classifier using both the original CBCT features and the updated segmentation probability maps, a sequence of classifiers can be derived for accurate segmentation of CBCT images. Results: Segmentation results on CBCTs of 30 subjects were both quantitatively and qualitatively validated based on manually labeled ground truth. The average Dice ratios of mandible and maxilla by the authors' method were 0.94 and 0.91, respectively, which are significantly better than the state-of-the-art method based on sparse representation (p-value < 0.001). Conclusions: The authors have developed and validated a novel fully automated method for CBCT segmentation. C

Pose-aware instance segmentation framework from cone beam CT images for tooth segmentation

“…Literature on Tooth Segmentation 1) Classical Methods: Classical image processing methods have been widely studied to achieve tooth segmentation [2], [3], [12], [13]. Several methods including region growing [1], watershed algorithm [2], [3], morphological operators [2], graph-cut-based segmentation [12], template-based registration [8], [9], and random forest classification [13] were implemented. Semiautomatic algorithms with manually annotated cues for easy implementation have also gained popularity [3], [14], [15].…”

Current status of digital dental surgery

“…Certain advances have been reported in the area of algorithms of semi-automated software segmentation of the mandible, as well as the attempts of a digital reconstruction of CT information based PONS Medicinski časopis / PONS Medical Journal REVIEW ARTICLE / PREGLEDNI RAD on a pre-existing mapping of key anatomical points of reference. 23,24 It is our opinion that further research is certainly warranted in the area of CBCT information segmentation which would enable adequate recognition and modeling of anatomical elements in the form of independent 3D objects.…”

Segmenting Tooth Components in Dental X-Ray Images Using Gaussian Kernel- Based Conditional Spatial Fuzzy C-Means Clustering Algorithm

“…The age estimation methods require segmentation of tooth components such as enamel, dentine and pulp which are still done manually. The drawback of manual segmentation is that it is tedious, time-consuming, and user-dependent; for example, it takes hours to segment the maxillomandibular region [6]. Therefore, automated age estimation methods have great potential to increase accuracy and repeatability.…”