Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network–based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.

Measuring porosity at the nanoscale by quantitative electron tomography

Quantitative electron tomography is proposed to characterize porous materials at a nanoscale. To achieve reliable three-dimensional (3D) quantitative information, the influence of missing wedge artifacts and segmentation methods is investigated. We are presenting the "Discrete Algebraic Reconstruction Algorithm" as the most adequate tomography method to measure porosity at the nanoscale. It provides accurate 3D quantitative information, regardless the presence of a missing wedge. As an example, we applied our approach to nanovoids in La2Zr2O7 thin films.

DART: a robust algorithm for fast reconstruction of three-dimensional grain maps

A novel algorithm is introduced for fast and nondestructive reconstruction of grain maps from X-ray diffraction data. The discrete algebraic reconstruction technique (DART) takes advantage of the intrinsic discrete nature of grain maps, while being based on iterative algebraic methods known from classical tomography. To test the properties of the algorithm, three-dimensional X-ray diffraction microscopy data are simulated and reconstructed with DART as well as by a conventional iterative technique, namely SIRT (simultaneous iterative reconstruction technique). For 100 × 100 pixel reconstructions and moderate noise levels, DART is shown to generate essentially perfect two-dimensional grain maps for as few as three projections per grain with running times on a PC in the range of less than a second. This is seen as opening up the possibility for fast reconstructions in connection within situstudies.

Optimal threshold selection for tomogram segmentation by projection distance minimization

Grey value thresholding is a segmentation technique commonly applied to tomographic image reconstructions. Many procedures have been proposed to optimally select the grey value thresholds based on the tomogram data only (e.g., using the image histogram). In this paper, a projection distance minimization (PDM) method is presented that uses the tomographic projection data to determine optimal thresholds. These thresholds are computed by minimizing the distance between the forward projection of the segmented image and the measured projection data. An important contribution of the current paper is the efficient implementation of the forward projection method, which makes the use of the original projection data as a segmentation criterion feasible. Simulation experiments applied to various phantom images show that our proposed method obtains superior results compared to established histogram-based methods.