Reconstruction of Panoramic Dental Images Through Bézier Function Optimization

A novel method for measuring the direction and angle of central ray and predicting rotation centre via panorama phantom

The aim of this study is to propose and evaluate a novel method for measuring the central ray direction and detecting the rotation centre of panoramic radiography using the panorama phantom. To determine the central ray direction, 2 points passing through the same x-coordinate in a panoramic radiograph were identified and connected. The angles formed by the central ray with the midline and the angle to the arch form were measured using mathematical calculations. Further, by analysing the continuous changes in the central ray obtained in this manner, the movement of the rotation centre was detected and visualized. The angle between the central ray and the midline exhibited a progressive decrease from the anterior to the posterior direction. With regards to the arch form, the angle of the central ray exhibited an increasing pattern as it moved from the anterior to the posterior direction, culminating in its peak value at the lower second premolar cusp region, followed by a consistent decrease. The rotation centre approximately started from the distolateral aspect of the coronoid process and then anteromedially moved to the midline in a curved line passing between the mandibular notch and coronoid process. By using the panorama phantom, we successfully obtained the central ray direction and detected the rotation centre of the panoramic radiography.

A novel method for determining dose distribution on panoramic reconstruction computed tomography images from radiotherapy computed tomography

Purpose

Patients with head and neck cancer (HNC) who undergo dental procedures during radiotherapy (RT) face an increased risk of developing osteoradionecrosis (ORN). Accordingly, new tools must be developed to extract critical information regarding the dose delivered to the teeth and mandible. This article proposes a novel approach for visualizing 3-dimensional planned dose distributions on panoramic reconstruction computed tomography (pCT) images.

Materials and Methods

Four patients with HNC who underwent volumetric modulated arc therapy were included. One patient experienced ORN and required the extraction of teeth after RT. In the study approach, the dental arch curve (DAC) was defined using an open-source platform. Subsequently, pCT images and dose distributions were generated based on the new coordinate system. All teeth and mandibles were delineated on both the original CT and pCT images. To evaluate the consistency of dose metrics, the Mann-Whitney U test and Student t-test were employed.

Results

A total of 61 teeth and 4 mandibles were evaluated. The correlation coefficient between the 2 methods was 0.999, and no statistically significant difference was observed (P>0.05). This method facilitated a straightforward and intuitive understanding of the delivered dose. In 1 patient, ORN corresponded to the region of the root and the gum receiving a high dosage (approximately 70 Gy).

Conclusion

The proposed method particularly benefits dentists involved in the management of patients with HNC. It enables the visualization of a 3-dimensional dose distribution in the teeth and mandible on pCT, enhancing the understanding of the dose delivered during RT.

Dental bitewing radiographs segmentation using deep learning-based convolutional neural network algorithms

OBJECTIVES

Dental radiographs, particularly bitewing radiographs, are widely used in dental diagnosis and treatment Dental image segmentation is difficult for various reasons, such as intricate structures, low contrast, noise, roughness, and unclear borders, resulting in poor image quality. Recent developments in deep learning models have improved performance in analyzing dental images. In this research, our primary objective is to determine the most effective segmentation technique for bitewing radiographs based on different metrics: accuracy, training time, and the number of training parameters as a reflection of architectural cost.

METHODS

In this research, we employ several deep learning models, namely Resnet-18, Resnet-50, Xception, Inception Resnet v2, and Mobilenetv2, to segment bitewing radiographs. The process begins by importing the radiographs into MATLAB®(MathWorks Inc), where the images are first improved, then segmented using the graph cut method based on regions to produce a binary mask that distinguishes the background from the original X-ray.

RESULTS

The deep learning models were trained on 298 and 99 radiograph training and validation sets and were evaluated using 99 images from the testing set. We also compare the segmentation model using several criteria, including accuracy, speed, and size, to determine which network is superior. Furthermore, we compare our findings with prior research to provide a comprehensive understanding of the advancements made in dental image segmentation. The accurate segmentation achieved was 93.67% and 94.42% by the Resnet-18 and Resnet-50 models, respectively.

CONCLUSION

This research advances dental image analysis and facilitates more accurate diagnoses and treatment planning by determining the best segmentation technique. The outcomes of this study can guide researchers and practitioners in selecting appropriate segmentation methods for practical dental image analysis.

Influence of CBCT-derived panoramic curve variability in the measurements for dental implant planning

OBJECTIVE

To investigate whether the curve markings performed prior to panoramic and cross-sectional reconstructions can influence the planning of oral implants.

METHODS

Twenty oral radiologists landmarked the reference panoramic curves in 25 CBCT scans of the mandible. Bone height was measured on the resulting cross-sectional slices in the edentulous region of the lower first molar. The following data were recorded: (1) number of landmarks used to build each reference curve; (2) shape of the reference curve (inverted "U", inverted "V" or "horseshoe"); and (3) measurement in the first molar region. The data were assessed for variability based on the number of landmarks, the shape of the reference curve, and the measurements obtained.

RESULTS

The number of landmarks used to guide the panoramic reconstruction varied among radiologists (p < 0.05), but most of them draw curves in inverted "U" shape (68-100%). The reproducibility of the measurements taken in the edentulous mandibular first molar region was excellent (84.7%). The number of landmarks and the shape of the curve did not have a significant influence on the reproducibility of the measurements (p > 0.05).

CONCLUSION

Variations of the operator-dependent steps during the panoramic reconstructions occur but do not play a significant part changing the measurements taken for oral implant planning.

[Oral panorama reconstruction method based on pre-segmentation and Bezier function]

For patients with partial jaw defects, cysts and dental implants, doctors need to take panoramic X-ray films or manually draw dental arch lines to generate Panorama images in order to observe their complete dentition information during oral diagnosis. In order to solve the problems of additional burden for patients to take panoramic X-ray films and time-consuming issue for doctors to manually segment dental arch lines, this paper proposes an automatic panorama reconstruction method based on cone beam computerized tomography (CBCT). The V-network (VNet) is used to pre-segment the teeth and the background to generate the corresponding binary image, and then the Bezier curve is used to define the best dental arch curve to generate the oral panorama. In addition, this research also addressed the issues of mistakenly recognizing the teeth and jaws as dental arches, incomplete coverage of the dental arch area by the generated dental arch lines, and low robustness, providing intelligent methods for dental diagnosis and improve the work efficiency of doctors.

Calibration of a Catadioptric System and 3D Reconstruction Based on Surface Structured Light

In response to the problem of the small field of vision in 3D reconstruction, a 3D reconstruction system based on a catadioptric camera and projector was built by introducing a traditional camera to calibrate the catadioptric camera and projector system. Firstly, the intrinsic parameters of the camera and the traditional camera are calibrated separately. Then, the calibration of the projection system is accomplished by the traditional camera. Secondly, the coordinate system is introduced to calculate, respectively, the position of the catadioptric camera and projector in the coordinate system, and the position relationship between the coordinate systems of the catadioptric camera and the projector is obtained. Finally, the projector is used to project the structured light fringe to realize the reconstruction using a catadioptric camera. The experimental results show that the reconstruction error is 0.75 mm and the relative error is 0.0068 for a target of about 1 m. The calibration method and reconstruction method proposed in this paper can guarantee the ideal geometric reconstruction accuracy.

A Fast Automatic Reconstruction Method for Panoramic Images Based on Cone Beam Computed Tomography

Panoramic images have been widely used in the diagnosis of dental diseases. In the process of panoramic image reconstruction, the position of the dental arch curve usually affects the quality of display content, especially the completion level of the panoramic image. In addition, the metal implants in the patient’s mouth often lead the contrast of the panoramic image to decrease. This paper describes a method to automatically synthesize panoramic images from dental cone beam computed tomography (CBCT) data. The proposed method has two essential features: the first feature is that the method can detect the dental arch curve through axial maximum intensity projection images over different ranges, and the second feature is that our method is able to adjust the intensity distribution of the implant in critical areas, to reduce the impact of the implant on the contrast of the panoramic image. The proposed method was tested on 50 CBCT datasets; the panoramic images generated by this method were compared with images attained from three other commonly used approaches and then subjectively scored by three experienced dentists. In the comprehensive image contrast score, the method in this paper has the highest score of 11.16 ± 2.64 points. The results show that the panoramic images generated by this method have better image contrast.

Dental Images' Segmentation Using Threshold Connected Component Analysis

Recent advances in medical imaging analysis, especially the use of deep learning, are helping to identify, detect, classify, and quantify patterns in radiographs. At the center of these advances is the ability to explore hierarchical feature representations learned from data. Deep learning is invaluably becoming the most sought out technique, leading to enhanced performance in analysis of medical applications and systems. Deep learning techniques have achieved great performance results in dental image segmentation. Segmentation of dental radiographs is a crucial step that helps the dentist to diagnose dental caries. The performance of these deep networks is however restrained by various challenging features of dental carious lesions. Segmentation of dental images becomes difficult due to a vast variety in topologies, intricacies of medical structures, and poor image qualities caused by conditions such as low contrast, noise, irregular, and fuzzy edges borders, which result in unsuccessful segmentation. The dental segmentation method used is based on thresholding and connected component analysis. Images are preprocessed using the Gaussian blur filter to remove noise and corrupted pixels. Images are then enhanced using erosion and dilation morphology operations. Finally, segmentation is done through thresholding, and connected components are identified to extract the Region of Interest (ROI) of the teeth. The method was evaluated on an augmented dataset of 11,114 dental images. It was trained with 10 090 training set images and tested on 1024 testing set images. The proposed method gave results of 93% for both precision and recall values, respectively.