Dental X-ray Images Research Articles

Removal of various Noises in Dental X-ray Images using Selective Median Filter

Image processing plays major role to provide additional information in medical diagnosis. Input images contain picture information as well as noise information. Noise information is added with the images during signal acquisition stage or in the transmission of image data. Salt & Pepper noise, Gaussian noise and Speckle noise is the major noises introduced in the images. Noise information may be interpreted as data and it may lead to severe problem. Linear and Non-linear filters are used to reduce these noises in the images. In medical image analysis, non-linear filters are preferred over linear filters because it preserves edge information. Dental X-ray image is used to identify the cavities and its depth. Average filter, median filter and wiener filter are the classical techniques used in many image processing applications. In this paper, three different noises (Salt &pepper, Gaussian and Speckle noise) are added and different filters (Average filters, median filter, Wiener filter) performances are analysed with the PSNR, SNR and MSE. Analysis shows that median filter is suitable for reducing salt & pepper noise and wiener filter is suitable for reducing Gaussian noise and speckle noise in the dental x-ray images. Selective median filter is a modified wiener filter. Median filter is used for the pixel value 0 and 255.For other pixel values wiener filter is used. Selective median filter is giving better result than traditional techniques.

The determination of age and gender by implementing new image processing methods and measurements to dental X-ray images

All of the features used to identify and distinguish people from others constitute that person's identity. For any reason, a person's identity may need to be identified and distinguished from other people. Authorities provided the credentials of a living or dead person in such cases from the forensic institutions. The identification process must be done correctly. In this study, specific measurement calculations were made on dental x-ray images to determine age and gender. Age and gender information of the persons were systematically determined by working with panoramic dental x-ray images. Panoramic dental x-ray images were taken out of bounds, and a total of 1315 tooth images and 162 different tooth groups were used. These images have been subjected to 3 different preprocess operations. Each preprocessed image is recorded in different (M1, M2, M3) folders. Then, image processing techniques applied for the first time to the tooth images (Area, Perimeter, Center of gravity, Similarity ratio, Radius calculation) were applied. This information of the teeth is also kept in separate XML (XMLlist-1, 2, 3) files. The application was developed in C # programming language. The user loads the tooth image into the application. This image can be predicted by comparing it with the comparison group (area, etc.) after the desired preprocessing. The highest estimated age and gender estimates are 100% and 95%, respectively.

Nanocrystalline bismuth oxyiodides thick films for X-ray detector

Materials such as PbI2, HgI2 and PbO are widely used to fabricate flat panel X-ray imaging detector because of high X-ray stopping power (attenuation coefficient). In general, the stopping power (Z4/E3) depends on high atomic number (Z) of the material and energy (E) of the X-ray radiation. In the present study, high atomic numbered bismuth oxyiodides such as BiOI and Bi5O7I nanocrystals were synthesized using a novel process and used in the device fabrication. Thick films of both the samples were coated on the top of patterned metal electrode and interfaced with a source meter to readout the electrical variation for 3.2 s illumination of X-ray using 70 kV real-time dental X-ray imaging machine. The observed result reveals that, the sensitivity increases with the increase of Z value. Also the possibility of utilizing both the nanocrystalline bismuth oxyiodides for the low-dose X-ray detector was explored.

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

Tooth component segmentation is a crucial task in computer-aided design for forensic odontology, especially to estimate chronological age. Tooth segmentation on radiographic data is a very challenging task due to noise, low contrast, and uneven illumination. The Fuzzy C-Means clustering is generally used for image segmentation that allow pixels to be classified into one or more clusters according to their membership value. However, this clustering method still has problems associated with the shifting of cluster centers and sensitivity to the overlapping intensity distributions between classes. This paper proposes a modified strategy of the conditional spatial Fuzzy C-Means (csFCM) that incorporates global and spatial information into a weighted membership function by replacing the Euclidean distance with the Gaussian kernel distance to increase insensitivity to noise and outliers. The aim of this paper is to divide the tooth into 3 components, i.e. enamel, dentine, and pulp. Therefore, this modified algorithm is preceded by dental X-ray image pre-processing and continued by combining each dental component clusters into one composite image. The tooth image is pre-processed using Contrast Limited Adequate Histogram Equalization (CLAHE) and gamma adjustment to enhance the dental X-ray images quality from the non-uniform lighting. The Gausian kernel-based conditional spatial Fuzzy C-Means (GK-csFCM) segments the dental image into four class clusters, namely enamel, dentine, pulp, and background. Through iterations, the resulting cluster centers are more convergent with real cluster centers, thus ensuring the proposed method improves the drawback of inherent FCM-based methods and further promoting image segmentation performance. The experimental results on the real dental X-ray images showed that GK-csFCM has better performance than the typical FCM and csFCM clustering algorithms in terms of both qualitative and quantitative metrics, i.e. accuracy, specificity, sensitivity, and precision.

A Novel Technique to Detect Caries Lesion Using Isophote Concepts

Background and ObjectivesDental caries is one of the most common painful and infectious oral diseases. Early detection of caries lesion prevents the spreading of infection. Generally, dentists use x-ray images to locate the lesion's position. Dental x-ray images have poor intensity which results difficulties in finding exact affected area at a glance. Due to scarcity of dentists at government hospital, it becomes very difficult for the dentists to treat large number of patients in a short span of time. The objective of this work is to design a system to assist dentists to detect caries lesion quickly and more accurately. Deep learning based method is not suitable for this application because there is not enough training set is available to prepare the pre-trained model properly for deep learning. Traditional handcrafted method is desirable for such situation. MethodsDental x-ray not only contains the image of teeth and bonny structure of the jaws but also the tissues within the gum regions. So normal texture based segmentation is not enough to detect the caries lesion. In x-ray, caries lesion looks like a catchment basin, in which the depth at the center is maximum. Isophote along with geodesic active contour method is suitable to model such property of caries lesion. But prior to that multistage background elimination is essential to locate the suspected caries region. Ramdomness calculation and rescaling of that value on the basis of a small training data set is the first part of this multi stage background elimination process. Initial background elimination is performed on the basis of modified k-means clustering upon the entropy value and gray scale values of the x-ray image. In this clustering technique the number of cluster is determined automatically based on analyzing the distribution of data points. The clustering technique is immune against over clustering. Most of the caries lesion lies within the teeth region. Hence this region is surrounded by teeth region. This property is also checked to detect the suspected caries lesion and eliminate the background. ResultTill now very limited dental x-ray databases with caries lesion is available online. ‘Digital dental periapical x-ray database for caries screening’ dataset is used to test the method. The proposed method achieved overall 94% of accuracy and average computational time is below 4.5 sec. DiscussionThis is an alternate solution to detect ROI when deep learning technique fails due to lack of exhaustive training set. This approach fails to generate correct result if resolution of the x-ray image is very low. Low resolution images make confusion between randomness and noise. In addition to that catchment basin properties are not identified properly. Due to this carries lesion are not properly identified.

Novel approaches to determine age and gender from dental x-ray images by using multiplayer perceptron neural networks and image processing techniques

Abstract It may be necessary to determine the identity or gender of a person for any reason (disasters, inheritance etc.). In such cases, forensic medical institutions are asked for help. Forensic science institutions try to estimate the age of people's teeth and bones. In this study, a novel algorithm was developed to keep these predictions at the highest level and to obtain definite results. The data base of 162 different tooth classes is created manually. All image sizes are 150×150 pixels. First, image preprocessing techniques have been applied to teeth images. These preprocessing techniques were first applied to teeth images. After this process, the segmentation process of the teeth images was performed to extract the feature by novel segmentation algorithm. Segmentation can be done automatically and dynamically. Numerical data obtained as a result of feature extraction from dental images is presented as an inputs to Multi layer perceptron neural network. In application, feature reduction can be performed. Thanks to the originally developed algorithm, the highest success rates were obtained with the highest 99.9% (full segment) and 100% (notfull segment) classification. After classification, for many dental groups the age estimate is performed with zero error. Application was developed as a multidisciplinary study.

Locating Anatomical Landmarks on 2D Lateral Cephalograms Through Adversarial Encoder-Decoder Networks

Locating anatomical landmarks in a cephalometric X-ray image is a crucial step in cephalometric analysis. Manual landmark localization suffers from inter- and intra-observer variability, which makes developing automated localization methods urgent in clinics. Most of the existing techniques follow the routine thoughts which estimate numerical values of displacements or coordinates for the target landmarks. Additionally, there are no reported applications of generative adversarial networks (GAN) in cephalometric landmark localization. Motivated by these facts, we propose a new automated cephalometric landmark localization method under the framework of GAN. The principle behind our approach is fundamentally different from the conventional ones. It trained an adversarial network under the framework of GAN to learn the mapping from features to the distance map of a specific target landmark. Namely, the output of the adversarial network in this paper is image data, instead of displacements or coordinates as the conventional approaches. Based on the trained networks, we can predict the distance maps of all target landmarks in a new cephalometric image. Subsequently, the target landmarks are detected from the predicted distance maps by an approach similar to regression voting. Experimental results validate the good performance of our method in localization of cephalometric landmarks in dental X-ray images.

Classification of Radiolucency in Dental X-Ray Image

Health is the greatest gift to any human being. Growth of the nation depends on the health of every individual. To maintain health and hygiene, a human being must eat good food. For eating healthy food teeth plays an important role. The teeth being a small part of the body plays a very critical part in digestion. Many times due to time constraints patient cannot go to the hospital at right time or wants to get a second opinion. So, in this aspect, the proposed system is created to diagnose the status of the tooth automatically. The anticipated system takes x-ray images as input and classifies the output as a category of radiolucency that it falls under. The classification of the tooth is done by using Multi-Layer Perceptron (MLP), SMO, KNN. Features are extracted using both, Spatial and Frequency domain. Classification is done using Weka tool.

Maintaining patient oral health by using a xeno-genetic spiking neural network

Many people are affected by dental problems that have serious long-term effects. Thus, oral hygiene maintenance is necessary to prevent dry mouth tooth decay, bad breath, and cold sores, which adversely affect oral health. In this paper, we investigated patients’ oral health by applying optimized machine learning techniques to successfully identify potential pathologies present in the oral cavity. During the oral health analysis process, dental X-ray images are collected from a patient and examined by using the xeno-genetic spiking neural network. This method effectively examines tooth structure, gaps between teeth, and positioning of teeth such as molars, premolars, and incisors. The resulting information facilitates oral health maintenance. Finally, we evaluated the efficiency of the system with the help of computerized dental applications.

GrabCut algorithm for dental X‐ray images based on full threshold segmentation

Teeth are difficult to be destroyed due to their corrosion resistance, high melting point and hardness. Dental biometrics can therefore provide assistance in human forensic identification, especially to the unknown corpses. One of the key issue in dental based human identification is the segmentation of Dental X-ray images. In this paper, a novel segmentation algorithm has been proposed for this purpose. The proposed algorithm is based on full threshold segmentation. We first obtain the outline image set Iwholen and crown image set Icrownm of the complete target tooth. Morphological open operation is then applied to the difference images of Iwholen and Icrownm. Subsequently, the most complete target tooth image and its corresponding crown image are selected. Getting independent target tooth image Icontour and its crown image Icrown from these two images. Median filtering is applied to the synthetic image of Icontour and Icrown, and the resulted image will be used as the Mask for GrabCut to obtain the target tooth image. Experimental results show our proposed algorithm can effectively overcome the problems of uneven grayscale distribution and adhesion of adjacent crowns in dental X-ray images. It can also achieve a high segmentation accuracy and outperform related methods to be compared.

New approaches to determine age and gender in image processing techniques using multilayer perceptron neural network

As a result of some events (disasters, inheritance, disappearances etc.), age and gender determination can be vital for people. Forensic medical institutions make the determination of age by examining the structures such as teeth and bones. Procedures for forensic science are currently estimated manually according to certain morphological findings on the tooth. In this study, 1313 panoramic dental images were used automatically to estimate age. Image preprocessing is applied on these images. Trapezoidal teeth are corrected in the coordinate plane to obtain more accurate and standard results. In the study, the correction process is done with original and novel developed algorithm. Dental images are automatically and dynamically segmented and feature vectors are created by extracting their features. The generated feature vectors are dynamic and presented as inputs to the Multilayer Perceptron Neural Network. Depending on the request, the number of input count reduction process can be performed. In this study, age and gender were determined from dental x-ray images with novel and originally developed algorithm. The application is written in C # programming language. In some tooth groups, the highest classification rate of 100% and age determination with 0 error were performed. With this study, age determination in forensic science will be more accurate.

Automatic computer-aided caries detection from dental x-ray images using intelligent level set

Dental diseases have high risk of affection across the globe and mostly in adult population. The analysis of dental X-ray images has some difficulties in comparison to other medical images, which makes segmentation a more challenging process. One of the most important and yet largely unsolved issues in the level set method framework is the efficiency of signed force, speed function and initial contour (IC) generation. In this paper, a new segmentation method based on level set (LS) is proposed in two phases; IC generation using morphological information of image and intelligent level set segmentation utilizing motion filtering and back propagation neural network. The segmentation results are efficient and accurate as compared to other studies. The new approach to isolate each segmented teeth image is proposed by employing integral projection technique and feature map designed for each tooth to extract the local information and therefore to detect caries area. The achieved overall performance of the proposed segmentation method was evaluated at 120 periapical dental radiograph (X-ray), with images at 90% and the detection accuracy of 98%.

Segmentation of dental X-ray images in medical imaging using neutrosophic orthogonal matrices

Abstract Over the last few decades, the advance of new technologies in computer equipment, cameras and medical devices became a starting point for the shape of medical imaging systems. Since then, many new medical devices, e.g. the X-Ray machines, computed tomography scans, magnetic resonance imaging, etc., accompanied with operational algorithms inside has contributed greatly to successful diagnose of clinical cases. Enhancing the accuracy of segmentation, which plays an important role in the recognition of disease patterns, has been the focus of various researches in recent years. Segmentation using advanced fuzzy clustering to handle the problems of common boundaries between clusters would tackle many challenges in medical imaging. In this paper, we propose a new fuzzy clustering algorithm based on the neutrosophic orthogonal matrices for segmentation of dental X-Ray images. This algorithm transforms image data into a neutrosophic set and computes the inner products of the cutting matrix of input. Pixels are then segmented by the orthogonal principle to form clusters. The experimental validation on real dental datasets of Hanoi Medical University Hospital, Vietnam showed the superiority of the proposed method against the relevant ones in terms of clustering quality.

An automated and hybrid method for cyst segmentation in dental X-ray images

The dental X-ray image has poor contrast and uneven exposure which results in the lack of reliable separation between various parts of teeth, which makes the segmentation of cyst very tedious. A unique hybrid automated technique has been proposed to detect and extract the cystic region using circularly symmetric isophote properties and fast marching method.The isophote curvature is the curve connecting the same intensity pixels. Each Isophote curvature line has an isocenter associated with it. Among them, the isocenter which is having a maximum response in the isophote center map to be concluded as the most likely estimate for locating the cystic region. This Maximum IsoCenter (MIC) is the seed point to the model-based segmentation of fast marching method. The fast marching algorithm (FMM) is like Dijkstra’s algorithm, and it follows the shortest path from seed area, where the information flows outward only. It works systematically to make it fast, and it is a one-pass method because each point is touched only once mainly. This fast marching method extracts the cystic region boundary very effectively and efficiently. This two-stage hybrid method is an automated, robust, and fast method for solving the complex problem of cyst segmentation. The average execution time calculated is 2.8 s and the accuracy achieved is 95%. The performance outcomes show that the proposed segmentation technique has the high correlation with the manual method. Therefore, the combination of model-based and feature based segmentation of the dental X-ray images has great potential in diagnosis of dental diseases and plays a significant role in the development of automated systems. The automated segmentation computerizes or automates the diagnostic method so that huge number of patients can be monitored with the same assured accuracy. High-speed computers are helpful in attaining fast and precise results. To extend the patient care to remote areas, the faster communication is possible by computer networks

A Comparative Analysis on the Dental X-ray Image Segmentation Approaches

A Comparative Analysis on the Dental X-ray Image Segmentation Approaches

Identification based Dental Image

Identification (matching) system is a recognition and classification form that helps in identifying the identity depending on his/her dental X-Ray image. This work displays a new method to identify a person from his/her dental X-Ray image that is widely used in forensic, border organization, parenting selecting and investigations. The goal of this paper is to design an efficient identification model depending on dental X-Ray image of identities and that can be useful to identify the unknown Individuals who died. The techniques that used were image processing and features extraction techniques which had been added to improve the goal. The best result attained from the dental X-Ray model was 89% as an identification rate.

Dental X-ray Image Segmentation using Gaussian Kernel-Based in Conditional Spatial Fuzzy C-means

Dental X-ray image segmentation is a difficult task because of intensity inhomogeneities among various regions, low image quality due to noise and low contrast errors of data scanning. In this paper, we proposed a new conditional spatial fuzzy C-means algorithm with Gaussian kernel function to facilitate dental X-ray image segmentation. The Gaussian kernel function is used as an objective function of conditional spatial fuzzy C-means algorithm to substitute the Euclidian distance. Performance evaluation of the proposed algorithm was carried on dental X-ray from different teeth of some panoramic radiographs. The average of false negative fraction (FNF) and false positive fraction (TPF) values using proposed algorithm better than conditional spatial fuzzy C-means algorithm but vise versa for true positive volume fraction (FPF) value. The segmentation result of the proposed algorithm effectively recognizes tooth region as main part of the dental X-ray image.

Evaluation of Image Enhancement Techniques of Dental X-Ray Images

Objectives: This study focuses on evaluation of the performance of various image enhancement techniques which were applied on dental X-ray images. Methods/Analysis: The images were calculated for comparing between input images and out images from three enhancement methods: imadjust, histogram equalization (HE) and contrast limited adaptive histogram equalization (CLAHE). A collection of eight dental x-ray images are chosen to apply these techniques on them. The x-ray images are -in general- low in contrast and dosage of radiation. This loss of image quality can be treated with enhancement process. Four quality image factors were used to evaluate the resulted images involved Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Maximum Error (MAXERR) and (L2rat). Findings: The quality of images had been raised and improved by these techniques for diagnosing goal. The results show that the enhancement methods chose to enhance the collected images led to more qualified images than original ones. Application/Improvements: The CLAHE method is better than other enhancement methods according to the values of quality image factors and the evaluation of expert dentists. Keywords: Contrast, Dental X-ray Images, Image Enhancement, Image Histogram, Image Quality

Human identification with dental panoramic radiographic images

Dental panoramic radiographic images are commonly used as biometrics for human identification. In this study, a novel method is presented for identifying humans by matching 2D panoramic dental X-ray images. Each tooth is first identified and labeled with support vector machines and probabilistic graphical models. Missing teeth and dental restorations are also detected. Then, matching scores between images are calculated according to tooth-wise appearance and geometric similarities by taking dental restorations into account. The method is tested on a dataset including 206 dental panoramic X-ray images of 170 different subjects. The proposed method has 81% rank-1 accuracy and 89% rank-2 accuracy.

Segmentation of dental X-ray images in medical imaging using neutrosophic orthogonal matrices

Over the last few decades, the advance of new technologies in computer equipment, cameras and medical devices became a starting point for the shape of medical imaging systems. Since then, many new medical devices, e.g. the X-Ray machines, computed tomography scans, magnetic resonance imaging, etc., accompanied with operational algorithms inside has contributed greatly to successful diagnose of clinical cases. Enhancing the accuracy of segmentation, which plays an important role in the recognition of disease patterns, has been the focus of various researches in recent years. Segmentation using advanced fuzzy clustering to handle the problems of common boundaries between clusters would tackle many challenges in medical imaging. In this paper, we propose a new fuzzy clustering algorithm based on the neutrosophic orthogonal matrices for segmentation of dental X-Ray images. This algorithm transforms image data into a neutrosophic set and computes the inner products of the cutting matrix of input. Pixels are then segmented by the orthogonal principle to form clusters. The experimental validation on real dental datasets of Hanoi Medical University Hospital, Vietnam showed the superiority of the proposed method against the relevant ones in terms of clustering quality.