Diagnosis of Pulpitis from Dental Panoramic Radiograph Using Histogram of Gradients with Discrete Wavelet Transform and Multilevel Neural Network Techniques

Radiograph plays the major role of diagnosis, treatment and surgery in the Dental field. There are many types of Intra and extra oral radiographs in which Dental Panoramic Radiograph helps in visualising the full view of the oral cavity. Pulpitis is the dental diseases caused due to the inflammation of the dental pulp from untreated caries, trauma or multiple restorations which leads to Apical Periodontitis. To predict the severity of pulp vitality pulp inflammation has to be evaluated. Radiographs helps the dentist in diagnosing the extent of tooth decay and inflammation. An automatic diagnostic model is proposed using robust algorithms to diagnose pulpits. Dental Panoramic Radiograph is used in the proposed research to diagnose the pulpitis and to classify the normal teeth from the pulpitis. The collected images are pre-processed using Histogram Equalization and filtered using Gaussian and Median filters. Modified K-Means algorithm is applied to segment the bony and teeth area from the oral cavity area. Integral Histogram of Gradients with Discrete Wavelet Transform feature extraction techniques and Multi-Layer Neural Network Classifier is proposed to achieve the accuracy of 91.09% which can be used as an assistive tool by the dentist to diagnose pulpitis.

Inisialisasi Otomatis Metode Level Set untuk Segmentasi Objek Overlapping pada Citra Panorama Gigi

<p class="Abstrak">Penelitian tentang segmentasi gigi individu telah banyak dilakukan dan memperoleh hasil yang baik. Namun, ketika dihadapkan kepada gigi overlap maka hal ini menjadi sebuah tantangan. Untuk memisahkan dua gigi overlap, maka perlu mengekstrak objek overlap terlebih dahulu. Metode level set banyak digunakan untuk melakukan segmentasi objek overlap, namun memiliki kelemahan yaitu perlu didefinisikan inisial awal metode level set secara manual oleh pengguna. Dalam penelitian ini diusulkan strategi inisialisasi otomatis pada metode level set untuk melakukan segmentasi gigi overlap menggunakan Hierarchical Cluster Analysis (HCA) pada citra panorama gigi. Tahapan strategi yang diusulkan terdiri dari preprocessing dimana di dalamnya ada proses perbaikan, rotasi dan cropping citra, dilanjutkan proses inisialisasi otomatis menggunakan algoritma HCA , dan yang terakhir segmentasi menggunakan metode level set. Hasil evaluasi menunjukkan bahwa strategi yang diusulkan berhasil melakukan inisialisasi secara otomatis dengan akurasi 73%. Hasil evaluasi segmentasi objek overlap cukup memuaskan dengan rasio misclassification error 0,93% dan relative foreground area error 24%. Dari hasil evaluasi menunjukkan bahwa strategi yang diusulkan dapat melakukan inisialisasi otomatis dengan baik. Inisialisasi yang tepat menghasilkan segmentasi yang baik pada metode level set.</p><p><em><strong><br /></strong></em></p><p><em><strong>Abstract</strong></em></p><p class="Judul2"><em>Individual teeth segmentation has done a lot of the recent research and obtained good results.</em><em> W</em><em>hen faced with overlapping teeth, this is quite challenging. To separate overlapping teeth, it is necessary to extract the overlapping object first. </em><em>The l</em><em>evel set method is widely used to segment overlap objects, but it has a limitation that needs to define the initial</em><em> </em><em>level set method manually by the user. This research proposes an automatic initialization strategy for the level set method to segment overlapping teeth using Hierarchical Cluster Analysis on dental panoramic radiograph images. The proposed strategy stage consists of preprocessing </em><em>where</em><em> there </em><em>are</em><em> several process</em><em>es</em><em> of enhancement, rotation</em><em>,</em><em> and cropping of the image, Then the automatic initialization process uses the HCA algorithm and the last is segmentation using the level set method. The evaluation results show that the proposed strategy is successful in carrying out automatic initialization with an accuracy of 73%. The results of the overlap object segmentation evaluation are satisfactory with a misclassification error ratio of 0.93% and a relative foreground area error of 24%. The evaluation results show that the proposed strategy can carry out automated initialization well. Proper initialization results can perform good segmentation of the level set method.</em></p><p><em><strong><br /></strong></em></p>

Multi-Task Deep Learning Model for Classification of Dental Implant Brand and Treatment Stage Using Dental Panoramic Radiograph Images

It is necessary to accurately identify dental implant brands and the stage of treatment to ensure efficient care. Thus, the purpose of this study was to use multi-task deep learning to investigate a classifier that categorizes implant brands and treatment stages from dental panoramic radiographic images. For objective labeling, 9767 dental implant images of 12 implant brands and treatment stages were obtained from the digital panoramic radiographs of patients who underwent procedures at Kagawa Prefectural Central Hospital, Japan, between 2005 and 2020. Five deep convolutional neural network (CNN) models (ResNet18, 34, 50, 101 and 152) were evaluated. The accuracy, precision, recall, specificity, F1 score, and area under the curve score were calculated for each CNN. We also compared the multi-task and single-task accuracies of brand classification and implant treatment stage classification. Our analysis revealed that the larger the number of parameters and the deeper the network, the better the performance for both classifications. Multi-tasking significantly improved brand classification on all performance indicators, except recall, and significantly improved all metrics in treatment phase classification. Using CNNs conferred high validity in the classification of dental implant brands and treatment stages. Furthermore, multi-task learning facilitated analysis accuracy.

SEPARATION OF OVERLAPPING OBJECT SEGMENTATION USING LEVEL SET WITH AUTOMATIC INITALIZATION ON DENTAL PANORAMIC RADIOGRAPH

To extract features on dental objects, it is necessary to segment the teeth. Segmentation is separating between the teeth (objects) with another part than teeth (background). The process of segmenting individual teeth has done a lot of the recently research and obtained good results. However, when faced with overlapping teeth, this is quite challenging. Overlapping tooth segmentation using the latest algorithm produces an object that should be segmented into two objects, instantly becoming one object. This is due to the overlapping between two teeth. To separate overlapping teeth, it is necessary to extract the overlapping object first. Level set method is widely used to segment overlap objects, but it has a limitation that needs to define the initial level set method manually by the user. In this study, an automatic initialization strategy is proposed for the level set method to segment overlapping teeth using hierarchical cluster analysis on dental panoramic radiographs images. The proposed strategy was able to initialize overlapping objects properly with accuracy of 73%. Evaluation to measure quality of segmentation result are using misscassification error (ME) and relative foreground area error (RAE). ME and RAE were calculated based on the average results of individual tooth segmentation and obtain 16.41% and 52.14%, respectively. This proposed strategy are expected to be able to help separate the overlapping teeth for human age estimation through dental images in forensic odontology.

Segmentasi Gigi pada Dental Panoramic Radiograph untuk Identifikasi Manusia

<p><em>Abstrak</em> – <strong>Indonesia memiliki tingkat kerawanan tinggi terhadap bencana alam dan kecelakaan yang mengakibatkan terjadinya korban massal. Banyak cara untuk mengidentifikasi korban, salah satunya menggunakan citra gigi. Gigi merupakan bagian dari tubuh yang lebih tahan lama karena struktur gigi yang padat dan kuat. </strong><strong>Identifikasi menggunakan sarana gigi dapat dilakukan dengan cara membandingkan data gigi yang telah diperoleh dari pemeriksaan gigi jenazah yang tidak dikenal (data <em>postmortem</em>) dengan data gigi yang sebelumnya pernah dibuat (data <em>antemortem</em>). Terdapat beberapa tahapan dalam melakukan identifikasi korban menggunakan citra gigi. Tahapan yang dilakukan oleh peneliti adalah tahap segmentasi gigi. Pertama, citra dilakukan <em>cropping</em> hingga mendapatkan dimensi berukuran 1564×589 piksel serta perbaikan citra menggunakan <em>Histogram Equalization</em>. Selanjutnya dilakukan pemisahan citra gigi menggunakan metode <em>Integral Projection</em> dilengkapi penggunaan <em>Spline Interpolation</em> untuk menggambar garis pemisah antara rahang atas-bawah serta gigi tunggal. Tiap citra memiliki nilai n-blok kolom yang berbeda sehingga dibutuhkan parameter sebesar 3 hingga 30 n-blok kolom untuk membentuk garis pemisah rahang atas-bawah. Citra gigi berjenis <em>Dental Panoramic Radiograph</em>. Hasil evaluasi kesalahan<em> </em>terkecil saat melakukan pemisahan rahang atas-bawah menggunakan <em>Horizontal Integral Projection</em> sebesar 56.8% dengan nilai n-blok kolom adalah 8 dan saat<em> </em>segmentasi gigi pada tahap <em>Vertical Integral Projection</em> sebesar 38.27% dengan nilai <em>average filter</em> adalah<em> </em>17.</strong></p><p><em>Abstract</em> – <strong>Indonesia has a high level of vulnerability to natural disasters and accidents that result in mass casualties. There are many ways to identify victims, especially by using dental images. The teeth are part of the body that are more durable because of the solid and strong tooth structure. Identification using dental images can be done by comparing dental data that has been obtained from unknown victim dental examination (postmortem data) with dental data previously made (antemortem data). There are several stages in identifying victims using dental images and researcher worked on tooth segmentation stage. First, the image need to cropped up to get dimensions size of 1564</strong><strong>×</strong><strong>589 pixels and improved contrast using Histogram Equalization method. Then, tooth separation is performed using Integral Projection method which is equipped with the use of Spline Interpolation to draw the separator line between the upper-lower jaws and single tooth. Each image has a different n-block column value, so researcher selected range number of n-block column is between 3-30. In this reseach, dental panoramic radiographs are used. The smallest error rate in the images is found when performing an Integral Projection to separate upper and lower jaws by 56.8% with n-block column value = 8 and when separating each tooth from the image by 38.27% with average filter value = 17.</strong></p><p><strong><em>Keywords</em></strong> – <em>Antemortem, Postmortem, Segmentation, Histogram Equalization, Integral Projection, Spline Interpolation</em></p>