scholarly journals Deep learning for early dental caries detection in bitewing radiographs

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shinae Lee ◽  
Sang-il Oh ◽  
Junik Jo ◽  
Sumi Kang ◽  
Yooseok Shin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Dental Caries ◽  
Diagnostic Performance ◽  
Preventive Treatment ◽  
Caries Detection ◽  
Initial Caries ◽  
Sensitivity Ratio ◽  
Accurate Performance ◽  
Increased Sensitivity ◽  
Deep Learning Model

AbstractThe early detection of initial dental caries enables preventive treatment, and bitewing radiography is a good diagnostic tool for posterior initial caries. In medical imaging, the utilization of deep learning with convolutional neural networks (CNNs) to process various types of images has been actively researched, with promising performance. In this study, we developed a CNN model using a U-shaped deep CNN (U-Net) for caries detection on bitewing radiographs and investigated whether this model can improve clinicians’ performance. The research complied with relevant ethical regulations. In total, 304 bitewing radiographs were used to train the CNN model and 50 radiographs for performance evaluation. The diagnostic performance of the CNN model on the total test dataset was as follows: precision, 63.29%; recall, 65.02%; and F1-score, 64.14%, showing quite accurate performance. When three dentists detected caries using the results of the CNN model as reference data, the overall diagnostic performance of all three clinicians significantly improved, as shown by an increased sensitivity ratio (D1, 85.34%; D1′, 92.15%; D2, 85.86%; D2′, 93.72%; D3, 69.11%; D3′, 79.06%; p < 0.05). These increases were especially significant (p < 0.05) in the initial and moderate caries subgroups. The deep learning model may help clinicians to diagnose dental caries more accurately.

scholarly journals Deep Learning for Early Dental Caries Detection in Bitewing Radiographs

2021 ◽  
Author(s):  
Shinae Lee ◽  
Sang-il Oh ◽  
Junik Jo ◽  
Sumi Kang ◽  
Yooseok Shin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Dental Caries ◽  
Diagnostic Performance ◽  
Preventive Treatment ◽  
Learning Model ◽  
Caries Detection ◽  
Test Dataset ◽  
Accurate Performance ◽  
Deep Cnn ◽  
Deep Learning Model

Abstract The early detection of incipient dental caries enables preventive treatment, and bitewing radiography is a good diagnostic tool for posterior incipient caries. In the field of medical imaging, the utilization of deep learning with convolutional neural networks (CNNs) to process various types of images has been actively researched and has shown promising performance. In this study, we developed a CNN model using a U-shaped deep CNN (U-Net) for dental caries detection on bitewing radiographs and investigated whether this model can improve clinicians’ performance. In total, 304 bitewing radiographs were used to train the deep learning model and 50 radiographs were used for performance evaluation. The diagnostic performance of the CNN model on the total test dataset was as follows: precision, 63.29%; recall, 65.02%; and F1-score, 64.14%, showing quite accurate performance. When three dentists detected dental caries using the results of the CNN model as reference data, the overall diagnostic performance of all three clinicians significantly improved, as shown by an increased recall ratio (D1, 85.34%; D1', 92.15%; D2, 85.86%; D2', 93.72%; D3, 69.11%; D3', 79.06%). These increases were especially significant in the incipient and moderate caries subgroups. The deep learning model may help clinicians to diagnose dental caries more accurately.

Dental Caries Classification System Using Deep Learning Based Convolutional Neural Network

2020 ◽  
Vol 17 (9) ◽  
pp. 4660-4665
Author(s):  
L. Megalan Leo ◽  
T. Kalpalatha Reddy
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Dental Caries ◽  
Convolutional Neural Network ◽  
Median Filter ◽  
Activation Function ◽  
Radiographic Examination ◽  
Testing Dataset ◽  
The People ◽  
Deep Learning Model

In the modern times, Dental caries is one of the most prevalent diseases of the teeth in the whole world. Almost 90% of the people get affected by cavity. Dental caries is the cavity which occurs due to the remnant food and bacteria. Dental Caries are curable and preventable diseases when it is identified at earlier stage. Dentist uses the radiographic examination in addition with visual tactile inspection to identify the caries. Dentist finds difficult to identify the occlusal, pit and fissure caries. It may lead to sever problem if the cavity left untreated and not identified at the earliest stage. Machine learning can be applied to solve this issue by applying the labelled dataset given by the experienced dentist. In this paper, convolutional based deep learning method is applied to identify the cavity presence in the image. 480 Bite viewing radiography images are collected from the Elsevier standard database. All the input images are resized to 128–128 matrixes. In preprocessing, selective median filter is used to reduce the noise in the image. Pre-processed inputs are given to deep learning model where convolutional neural network with Google Net inception v3 architecture algorithm is implemented. ReLu activation function is used with Google Net to identify the caries that provide the dentists with the precise and optimized results about caries and the area affected. Proposed technique achieves 86.7% accuracy on the testing dataset.

scholarly journals ASSESSMENT OF DENTAL CARIOUS LESIONS BY ICDAS II

2021 ◽  
Vol 21 (1) ◽  
pp. 76-80
Author(s):  
V. Melnik ◽  
L. Gorzov ◽  
S. Melnik ◽  
Ya. Duganchik
Keyword(s):  
Dental Caries ◽  
Age Groups ◽  
Dental Enamel ◽  
Statistical Processing ◽  
Caries Detection ◽  
Average Intensity ◽  
Initial Caries ◽  
Carious Lesions ◽  
Icdas Ii ◽  
Caries Lesions

Introduction. The largest amount of information about the dental caries is provided by the International Caries Detection and Assessment II system (ICDAS II), which is known as evidence-based approach to clinical visual detection of dental caries and enables to detect the stage and depth of carious lesions from the slightest changes in dental enamel to visible cavities affecting dentin. This system has been developed by the group of leading experts in the field of cariology. The results obtained by determining the ICDAS II index contribute to making right clinical decision in the choice of prevention and treatment methods, as well as to predicting the carious progression. The aim of the study is to assess the prevalence and intensity of initial dental caries in people using the ICDAS II index. Materials and methods. A total of 32 patients aged 12 to 25 years were examined. During the dental examination, we assessed the prevalence of dental caries using the ICDAS II. Clinical findings were recorded in oral follow-up charts proposed by the ICDAS Foundation for Epidemiological Studies, which allow us to record dental hard tissue status using six codes: three for assessing carious changes in enamel and three for assessing carious changes in dentine in a sequence of growing severity. Statistical processing of the findings was performed using Student's t-test. Results. Carious lesions were detected in all study participants, their total number was 285, of which 140 (49.1%) had the code 1 and 145 (50.8%) had the code 2 according to the ICDAS II. On average, each of the participants had 9.28 ± 0.67 foci of enamel demineralization. The average number of lesions with codes 1 and 2 by the ICDAS II was respectively 4.54 ± 0.51 and 4.74 ± 0.38 (p> 0.05). The average intensity of dental caries increased with age from 8.29 ± 0.83 in 12-15 year old individuals to 9.39 ± 1.20 in 18-25 year old individuals (p> 0.05), mainly by the growth of the average number of the mean number of caries lesions with the code 1 according to the ICDAS II. Mostly carious lesions are found on the masticatory surfaces, their total number made up 159 (55.7%). 101 (35.4%) caries lesions were found on the vestibular and oral parts of the tooth surfaces, and 25 (8.9%) average lesions were detected on the proximal surfaces. The average intensity of caries detected on the chewing surfaces of the teeth was 5.15 ± 0.49 and was significantly higher than on the vestibular and oral (3.33 ± 0.57, p <0.05) and proximal (0.79 ± 0, 20, p <0.001) surfaces. Conclusion. The obtained results showed a high intensity of carious lesions, with their predominance in the active stages in the two age groups under the study. This proves the appropriateness of using diagnostic ICDAS criteria for early detection of initial caries and its proper treatment.

scholarly journals Automated Radiology Alert System for Pneumothorax Detection on Chest Radiographs Improves Efficiency and Diagnostic Performance

Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1182
Author(s):  
Cheng-Yi Kao ◽  
Chiao-Yun Lin ◽  
Cheng-Chen Chao ◽  
Han-Sheng Huang ◽  
Hsing-Yu Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Diagnostic Performance ◽  
Medical Center ◽  
Characteristic Curve ◽  
Learning Model ◽  
Chest Radiographs ◽  
Alert System ◽  
Before And After ◽  
Set Up ◽  
Deep Learning Model

We aimed to set up an Automated Radiology Alert System (ARAS) for the detection of pneumothorax in chest radiographs by a deep learning model, and to compare its efficiency and diagnostic performance with the existing Manual Radiology Alert System (MRAS) at the tertiary medical center. This study retrospectively collected 1235 chest radiographs with pneumothorax labeling from 2013 to 2019, and 337 chest radiographs with negative findings in 2019 were separated into training and validation datasets for the deep learning model of ARAS. The efficiency before and after using the model was compared in terms of alert time and report time. During parallel running of the two systems from September to October 2020, chest radiographs prospectively acquired in the emergency department with age more than 6 years served as the testing dataset for comparison of diagnostic performance. The efficiency was improved after using the model, with mean alert time improving from 8.45 min to 0.69 min and the mean report time from 2.81 days to 1.59 days. The comparison of the diagnostic performance of both systems using 3739 chest radiographs acquired during parallel running showed that the ARAS was better than the MRAS as assessed in terms of sensitivity (recall), area under receiver operating characteristic curve, and F1 score (0.837 vs. 0.256, 0.914 vs. 0.628, and 0.754 vs. 0.407, respectively), but worse in terms of positive predictive value (PPV) (precision) (0.686 vs. 1.000). This study had successfully designed a deep learning model for pneumothorax detection on chest radiographs and set up an ARAS with improved efficiency and overall diagnostic performance.

Sweet Taste Perception and Dental Caries in 13- to 15-Year-Olds: A Multicenter Cross-Sectional Study

2017 ◽  
Vol 51 (4) ◽  
pp. 443-450 ◽  
Author(s):  
H. Ashi ◽  
C. Lara-Capi ◽  
G. Campus ◽  
G. Klingberg ◽  
P. Lingström
Keyword(s):  
Dental Caries ◽  
Dietary Habits ◽  
Sweet Taste ◽  
Assessment System ◽  
Taste Perception ◽  
Caries Detection ◽  
Caries Experience ◽  
Cross Sectional ◽  
Initial Caries ◽  
Significant Difference

Dietary habits and, in particular, the intake frequency of sucrose are of major importance for the development of dental caries. The perception of sweet taste is believed to have an influence on sucrose intake and therefore affects the predisposition to dental caries. The aim was to study the caries experience and sweet taste perception and to further analyze the possible relationship between the 2 tested variables in 13- to 15-year-old children from 3 different geographical areas. A cross-sectional survey comprising 669 children (220 Italian, 224 Mexican, and 225 Saudi Arabian) was conducted. The children were examined in their school setting. A sweet taste perception level was determined by the sweet taste threshold (TT) and sweet taste preference (TP). The sweet test was performed with sucrose solutions varying in concentration from 1.63 to 821.52 g/L. The International Caries Detection and Assessment System (ICDAS) and DMFS indices were used to diagnose caries. The highest mean value for TT was found for Italian children followed by Saudi and Mexican. Saudi schoolchildren showed the highest mean values for TP and DMFS, followed by Italian and Mexican. A statistically significant difference for TP, TT, DMFS, and initial caries was found between the 3 countries. A weak yet positive correlation was found between taste perception (TT and TP) versus DMFS and manifest caries in all 3 countries (r = 0.137-0.313). The findings of the present study showed a variation in sweet taste perception between the 3 countries, which may influence the caries outcome of the children in the individual countries.

Oral Health Status among Children with Repaired Esophageal Atresia

2020 ◽  
Author(s):  
Cansu Ozsin-Ozler ◽  
Melek D. Turgut ◽  
Meryem Uzamis-Tekcicek ◽  
Tutku Soyer
Keyword(s):  
Oral Health ◽  
Dental Caries ◽  
Esophageal Atresia ◽  
Evaluation System ◽  
Dental Erosion ◽  
Caries Detection ◽  
Team Approach ◽  
Oral Malodor ◽  
Initial Caries ◽  
Swallowing Problems

Abstract Introduction Esophageal atresia (EA) is a congenital anomaly, presenting multifactorial etiology. Swallowing problems and gastroesophageal reflux disease may accompany EA, which have adverse effects on oral health. Materials and Methods In this descriptive study, intraoral examination of the children with repaired EA and of the dental patients without systemic/chronic disease was performed. Dental caries, dental erosion, and halitosis status were evaluated using the International Caries Detection and Evaluation System II, and the Basic Erosive Wear Examination indices as well as the Halimeter, respectively. Results There were 19 (n = 12 male; n = 7 female) case subjects and 16 (n = 10 male; n = 6 female) control subjects whose age ranged between 14 and 72 months. Among cases, 15 children had dental caries (78.9%; initial caries n = 4, moderate caries n = 4, and extensive caries n = 7). Of the controls, 13 had dental caries (81.2%; initial caries n = 5, moderate caries n = 5, and extensive caries n = 3). Although the median scores of decayed, missing, filled teeth (dmft) and decayed, missing, filled surfaces (dmfs)—for primary dentition—were not statistically significantly different between two groups, both dmft and dmfs were found to be higher among the case subjects (p = 0.172 for dmft; p = 0.230 for dmfs). Furthermore, six children with repaired EA had dental abnormalities (in shape, number, or calcification) and six children with repaired EA had dental erosion. The Halimeter measurement was performed for five case children of whom three had oral malodor, and for seven control children of whom two had oral malodor. Conclusion Regular dental counseling adopting the multidisciplinary team approach for patients with EA is necessary to ensure better general and oral health.

scholarly journals Automatic Blob Detection for Dental Caries

2021 ◽  
Vol 11 (19) ◽  
pp. 9232
Author(s):  
Vincent Majanga ◽  
Serestina Viriri
Keyword(s):  
Deep Learning ◽  
Dental Caries ◽  
Data Augmentation ◽  
Active Contours ◽  
Threshold Value ◽  
Detection Methods ◽  
Caries Detection ◽  
Data Set ◽  
Blob Detection ◽  
Carious Lesions

Dental Caries are one of the most prevalent chronic diseases around the globe. Detecting carious lesions is a challenging task. Conventional computer aided diagnosis and detection methods in the past have heavily relied on the visual inspection of teeth. These methods are only effective on large and clearly visible caries on affected teeth. Conventional methods have been limited in performance due to the complex visual characteristics of dental caries images, which consist of hidden or inaccessible lesions. The early detection of dental caries is an important determinant for treatment and benefits much from the introduction of new tools, such as dental radiography. In this paper, we propose a deep learning-based technique for dental caries detection namely: blob detection. The proposed technique automatically detects hidden and inaccessible dental caries lesions in bitewing radio-graphs. The approach employs data augmentation to increase the number of images in the data set to have a total of 11,114 dental images. Image pre-processing on the data set was through the use of Gaussian blur filters. Image segmentation was handled through thresholding, erosion and dilation morphology, while image boundary detection was achieved through active contours method. Furthermore, the deep learning based network through the sequential model in Keras extracts features from the images through blob detection. Finally, a convexity threshold value of 0.9 is introduced to aid in the classification of caries as either present or not present. The process of detection and classifying dental caries achieved the results of 97% and 96% for the precision and recall values, respectively.

Sign in / Sign up

Export Citation Format

Share Document