• Imaging Science in Dentistry
• /
• v.52 no.4
• /
• pp.383-391
• /
• 2022

Purpose: Periodontitis, the most prevalent chronic inflammatory condition affecting teeth-supporting tissues, is diagnosed and classified through clinical and radiographic examinations. The staging of periodontitis using panoramic radiographs provides information for designing computer-assisted diagnostic systems. Performing image segmentation in periodontitis is required for image processing in diagnostic applications. This study evaluated image segmentation for periodontitis staging based on deep learning approaches. Materials and Methods: Multi-Label U-Net and Mask R-CNN models were compared for image segmentation to detect periodontitis using 100 digital panoramic radiographs. Normal conditions and 4 stages of periodontitis were annotated on these panoramic radiographs. A total of 1100 original and augmented images were then randomly divided into a training (75%) dataset to produce segmentation models and a testing (25%) dataset to determine the evaluation metrics of the segmentation models. Results: The performance of the segmentation models against the radiographic diagnosis of periodontitis conducted by a dentist was described by evaluation metrics(i.e., dice coefficient and intersection-over-union [IoU] score). MultiLabel U-Net achieved a dice coefficient of 0.96 and an IoU score of 0.97. Meanwhile, Mask R-CNN attained a dice coefficient of 0.87 and an IoU score of 0.74. U-Net showed the characteristic of semantic segmentation, and Mask R-CNN performed instance segmentation with accuracy, precision, recall, and F1-score values of 95%, 85.6%, 88.2%, and 86.6%, respectively. Conclusion: Multi-Label U-Net produced superior image segmentation to that of Mask R-CNN. The authors recommend integrating it with other techniques to develop hybrid models for automatic periodontitis detection.

• Korean Journal of Radiology
• /
• v.21 no.10
• /
• pp.1150-1160
• /
• 2020

Objective: To describe the experience of implementing a deep learning-based computer-aided detection (CAD) system for the interpretation of chest X-ray radiographs (CXR) of suspected coronavirus disease (COVID-19) patients and investigate the diagnostic performance of CXR interpretation with CAD assistance. Materials and Methods: In this single-center retrospective study, initial CXR of patients with suspected or confirmed COVID-19 were investigated. A commercialized deep learning-based CAD system that can identify various abnormalities on CXR was implemented for the interpretation of CXR in daily practice. The diagnostic performance of radiologists with CAD assistance were evaluated based on two different reference standards: 1) real-time reverse transcriptase-polymerase chain reaction (rRT-PCR) results for COVID-19 and 2) pulmonary abnormality suggesting pneumonia on chest CT. The turnaround times (TATs) of radiology reports for CXR and rRT-PCR results were also evaluated. Results: Among 332 patients (male:female, 173:159; mean age, 57 years) with available rRT-PCR results, 16 patients (4.8%) were diagnosed with COVID-19. Using CXR, radiologists with CAD assistance identified rRT-PCR positive COVID-19 patients with sensitivity and specificity of 68.8% and 66.7%, respectively. Among 119 patients (male:female, 75:44; mean age, 69 years) with available chest CTs, radiologists assisted by CAD reported pneumonia on CXR with a sensitivity of 81.5% and a specificity of 72.3%. The TATs of CXR reports were significantly shorter than those of rRT-PCR results (median 51 vs. 507 minutes; p < 0.001). Conclusion: Radiologists with CAD assistance could identify patients with rRT-PCR-positive COVID-19 or pneumonia on CXR with a reasonably acceptable performance. In patients suspected with COVID-19, CXR had much faster TATs than rRT-PCRs.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.53-63
• /
• 2024

Alzheimer's disease is a brain disorder that worsens over time and affects millions of people around the world. It leads to a gradual deterioration in memory, thinking ability, and behavioral and social skills until the person loses his ability to adapt to society. Technological progress in medical imaging and the use of artificial intelligence, has provided the possibility of detecting Alzheimer's disease through medical images such as magnetic resonance imaging (MRI). However, Deep learning algorithms, especially convolutional neural networks (CNNs), have shown great success in analyzing medical images for disease diagnosis and classification. Where CNNs can recognize patterns and objects from images, which makes them ideally suited for this study. In this paper, we proposed to compare the performances of Alzheimer's disease detection by using two deep learning methods: You Only Look Once (YOLO), a CNN-enabled object recognition algorithm, and Visual Geometry Group (VGG16) which is a type of deep convolutional neural network primarily used for image classification. We will compare our results using these modern models Instead of using CNN only like the previous research. In addition, the results showed different levels of accuracy for the various versions of YOLO and the VGG16 model. YOLO v5 reached 56.4% accuracy at 50 epochs and 61.5% accuracy at 100 epochs. YOLO v8, which is for classification, reached 84% accuracy overall at 100 epochs. YOLO v9, which is for object detection overall accuracy of 84.6%. The VGG16 model reached 99% accuracy for training after 25 epochs but only 78% accuracy for testing. Hence, the best model overall is YOLO v9, with the highest overall accuracy of 86.1%.

• Journal of the Korean Society of Radiology
• /
• v.11 no.5
• /
• pp.379-385
• /
• 2017

This study identifies the optimal tube voltages depending on the changes in the patient's body type for limb tests using a digital radiography (DR) system. For the upper-limp test, the dose area product (DAP) was fixed at $5.06dGy{\ast} cm^2$, and for the lower-limb test, the DAP was fixed at $5.04dGy{\ast} cm^2$. Afterwards, the tube voltage was changed to four different stages and the images were taken three times at each stage. The thickness of the limbs was increased by 10 mm to 30 mm to change in the patient's body type. For a quantitative evaluation, Image J was used to calculate the contrast to noise ratio (CNR) and signal to noise ratio (SNR) among the four groups, according to the tube voltage. For statistical testing, the statistically significant differences were analyzed through the Kruskal-Wallis test at a 95% confidence level. For the qualitative analysis of the images, the pre-determined items were evaluated based on a 5-point Likert scale. In both upper-limb and lower-limb tests, the more the tube voltage increased, the more the CNR and SNR of the images decreased. The test on the changes depending on the patient's body shape showed that the more the thickness increased, the more the CNR and SNR decreased. In the qualitative evaluation on the upper limbs, the more the tube voltage increased, the more score increased to 4.6 at the maximum of 55kV and 3.6 at 40kV, respectively. The mean score for the lower limbs was 4.4, regardless of the tube voltage. The more either the upper or lower limbs got thicker, the more the score generally decreased. The score of the upper limps sharply dropped at 40kV, whereas that of the lower limps sharply dropped at 50kV. For patients with a standard thickness, the optimized images can be obtained when taken at 45kV for the upper limbs, and at 50kV for the lower limbs. However, when the thickness of the patient's limbs increases, it is best to set the tube voltage at 50 kV for the upper limbs and at 55 kV for the lower limbs.

• Journal of radiological science and technology
• /
• v.37 no.1
• /
• pp.1-6
• /
• 2014

Breast shooting performance management and quality control of the generator is applied to the amount of current IEC(International Electrotechnical Commission) 60601-2-45 tube voltage and tube current are based on standards that were proposed in the analysis of the test results were as follows. Tube voltage according to the value of the standard deviation by year of manufacture from 2001 to 2010 as a 42-3.15 showed the most significant, according to the year of manufacture by tube amperage value of the standard deviation to 6.38 in the pre-2000 showed the most significant, manufactured after 2011 the standard deviation of the devices, the PAE(Percent Average Error) was relatively low. This latest generation device was manufactured in the breast of the tube voltage and tube diagnosed shooting the correct amount of current to maintain the performance that can be seen. The results of this study as the basis for radiography diagnosed breast caused by using the device's performance and maintain quality control, so the current Food and Drug Administration "about the safety of diagnostic radiation generator rule" specified in the test cycle during three years of self-inspection radiation on a radiation generating device ensure safety and performance of the device using a coherent X-ray(constancy) by two ultimately able to keep the radiation dose to the public to reduce the expected effect is expected.

• Journal of radiological science and technology
• /
• v.21 no.1
• /
• pp.35-39
• /
• 1998

We analyzed image factors to determine the characteristic factors that need for intelligent replenishment system of the auto film processor. We processed the serial 300 sheets of radiographic films of chest phantom without replenishment of developing and fixation replenisher. We took the digital data by using film digitizer which scaned the films and automatically summed up the pixel values of the films. We analyzed characteristic curves, average gradients and relative speeds of individual film using densitometer and step densitometry. We also evaluated the pH of developer, fixer, and washer fluid with digital pH meter. Fixer residual rate and washing effect were measured by densitometer using the reagent methods. There was no significant reduction of the digital density numbers of the serial films without replenishment of developer and fixer. The average gradients were gradually decreased by 0.02 and relative speeds were also gradually decreased by 6.96% relative to initial standard step-densitometric measurement. The pHs of developer and fixer were reflected the inactivation of each fluid. The fixer residual rates and washing effects after processing each 25 sheets of films were in the normal range. We suggest that the digital data are not reliable due to limitation of the hardware and software of the film digitizer. We conclude that average gradient and relative speed which mean the film's contrast and sensitivity respectively are reliable factors for determining the need for the replenishment of the auto film processor. We need more study of simpler equations and programming for more intelligent replenishment system of the auto film processor.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.48 no.2
• /
• pp.221-228
• /
• 2021

The aim of this study was to evaluate the use of easily accessible machine learning application to identify mesiodens, and to compare the ability to identify mesiodens between trained model and human. A total of 1604 panoramic images (805 images with mesiodens, 799 images without mesiodens) of patients aged 5 - 7 years were used for this study. The model used for machine learning was Google's teachable machine. Data set 1 was used to train model and to verify the model. Data set 2 was used to compare the ability between the learning model and human group. As a result of data set 1, the average accuracy of the model was 0.82. After testing data set 2, the accuracy of the model was 0.78. From the resident group and the student group, the accuracy was 0.82, 0.69. This study developed a model for identifying mesiodens using panoramic radiographs of children in primary and early mixed dentition. The classification accuracy of the model was lower than that of the resident group. However, the classification accuracy (0.78) was higher than that of dental students (0.69), so it could be used to assist the diagnosis of mesiodens for non-expert students or general dentists.