• 대한방사선기술학회지:방사선기술과학
• /
• 제43권5호
• /
• pp.397-404
• /
• 2020

Coronavirus disease(COVID-19) is highly infectious disease that directly affects the lungs. To observe the clinical findings from these lungs, the Chest Radiography(CXR) can be used in a fast manner. However, the diagnostic performance via CXR needs to be improved, since the identifying these findings are highly time-consuming and prone to human error. Therefore, Artificial Intelligence(AI) based tool may be useful to aid the diagnosis of COVID-19 via CXR. In this study, we explored various Deep learning(DL) approach to classify COVID-19, other viral pneumonia and normal. For the original dataset and lung-segmented dataset, the pre-trained AlexNet, SqueezeNet, ResNet18, DenseNet201 were transfer-trained and validated for 3 class - COVID-19, viral pneumonia, normal. In the results, AlexNet showed the highest mean accuracy of 99.15±2.69% and fastest training time of 1.61±0.56 min among 4 pre-trained neural networks. In this study, we demonstrated the performance of 4 pre-trained neural networks in COVID-19 diagnosis with CXR images. Further, we plotted the class activation map(CAM) of each network and demonstrated that the lung-segmentation pre-processing improve the performance of COVID-19 classifier with CXR images by excluding background features.

• Journal of Korean Neurosurgical Society
• /
• 제66권1호
• /
• pp.53-62
• /
• 2023

Objective : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance. Results : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anterior-posterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

• 대한방사선기술학회지:방사선기술과학
• /
• 제37권3호
• /
• pp.211-221
• /
• 2014

임상실습은 전공분야에 관한 실제적 경험을 의료기관에서 현장 실습교육을 통해서 배울 수 있는 좋은 기회가 되고 있다. 이에 임상실습이 진행되는 가운데 임상 지도강사와 학생의 임상실습에 관한 인식을 비교 연구하고자 한다. 수도권에 소재하고 있는 방사선을 전공하는 재학생 중에 2013년 임상실습을 마친 학생을 대상으로 하였다. 본 연구를 위해 고안된 설문지를 사용하여 진행하였으며, 회수된 설문지 275부를 통계프로그램 SPSS(12.0 version)을 사용하여 빈도분석, 교차분석, 카이제곱 검정, McNemar검정을 실시하였다. 방사선 전공을 선택한 동기는 높은 취업률 때문(44.0%)이고, 학과에 대한 만족도는 보통(53.1%)이라고 대답하였다. 8주의 임상실습 기간에 대해 51.3%가 적절하다고 인식하였으며, 임상실습 시기는 3년 과정의 학생은 2학년 겨울방학(47.3%), 4년 과정의 학생은 3학년 1학기(27.7%)로 나타났다. 임상실습 동안 학생들은 전문지식의 부족(32.4%)을 느꼈으며, 실습교육의 일부 내용이 학교에서 이루어지는 교육과 차이가 있다(68.4%)고 대답하였다. 임상실습교육에 대해 대부분 만족하는 것으로 나타났으며 그중에서 임상실습에 대한 중요성의 인식은 $3.94{\pm}0.89$로 나타났다. 실습의 실시 전과 후에 방사선사 취업에 대한 인식의 변화는 84.1%에서 82.9%로 나타났다. 방사선사 취업을 원하는 이유는 직업의 안정성으로 실습 전 49.0%와 실습 후 46.0%, 취업을 원하지 않은 이유는 적성 및 소질에 맞지 않아서가 실습 전 37.0%와 실습 후 40.7%로 대답하였다. 취업을 위한 대학교육이 아닌 유능한 인재를 통한 방사선사의 위상을 높일 수 있는 내실 있고 만족도 높은 대학교육이 이루어 질 수 있는 노력이 필요하고 교육대상자인 학생들에게 효과적인 교육이 이루어 질 수 있는 임상실습시기와 기간에 대한 폭넓은 논의가 지속적으로 필요하다고 사료된다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제31권2호
• /
• pp.177-182
• /
• 2008

디지털 시스템이 가지는 장점인 영상판 검출기의 반응 범위(dynamic range)가 상당히 넓다는 것은 필름/증감지 시스템보다 더 높은 수준의 노광 관용도를 갖기에 재촬영이 줄어들고 영상관리에 효율적이지만, 조사조건의 설정범위가 상당히 넓어 필름/증감지 시스템의 엄격한 조사조건보다 더 많은 조사선량이 환자에게 노출 될 수도 있다. 본 연구는 디지털 시스템 하에서 일반촬영 시 방사선사 개인 별 조사선량에 대한 인식과 행위실태를 파악하여 환자피폭선량을 감소시킬 수 있는 방안을 마련하고, 방사선 선량관리의 중요성을 새로이 인식하고자 하였다. 디지털 시스템 하에서 근무 중인 방사선사의 조사조건 설정과 환자피폭선량 인지 실태를 파악해 본 결과 환자의 체형이나 상태, 촬영부위에 따라 최적의 조사선량을 적용하기 보다는 영상의 농도와 업무의 편의성에 따라 조사조건이 설정되고 있었다. 디지털 시스템이 도입되며 검출기의 반응 범위가 필름/스크린 시스템보다 넓어짐에 따라 조사조건 설정에 대해 관심이 소홀한 경향이 있었다. 따라서 디지털 방사선 시스템 하에서 환자 피폭선량의 감소를 위해 최적의 조사조건으로 영상을 얻어야 할 것이다. 또한 조사선량을 최소로 하고 환자 피폭선량을 줄이기 위해 업무 습관과 인식을 새로이 할 필요성이 있고, 지속적인 관심과 주기적인 교육 및 점검, 다양한 교육 기회제공 등이 필요하다고 본다.

• 한국전문물리치료학회지
• /
• 제7권3호
• /
• pp.1-18
• /
• 2000

The present study was performed to investigate the prevalence rate of idiopathic scoliosis and to determine the effect of exercise training on scoliotic angle in elementary school children. In this study, two out of five elementary schools in Seosan city were chosen by random sampling. Seven hundred sixty four students (from four grade to the sixth grade student) were selected in two schools. Screening tests were conducted to find idiopathic scoliosis. Among the 764 individuals, 139 subjects who showed positive sign in physical examination took whole spine radiography. Thirty six subjects who had a curve of 10 or greater and consented to participate in the exercise program were selected for the exercise program. The exercise program was performed four times a week for 5 months. The results of this study were as follows: 1) One hundred thirty nine subjects showed positive sign in the scoliosis screening test. 2) The overall prevalence of curve of $10^{\circ}or$ greater in X-ray finding was 8.15%. The prevalencies of curve of $10^{\circ}or$ greater in male and female were 7.1% and 9.2%, respectively. 3) Scoliosis curves were observed at thoracic area (48.4%), at thoracolumbar area (27.4%) and at lumbar area(24.4%). 4) Right side curve was 59.7%, and left side curve was 40.3%. 5) After the 5 month exercise program for scoliosis, the Cobb's angle was significantly decreased. 6) There was no significant difference of Cobb's angle change respect to sex, grades, and scoliosis curve site. Results shown here indicates that an early detection and early exercise for scoliosis can result in decreased the Cobb's angle in elementary school children.

• Imaging Science in Dentistry
• /
• 제52권2호
• /
• pp.219-224
• /
• 2022

Purpose: This study aimed to evaluate the performance of transfer learning in a deep convolutional neural network for classifying implant fixtures. Materials and Methods: Periapical radiographs of implant fixtures obtained using the Superline (Dentium Co. Ltd., Seoul, Korea), TS III(Osstem Implant Co. Ltd., Seoul, Korea), and Bone Level Implant(Institut Straumann AG, Basel, Switzerland) systems were selected from patients who underwent dental implant treatment. All 355 implant fixtures comprised the total dataset and were annotated with the name of the system. The total dataset was split into a training dataset and a test dataset at a ratio of 8 to 2, respectively. YOLOv3 (You Only Look Once version 3, available at https://pjreddie.com/darknet/yolo/), a deep convolutional neural network that has been pretrained with a large image dataset of objects, was used to train the model to classify fixtures in periapical images, in a process called transfer learning. This network was trained with the training dataset for 100, 200, and 300 epochs. Using the test dataset, the performance of the network was evaluated in terms of sensitivity, specificity, and accuracy. Results: When YOLOv3 was trained for 200 epochs, the sensitivity, specificity, accuracy, and confidence score were the highest for all systems, with overall results of 94.4%, 97.9%, 96.7%, and 0.75, respectively. The network showed the best performance in classifying Bone Level Implant fixtures, with 100.0% sensitivity, specificity, and accuracy. Conclusion: Through transfer learning, high performance could be achieved with YOLOv3, even using a small amount of data.

• Imaging Science in Dentistry
• /
• 제53권1호
• /
• pp.27-34
• /
• 2023

Purpose: The aim of this study was to clarify the influence of training with a different kind of lesion on the performance of a target model. Materials and Methods: A total of 310 patients(211 men, 99 women; average age, 47.9±16.1 years) were selected and their panoramic images were used in this study. We created a source model using panoramic radiographs including mandibular radiolucent cyst-like lesions (radicular cyst, dentigerous cyst, odontogenic keratocyst, and ameloblastoma). The model was simulatively transferred and trained on images of Stafne's bone cavity. A learning model was created using a customized DetectNet built in the Digits version 5.0 (NVIDIA, Santa Clara, CA). Two machines(Machines A and B) with identical specifications were used to simulate transfer learning. A source model was created from the data consisting of ameloblastoma, odontogenic keratocyst, dentigerous cyst, and radicular cyst in Machine A. Thereafter, it was transferred to Machine B and trained on additional data of Stafne's bone cavity to create target models. To investigate the effect of the number of cases, we created several target models with different numbers of Stafne's bone cavity cases. Results: When the Stafne's bone cavity data were added to the training, both the detection and classification performances for this pathology improved. Even for lesions other than Stafne's bone cavity, the detection sensitivities tended to increase with the increase in the number of Stafne's bone cavities. Conclusion: This study showed that using different lesions for transfer learning improves the performance of the model.

• Imaging Science in Dentistry
• /
• 제54권1호
• /
• pp.33-41
• /
• 2024

Purpose: The aims of this study were to create a deep learning model to distinguish between nasopalatine duct cysts (NDCs), radicular cysts, and no-lesions (normal) in the midline region of the anterior maxilla on panoramic radiographs and to compare its performance with that of dental residents. Materials and Methods: One hundred patients with a confirmed diagnosis of NDC (53 men, 47 women; average age, 44.6±16.5 years), 100 with radicular cysts (49 men, 51 women; average age, 47.5±16.4 years), and 100 with normal groups (56 men, 44 women; average age, 34.4±14.6 years) were enrolled in this study. Cases were randomly assigned to the training datasets (80%) and the test dataset (20%). Then, 20% of the training data were randomly assigned as validation data. A learning model was created using a customized DetectNet built in Digits version 5.0 (NVIDIA, Santa Clara, USA). The performance of the deep learning system was assessed and compared with that of two dental residents. Results: The performance of the deep learning system was superior to that of the dental residents except for the recall of radicular cysts. The areas under the curve (AUCs) for NDCs and radicular cysts in the deep learning system were significantly higher than those of the dental residents. The results for the dental residents revealed a significant difference in AUC between NDCs and normal groups. Conclusion: This study showed superior performance in detecting NDCs and radicular cysts and in distinguishing between these lesions and normal groups.

• 한국멀티미디어학회논문지
• /
• 제23권6호
• /
• pp.729-737
• /
• 2020

Screening with low-dose spiral computed tomography (LDCT) has been shown to reduce lung cancer mortality by about 20% when compared to standard chest radiography. One of the problems arising from screening programs is that large amounts of CT image data must be interpreted by radiologists. To solve this problem, automated detection of pulmonary nodules is necessary; however, this is a challenging task because of the high number of false positive results. Here we demonstrate detection of pulmonary nodules using six off-the-shelf convolutional neural network (CNN) models after modification of the input/output layers and end-to-end training based on publicly databases for comparative evaluation. We used the well-known CNN models, LeNet-5, VGG-16, GoogLeNet Inception V3, ResNet-152, DensNet-201, and NASNet. Most of the CNN models provided superior results to those of obtained using customized CNN models. It is more desirable to modify the proven off-the-shelf network model than to customize the network model to detect the pulmonary nodules.

• 한국환경보건학회지
• /
• 제44권5호
• /
• pp.452-459
• /
• 2018

Objectives: We aimed to examine whether dental waste was being managed adequately at different types of dental institutions in City D in South Korea. Methods: The staff responsible for disinfection at 101 dental offices and clinics (six dentistry departments of general hospitals, 12 dental hospitals, and 83 dental clinics) was interviewed. Results: Solid suction pump waste was handled appropriately at four of the general hospital dentistry departments (66.7%), six dental hospitals (50.0%), and 15 dental clinics (18.1%). Solid spittoon waste was handled appropriately at four general hospital dentistry departments (66.7%), seven dental hospitals (58.3%), and 14 dental clinics (16.9%). Developer and fixer were handled appropriately by a subcontractor at two general hospital dentistry departments (100.0%), five dental hospitals (100.0%), and 24 dental clinics (75.0%). Impression materials were handled appropriately at four general hospital dentistry departments (66.7%), six dental hospitals (50.0%), and 11 dental clinics (13.3%). The plastic covers of intra-oral radiography films were handled appropriately at five general hospital dentistry departments (100.0%), eight dental hospitals (72.7%), and 22 dental clinics (30.1%). Conclusion: South Korea must implement detailed and specialized guidelines for the disposal of solid and general medical waste from dental institutions. Moreover, waste disposal training should be provided annually, and not only once every three years.