• Title/Summary/Keyword: Radiography training

Search Result 48, Processing Time 0.052 seconds

Diagnostic Performance of a New Convolutional Neural Network Algorithm for Detecting Developmental Dysplasia of the Hip on Anteroposterior Radiographs

  • Hyoung Suk Park;Kiwan Jeon;Yeon Jin Cho;Se Woo Kim;Seul Bi Lee;Gayoung Choi;Seunghyun Lee;Young Hun Choi;Jung-Eun Cheon;Woo Sun Kim;Young Jin Ryu;Jae-Yeon Hwang
    • Korean Journal of Radiology
    • /
    • v.22 no.4
    • /
    • pp.612-623
    • /
    • 2021
  • Objective: To evaluate the diagnostic performance of a deep learning algorithm for the automated detection of developmental dysplasia of the hip (DDH) on anteroposterior (AP) radiographs. Materials and Methods: Of 2601 hip AP radiographs, 5076 cropped unilateral hip joint images were used to construct a dataset that was further divided into training (80%), validation (10%), or test sets (10%). Three radiologists were asked to label the hip images as normal or DDH. To investigate the diagnostic performance of the deep learning algorithm, we calculated the receiver operating characteristics (ROC), precision-recall curve (PRC) plots, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) and compared them with the performance of radiologists with different levels of experience. Results: The area under the ROC plot generated by the deep learning algorithm and radiologists was 0.988 and 0.988-0.919, respectively. The area under the PRC plot generated by the deep learning algorithm and radiologists was 0.973 and 0.618-0.958, respectively. The sensitivity, specificity, PPV, and NPV of the proposed deep learning algorithm were 98.0, 98.1, 84.5, and 99.8%, respectively. There was no significant difference in the diagnosis of DDH by the algorithm and the radiologist with experience in pediatric radiology (p = 0.180). However, the proposed model showed higher sensitivity, specificity, and PPV, compared to the radiologist without experience in pediatric radiology (p < 0.001). Conclusion: The proposed deep learning algorithm provided an accurate diagnosis of DDH on hip radiographs, which was comparable to the diagnosis by an experienced radiologist.

A comparative study of educators vs, non-educators designed to improve dental radiographic quality control - Focusing on theories of dental radiographic and practical training and clinical practice education - (치과방사선 질관리 향상을 위한 교육자 대비 비교육자 비교연구 - 치과방사선학 이론 및 실습교육과 임상실습교육을 중심으로 -)

  • Kim, Seung-Hee;Hong, Su-Min;Lee, Kwang-Ok
    • Journal of the Korean Society of Radiology
    • /
    • v.6 no.5
    • /
    • pp.421-426
    • /
    • 2012
  • The purpose of this study was to investigate the knowledge of dental hygiene students of the quality assurance of dental radiation such quality assurance and related educational experiences in an effort to accelerate the preparation of a curriculum for systematic quality-assurance. The subjects in this study were 453 dental hygiene students who participated in dental radiography courses. Varied statistical analyses such as frequency analyses, reliability, chi-square, and independent samples t-tests were conducted on the data collected, using SPSS 12.0. Scheffe test was also used after one-way ANOVA as post-hoc tests. Results showed that (a) the students' acknowledge level of Radiographic Quality Assurance was $7.71{\pm}1.7$ out of 12 on average. The more theory and practical classes students took, the higher points they got (p<0.001); (b) Most of the students experienced 1-3 lessons out of 13 in practical training and 26.3% of students did not take any practical lesson. ;(c)Students who did not take any practical training got 7.20 points out of 13, students who took 1-3 lessons got 7.84 points out of 13, students who took 4-5 lessons got 7.87 points out of 13, and students who took more than 6 lessons got 8.14 points out of 13 on average. The more practical classes they took the higher acknowledge level they were. Therefore it needs to provide adequate practical lessons to them.

A Study on Radiation Safety Management by Dental Hygienist (치과위생사의 방사선 안전관리에 대한 조사 연구)

  • Kang, Eun-Ju;Lee, Kyung-Hee;Kim, Young-Im
    • Journal of dental hygiene science
    • /
    • v.5 no.3
    • /
    • pp.105-112
    • /
    • 2005
  • In spite of relatively low level of radiation dose used at dental clinics, long term exposure may be harmful, so radiation workers at dental clinics must be well aware of its danger. This study was to analyze the factors to have an influence on safety management behavior in the radiography chamber by understanding the relationship among the knowledge, attitudes and behavior in regard with radiation safety management by dental hygienists in order to take preventive measures for dental hygienists and suggest ideas to develop radiation safety training programs. For this, we contacted dental hygienists working at the local dental clinics for 4 months from December of 2003 to march of 2004 and obtained the following findings. 1. Concering the knowledge level of radiation safety management, $8.59{\pm}2.36$ was average score with the highest of 13 and the lowest of 3 from 15-scale test. In addition, knowledge level of radiation safety management by general characteristics showed statistically significant difference according to working experience (p < 0.001), marital status (p < 0.001), attendance rate of radiation safety management training program (p < 0.001), and type of clinic (p < 0.001). 2. Concering the attitude level of radiation safety management, $4.08{\pm}0.50$ is average score with the highest of $4.31{\pm}0.73$ and the lowest of $3.82{\pm}0.89$ by item from 5-scale test. Besides, attitude level of radiation safety management by general characteristics showed statistically significant difference according to age (p < 0.001), working experience (p < 0.05), attendance rate of radiation safety management training program (p < 0.01), and type of clinic (p < 0.001). 3. Concering the behavior level of radiation safety management, $2.89{\pm}0.77$ is average score from 5-scale test, which was relatively low in comparison with the level of attitude and the highest score was $3.82{\pm}0.94$ and the lowest $2.37{\pm}1.04$ by item. Behavior level of radiation safety management by general characteristics showed statistically significant difference according to working experience (p < 0.001) and type of clinic (p < 0.001). 4. From the survey of relationship among knowledge, attitude and behavior of radiation safety management was, we found that the higher the knowledge level of radiation safety management, the higher the level of attitude and behavior, and the higher the attitude level was, the higher the level of behavior.

  • PDF

A Study of the Improvement of Clinical and Practical Trainings in the Education of Radiologic Technologists (방사선사(放射線士) 교육(敎育)의 임상실습(臨床實習) 개선(改善)에 관(關)한 연구(硏究))

  • Lee, Man-Koo;Kang, Se-Sik;Yoon, Han-Sik;Huh, Joon
    • Journal of radiological science and technology
    • /
    • v.6 no.1
    • /
    • pp.117-129
    • /
    • 1983
  • This study, in order to improve clinical and practical trainings in the education of radiologic technologists, applies to 76 medical institutions of 91 ones which are used as the hospitals of clinical and practical training in 9 existing junior colleges except 3 new ones of 12 ones throughout all over the country from November 1, in 1982 to April 30, in 1983. And the purpose of this study is to research the percent conditions of basic practical trainings and clinical ones enforced in each college, and the percent conditions, equipments, contents, and opinions in clinical and practical trainings enforced in each hospital. The results are summarized as follows; 1. In the case of junior colleges in the whole country the curriculum of basic practical trainings averages 336.66 hours and the limits are between 120 and 510 hours. The actual hours in practice average 140 hours and the limits are between 60 and 240 hours, which correspond to 41.58% of the curriculum of basic practical trainings. 2. There were three junior colleges among nine that had a reserved hospital for clinical and practical trainings(only 33.33%). 3. The period of the practice was almost vacation in 4 junior colleges. The practice was conducted only for students to want the practice(44.45%), junior colleges that all students in them conducted the practice was 2 junior colleges and presented 22.22%. 4. In the field of students engaging in the practice, each field of radiation therapy and nuclear medicine presented 16.5%, 20.3% and almost students didin't have experience for the practice. 5. In medical institutions the educational institutions for intern showed 67.11%. Hospital with radiologist showed 26.32%. Radiotechnologist who had experience below 5 years presented 60.17%. 6. In the equipment for radiation diagnosis, each hospital had no difference. The number of hospitals passessing diagnostic equipments above 125 KVP was 56.26%. But radiation therapy equipment and nuclear medicine equipment had extremely low rate. 7. In the diagnosis of patient in the practice hospital, conventional radiography-to Skull, Chest, Abdomen, Skeleton, Urogenital system-reached the criterion. But special radiography was comparatively low. There appeared low rate, 32.89% in the field of nuclear medicine, 15.79% in the field of radiation therapy. 8. Students who carried out the practice were 1-89 students, days in practice were 1-30 days. There were differences in that point among among hospitals. Junior colleges conducting the practice were 2 colleges per hospital. Scope of the object were 1-8 junior colleges. 9. The practice conducted for the request of the colleges presented 72.37%, in addition, The prctices were conducted for growth of the younger generation and the same coperation with the colleges establishment of sisterhood with the colleges, relationship with students. 10. The practice conducted without the establishment of plan presented 59.21% The need for guiding book to the practice and evaluating was recognized over 90%. 11. In the relation between the practice with achievement of credit. There were big differences in opinion between hospitals-Group and the colleges-Group; hospital-Group had opinion that must follow achievement of credit with the practice. The colleges-Group had opinion that must conduct the practice after achieving credit. 12. After conducting the practice, in the practice leaders satisfaction degree dissatisfactory opinion presented the most rate 80.26%. Very much satisfactory opinion, as one hospital, presentd only 1.32%. 13. Both hospitals-Group and the colleges-Group had an opinion that the practice leader must have actual experiences, lectures and achievement, an opinion that actual experiences is over 5 years. 14. In the guide of human relation, cooperation, responsibility, courtesy to patients. Both hospitals-Group and the colleges-Group had an opinion that the guide must be involved in the period of the practice and must be instructed.

  • PDF

Investigation of the Super-resolution Algorithm for the Prediction of Periodontal Disease in Dental X-ray Radiography (치주질환 예측을 위한 치과 X-선 영상에서의 초해상화 알고리즘 적용 가능성 연구)

  • Kim, Han-Na
    • Journal of the Korean Society of Radiology
    • /
    • v.15 no.2
    • /
    • pp.153-158
    • /
    • 2021
  • X-ray image analysis is a very important field to improve the early diagnosis rate and prediction accuracy of periodontal disease. Research on the development and application of artificial intelligence-based algorithms to improve the quality of such dental X-ray images is being widely conducted worldwide. Thus, the aim of this study was to design a super-resolution algorithm for predicting periodontal disease and to evaluate its applicability in dental X-ray images. The super-resolution algorithm was constructed based on the convolution layer and ReLU, and an image obtained by up-sampling a low-resolution image by 2 times was used as an input data. Also, 1,500 dental X-ray data used for deep learning training were used. Quantitative evaluation of images used root mean square error and structural similarity, which are factors that can measure similarity through comparison of two images. In addition, the recently developed no-reference based natural image quality evaluator and blind/referenceless image spatial quality evaluator were additionally analyzed. According to the results, we confirmed that the average similarity and no-reference-based evaluation values were improved by 1.86 and 2.14 times, respectively, compared to the existing bicubic-based upsampling method when the proposed method was used. In conclusion, the super-resolution algorithm for predicting periodontal disease proved useful in dental X-ray images, and it is expected to be highly applicable in various fields in the future.

Diagnosis of Scoliosis Using Chest Radiographs with a Semi-Supervised Generative Adversarial Network (준지도학습 방법을 이용한 흉부 X선 사진에서 척추측만증의 진단)

  • Woojin Lee;Keewon Shin;Junsoo Lee;Seung-Jin Yoo;Min A Yoon;Yo Won Choi;Gil-Sun Hong;Namkug Kim;Sanghyun Paik
    • Journal of the Korean Society of Radiology
    • /
    • v.83 no.6
    • /
    • pp.1298-1311
    • /
    • 2022
  • Purpose To develop and validate a deep learning-based screening tool for the early diagnosis of scoliosis using chest radiographs with a semi-supervised generative adversarial network (GAN). Materials and Methods Using a semi-supervised learning framework with a GAN, a screening tool for diagnosing scoliosis was developed and validated through the chest PA radiographs of patients at two different tertiary hospitals. Our proposed method used training GAN with mild to severe scoliosis only in a semi-supervised manner, as an upstream task to learn scoliosis representations and a downstream task to perform simple classification for differentiating between normal and scoliosis states sensitively. Results The area under the receiver operating characteristic curve, negative predictive value (NPV), positive predictive value, sensitivity, and specificity were 0.856, 0.950, 0.579, 0.985, and 0.285, respectively. Conclusion Our deep learning-based artificial intelligence software in a semi-supervised manner achieved excellent performance in diagnosing scoliosis using the chest PA radiographs of young individuals; thus, it could be used as a screening tool with high NPV and sensitivity and reduce the burden on radiologists for diagnosing scoliosis through health screening chest radiographs.

Deep Learning-Assisted Diagnosis of Pediatric Skull Fractures on Plain Radiographs

  • Jae Won Choi;Yeon Jin Cho;Ji Young Ha;Yun Young Lee;Seok Young Koh;June Young Seo;Young Hun Choi;Jung-Eun Cheon;Ji Hoon Phi;Injoon Kim;Jaekwang Yang;Woo Sun Kim
    • Korean Journal of Radiology
    • /
    • v.23 no.3
    • /
    • pp.343-354
    • /
    • 2022
  • Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.

Deep learning-based automatic segmentation of the mandibular canal on panoramic radiographs: A multi-device study

  • Moe Thu Zar Aung;Sang-Heon Lim;Jiyong Han;Su Yang;Ju-Hee Kang;Jo-Eun Kim;Kyung-Hoe Huh;Won-Jin Yi;Min-Suk Heo;Sam-Sun Lee
    • Imaging Science in Dentistry
    • /
    • v.54 no.1
    • /
    • pp.81-91
    • /
    • 2024
  • Purpose: The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs. Materials and Methods: A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset. Results: Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%. Conclusion: This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.