• Journal of Periodontal and Implant Science
• /
• v.48 no.2
• /
• pp.114-123
• /
• 2018

Purpose: The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Methods: Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. Results: The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. Conclusions: We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.178-190
• /
• 2021

Alzheimer's disease (AD) is an insidious and degenerative neurological disease. It is a new topic for AD patients to use magnetic resonance imaging (MRI) and computer technology and is gradually explored at present. Preprocessing and correlation analysis on MRI data are firstly made in this paper. Then kernel principal component analysis (KPCA) is used to extract features of brain gray matter images. Finally supervised classification schemes such as AdaBoost algorithm and support vector machine algorithm are used to classify the above features. Experimental results by means of AD program Alzheimer's Disease Neuroimaging Initiative (ADNI) database which contains brain structural MRI (sMRI) of 116 AD patients, 116 patients with mild cognitive impairment, and 117 normal controls show that the proposed method can effectively assist the diagnosis and analysis of AD. Compared with principal component analysis (PCA) method, all classification results on KPCA are improved by 2%-6% among which the best result can reach 84%. It indicates that KPCA algorithm for feature extraction is more abundant and complete than PCA.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.337-339
• /
• 2001

본 연구에서는 임상적으로 얻어진 95개의 영상 자료를 전산화하여 특정 간 영역의 명도분포를 분석하여 이와 간의 지방화 정도와의 상관성을 연구하였다. 지방화 정도를 판단하는 임상적 기준으로 보편적으로 인정되는 지방간지수와 계산된 평균 명도 수치와의 선형 상관 계수를 구하였다. 각각의 영상의 밝기 및 에코정도가 일반적으로 불균일하기 때문에 이를 보정하기 위해 밝은 명도와 어두운 명도의 기준영역을 선정하여 상대명도를 추출하였다. 두 가지 독립적인 방법으로 기준 영역을 선택하여 비교한 결과, 임상 지방간지수와 높은 상관성을 보임을 알 수 있었고, 지방간 진단의 보조자료로 유용함을 확인하였다. 계산된 지방간지수와 상대명도의 상관계수는 0.69 에서 0.79로 나타났다.

• Journal of the Korean Society of Radiology
• /
• v.85 no.4
• /
• pp.769-779
• /
• 2024

Purpose To determine the pros and cons of an artificial intelligence (AI) model developed to diagnose acute rib fractures in chest CT images of patients with chest trauma. Materials and Methods A total of 1209 chest CT images (acute rib fracture [n = 1159], normal [n = 50]) were selected among patients with chest trauma. Among 1159 acute rib fracture CT images, 9 were randomly selected for AI model training. 150 acute rib fracture CT images and 50 normal ones were tested, and the remaining 1000 acute rib fracture CT images was internally verified. We investigated the diagnostic accuracy and errors of AI model for the presence and location of acute rib fractures. Results Sensitivity, specificity, positive and negative predictive values, and accuracy for diagnosing acute rib fractures in chest CT images were 93.3%, 94%, 97.9%, 82.5%, and 95.6% respectively. However, the accuracy of the location of acute rib fractures was low at 76% (760/1000). The cause of error in the diagnosis of acute rib fracture seemed to be a result of considering the scapula or clavicle that were in the same position (66%) or some ribs that were not recognized (34%). Conclusion The AI model for diagnosing acute rib fractures showed high accuracy in detecting the presence of acute rib fractures, but diagnosis of the exact location of rib fractures was limited.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.29 no.2
• /
• pp.387-396
• /
• 1999

In dentistry. RadioVisioGraphy was introduced as a first electronic dental x-ray imaging modality in 1989. Thereafter. many types of direct digital radiographic system have been produced in the last decade. They are based either on charge-coupled device(CCD) or on storage phosphor technology. In addition. new types of digital radiographic system using amorphous selenium. image intensifier etc. are under development. Advantages of digital radiographic system are elimination of chemical processing, reduction in radiation dose. image processing, computer storage. electronic transfer of images and so on. Image processing includes image enhancement. image reconstruction. digital subtraction, etc. Especially digital subtraction and reconstruction can be applied in many aspects of clinical practice and research. Electronic transfer of images enables filmless dental hospital and teleradiology/teledentistry system. Since the first image management and communications system(IMACS) for dentomaxillofacial radiology was reported in 1992. IMACS in dental hospital has been increasing. Meanwhile. researches about computer-assisted diagnosis, such as structural analysis of bone trabecular patterns of mandible. feature extraction, automated identification of normal landmarks on cephalometric radiograph and automated image analysis for caries or periodontitis. have been performed actively in the last decade. Further developments in digital radiographic imaging modalities. image transmission system. imaging processing and automated analysis software will change the traditional clinical dental practice in the 21st century.

• The Korean Journal of Cytopathology
• /
• v.17 no.2
• /
• pp.116-119
• /
• 2006

The diagnosis of papillary thyroid cancer is generally based on the findings of intranuclear cytoplasmic inclusions and nuclear grooves. Although anisokaryosis and poikilokaryosis, in papillary thyroid cancer, are not distinct when compared to other cancers, cytological examination can provide useful preoperative information. Our study evaluated the diagnostic role of computer-assisted image analysis for the pre-surgical assessment of papillary thyroid carcinoma. Thyroid aspirates from twenty female patients who were histologically confirmed to have both papillary carcinoma and benign nodules were studied. Different populations of 50 benign cells and 50 malignant cells were analyzed. Five morphometric parameters were selected for analysis: nuclear area, perimeter, maximum length, maximum width and intensity standard variation. The values obtained for papillary carcinomas were higher than the surrounding benign nodules as follows: nuclear area 63.5 vs. 36.1 (p=0.000), nuclear perimeter were 29.4 vs. 22.0 (p=0.000), maximum length 9.6 vs. 7.1 (p=0.000), maximum width 8.2 vs. 6.3 (p=0.000), the ratio between maximal length and maximal width 1.16 vs. 1.13 (p=0.000), the standard variation of intensity 14.9 vs. 15.9 (p=0.101) respectively. Therefore, morphometric information can be helpful for the differential cytological diagnosis of papillary thyroid carcinoma.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.19 no.1
• /
• pp.122-133
• /
• 2012

Purpose: The purpose of this study was to develop a web-based education program on control vancomycin-resistant enterococci (VRE) infections and to identify the effects of the program on knowledge and performance of nursing students. Methods: The web-based VRE infection control education program was developed by using the network-based instructional systems design model. The nursing students in the experimental group could access this web-based education program at any time, and as many times as they wanted, during the clinical training period. Effects were evaluated by assessing knowledge and performance of VRE infection control measures during the clinical training period. Results: The contents of the education program included diagnosis, transmission, and treatment of VRE, contact precautions, hand washing, personal protective equipment, environment management, and quizzes. The lecture portion was filmed in a virtual screen studio using flash animation, video, and sound effects, and it was uploaded on an internet site. The knowledge and performance scores of the experimental group after using the education program were significantly higher than those of the control group. Conclusion: The results suggest that the web-based VRE infection control education program is an effective educational method to enhance knowledge and performance of VRE infection control measures.

• Imaging Science in Dentistry
• /
• v.44 no.2
• /
• pp.129-135
• /
• 2014

Purpose: The objective of this study was to assess the trabecular bone changes that occurred around functional endosseous dental implants by means of radiographic image analysis techniques. Materials and Methods: Immediate preoperative and postoperative periapical radiographs of de-identified implant patients at the University Dental Hospital of Manchester were retrieved, screened for specific inclusion criteria, digitized, and quantified for structural elements of the trabecular bone around the endosseous implants, by using image analysis techniques. Data were analyzed using SPSS version 11.5. P values of less than 0.05 were considered statistically significant. Results: A total of 12 implants from 11 patients were selected for the study, and 26 regions of interest were obtained. There was a significant increase in the bone area in terms of the mean distance between nodes (p=0.006) and a significant decrease in the marrow area in terms of the bone area (p=0.006) and the length of marrow spaces (p=0.032). Conclusion: It appeared that the bone around the implant underwent remodeling that resulted in a net increase in bone after implant placement.

• Imaging Science in Dentistry
• /
• v.44 no.4
• /
• pp.279-285
• /
• 2014

Purpose: To assess the influence of anatomic location on the relationship between computed tomography (CT) number and X-ray attenuation in limited and medium field-of-view (FOV) scans. Materials and Methods: Tubes containing solutions with different concentrations of $K_2HPO_4$ were placed in the tooth sockets of a human head phantom. Cone-beam computed tomography (CBCT) scans were acquired, and CT numbers of the $K_2HPO_4$ solutions were measured. The relationship between CT number and $K_2HPO_4$ concentration was examined by linear regression analyses. Then, the variation in CT number according to anatomic location was examined. Results: The relationship between $K_2HPO_4$ concentration and CT number was strongly linear. The slopes of the linear regressions for the limited FOVs were almost 2-fold lower than those for the medium FOVs. The absolute CT number differed between imaging protocols and anatomic locations. Conclusion: There is a strong linear relationship between X-ray attenuation and CT number. The specific imaging protocol and anatomic location of the object strongly influence this relationship.

• Imaging Science in Dentistry
• /
• v.53 no.2
• /
• pp.109-115
• /
• 2023

Purpose: The aim of this study was to evaluate changes in the trabecular bone through texture analysis and compare the texture analysis characteristics of different areas in patients with medication-related osteonecrosis of the jaw (MRONJ). Materials and Methods: Cone-beam computed tomographic images of 16 patients diagnosed with MRONJ were used. In sagittal images, 3 regions were chosen: active osteonecrosis(AO); intermediate tissue (IT), which presented a zone of apparently healthy tissue adjacent to the AO area; and healthy bone tissue (HT) (control area). Texture analysis was performed evaluating 7 parameters: secondary angular momentum, contrast, correlation, sum of squares, inverse moment of difference, sum of entropies, and entropy. Data were analyzed using the Kruskal-Wallis test with a significance level of 5%. Results: Comparing the areas of AO, IT, and HT, significant differences (P<0.05) were observed. The IT and AO area images showed higher values for parameters such as contrast, entropy, and secondary angular momentum than the HT area, indicating greater disorder in these tissues. Conclusion: Through texture analysis, changes in the bone pattern could be observed in areas of osteonecrosis. The texture analysis demonstrated that areas visually identified and classified as IT still had necrotic tissue, thereby increasing the accuracy of delimiting the real extension of MRONJ.