• 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.

• Journal of Computing Science and Engineering
• /
• v.8 no.2
• /
• pp.119-128
• /
• 2014

The appearance of retinal blood vessels is an important diagnostic indicator of serious disease, such as hypertension, diabetes, cardiovascular disease, and stroke. Automatic segmentation of the retinal vasculature is a primary step towards automatic assessment of the retinal blood vessel features. This paper presents an automated method for the enhancement and segmentation of blood vessels in fundus images. To decrease the influence of the optic disk, and emphasize the vessels for each retinal image, a multidirectional morphological top-hat transform with rotating structuring elements is first applied to the background homogenized retinal image. Then, an improved multiscale line detector is presented to produce a vessel response image, and yield the retinal blood vessel tree for each retinal image. Since different line detectors at varying scales have different line responses in the multiscale detector, the line detectors with longer length produce more vessel responses than the ones with shorter length; the improved multiscale detector combines all the responses at different scales by setting different weights for each scale. The methodology is evaluated on two publicly available databases, DRIVE and STARE. Experimental results demonstrate an excellent performance that approximates the average accuracy of a human observer. Moreover, the method is simple, fast, and robust to noise, so it is suitable for being integrated into a computer-assisted diagnostic system for ophthalmic disorders.

• The Journal of Korean Medicine
• /
• v.27 no.2 s.66
• /
• pp.134-144
• /
• 2006

Tongue diagnosis is an important diagnostic method in traditional Oriental medicine. It has been especially accepted that quantitative analysis of tongue images allows the accurate diagnosis of the exterior-interior and cold-heat patterns of a patient. However, to ensure stable and reliable results, the color reproduction of such images must first be error-tree. Moreover, tongue diagnosis is much influenced by the surrounding illumination and subjective color recognition, so it has to be performed objectively and quantitatively using a digital diagnostic machine. In this study, 457 tongue images of outpatients were collected using the Digital Tongue Inspection System. Through statistical analysis, the result shows that the heat and cold patterns can be distinguished clearly based on the hue value of the tongue images. The average hue value (1.00) of the tongue's image in the cold pattern is higher than that in the heat pattern (0.99).

• 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.

• The Korean Journal of Cytopathology
• /
• v.12 no.1
• /
• pp.1-15
• /
• 2001

The Bethesda System (TBS) was first developed in 1988 for the need to enhance the communication of the cytopathologic findings to the referring physician in unambiguous diagnostic terms. The terminology used in this reporting system should reflect current understanding of the pathogenesis of cervical/vaginal disease so the framework of the reporting system should be flexible enough to accommodate advances in medicine including virology, molecular biology, and pathology. Three years after the Introduction of TBS, the second Bethesda workshop was held to set or amend diagnostic criteria for each categories of TBS. TBS 1991 is now widely used. The third Bethesda workshop, The Bethesda System 2001 Workshop, was held in National Cancer institute Bethesda, Maryland from April 30 to May 2, 2001. Again, the goals of this workshop were to promote effective communication and to clarify in reporting cervical cytopathology results to clinicians and to provide with the information to make appropriate decisions about diagnosis and treatment. Nine forum groups were made and there were Web-based bulletin board discussions between October, 2000 and the first week of April, 2001. On the basis of bulletin board comments and discussions, the forum moderators recommended revised terminologies in the Workshop. Hot discussions were followed after the presentation by forum moderators during the workshop. Terminologies confusing clinicians and providing no additional informations regarding patient management were deleted in the workshop to clarify the cervicovaginal cytology results. Any informations related to the patient management were encouraged to add. So 'Satisfactory for evaluation but limited by...' of 'Specimen Adequacy' catergory was deleted. Terminology of 'Unsatisfactory' was further specified as 'Specimen rejected' and 'Specimen processed and examined, but unsatisfactory'. Terminologies of 'Benign Cellular Change' and 'Within Normal Limits' were combined and terminology was changed to 'Negative for intraepithelial lesion or malignancy'. In General categorization, category 'Other' was newly inserted and the presence of 'Endometrial cells' in women over 40 years old can be checked. Although the category 'Benign Cellular Change' was deleted, the organisms or reactive changes of this category can be listed in the descriptive diagnoses. Terminologies of ASCUS and AGUS were changed to atypical squamous cell and atypical glandular cell, respectively. Diagnostic term of 'Adenocarcinoma in situ', which is highly reproducible with reliable diagnostic criteria, was newly Inserted. The category of hormonal evaluation was deleted. Criteria for liquid-based specimen were discussed. Reporting by computer-assisted cytology was discussed and terminology for automated review was newly inserted. This is not the final edition of Bethesda 2001. The final document can be prepared before the ASCCP meeting in which Consensus Guidelines for the Management on Cytology Abnormalities and Cervical Precursors will develop in September 2001.

• Imaging Science in Dentistry
• /
• v.43 no.3
• /
• pp.153-161
• /
• 2013

Purpose: To prevent low bone mineral density (BMD), that is, osteoporosis, in postmenopausal women, it is essential to diagnose osteoporosis more precisely. This study presented an automatic approach utilizing a histogram-based automatic clustering (HAC) algorithm with a support vector machine (SVM) to analyse dental panoramic radiographs (DPRs) and thus improve diagnostic accuracy by identifying postmenopausal women with low BMD or osteoporosis. Materials and Methods: We integrated our newly-proposed histogram-based automatic clustering (HAC) algorithm with our previously-designed computer-aided diagnosis system. The extracted moment-based features (mean, variance, skewness, and kurtosis) of the mandibular cortical width for the radial basis function (RBF) SVM classifier were employed. We also compared the diagnostic efficacy of the SVM model with the back propagation (BP) neural network model. In this study, DPRs and BMD measurements of 100 postmenopausal women patients (aged >50 years), with no previous record of osteoporosis, were randomly selected for inclusion. Results: The accuracy, sensitivity, and specificity of the BMD measurements using our HAC-SVM model to identify women with low BMD were 93.0% (88.0%-98.0%), 95.8% (91.9%-99.7%) and 86.6% (79.9%-93.3%), respectively, at the lumbar spine; and 89.0% (82.9%-95.1%), 96.0% (92.2%-99.8%) and 84.0% (76.8%-91.2%), respectively, at the femoral neck. Conclusion: Our experimental results predict that the proposed HAC-SVM model combination applied on DPRs could be useful to assist dentists in early diagnosis and help to reduce the morbidity and mortality associated with low BMD and osteoporosis.

• Korean Journal of Radiology
• /
• v.24 no.3
• /
• pp.259-270
• /
• 2023

Objective: It is unknown whether artificial intelligence-based computer-aided detection (AI-CAD) can enhance the accuracy of chest radiograph (CR) interpretation in real-world clinical practice. We aimed to compare the accuracy of CR interpretation assisted by AI-CAD to that of conventional interpretation in patients who presented to the emergency department (ED) with acute respiratory symptoms using a pragmatic randomized controlled trial. Materials and Methods: Patients who underwent CRs for acute respiratory symptoms at the ED of a tertiary referral institution were randomly assigned to intervention group (with assistance from an AI-CAD for CR interpretation) or control group (without AI assistance). Using a commercial AI-CAD system (Lunit INSIGHT CXR, version 2.0.2.0; Lunit Inc.). Other clinical practices were consistent with standard procedures. Sensitivity and false-positive rates of CR interpretation by duty trainee radiologists for identifying acute thoracic diseases were the primary and secondary outcomes, respectively. The reference standards for acute thoracic disease were established based on a review of the patient's medical record at least 30 days after the ED visit. Results: We randomly assigned 3576 participants to either the intervention group (1761 participants; mean age ± standard deviation, 65 ± 17 years; 978 males; acute thoracic disease in 472 participants) or the control group (1815 participants; 64 ± 17 years; 988 males; acute thoracic disease in 491 participants). The sensitivity (67.2% [317/472] in the intervention group vs. 66.0% [324/491] in the control group; odds ratio, 1.02 [95% confidence interval, 0.70-1.49]; P = 0.917) and false-positive rate (19.3% [249/1289] vs. 18.5% [245/1324]; odds ratio, 1.00 [95% confidence interval, 0.79-1.26]; P = 0.985) of CR interpretation by duty radiologists were not associated with the use of AI-CAD. Conclusion: AI-CAD did not improve the sensitivity and false-positive rate of CR interpretation for diagnosing acute thoracic disease in patients with acute respiratory symptoms who presented to the ED.

• Imaging Science in Dentistry
• /
• v.32 no.2
• /
• pp.107-111
• /
• 2002

Purpose : To compare the accuracy of digital subtraction images acquired by two different methods different in positioning four reference points for geometrical standardization. Materials and Methods : A total of 36 digital radiographic images of 6 volunteers were taken at the areas of the incisor, premolar, and molar of both the maxilla and mandible using the Digora system. Each image was moved 4 mm vertically and horizontally. Four oral and maxillofacial radiologists performed digital subtraction radiography between the paired images before and after movement using Emago (Oral Diagnostic Systems, Amsterdam, The Netherlands) and Sunny (Biomedisys Co., Seoul, Korea). The standard deviation of the internal gray value in Region of Interest (ROI) was statistically analyzed between the two programs using the paired t-test. Results : The standard deviation of pixel gray values from the digital subtraction images using the Sunny program were lower than that of the Emago program (p<0.05). All observers showed significant differences between each other when the Sunny program was used (p<0.05), but one observer showed a significantly higher score than other observers when they used Emago (p<0.05). The standard deviations of premolar area from both Sunny and Emago programs were significantly higher than those of anterior and molar regions (p<0.05). Conclusion: The subtracted images using the Sunny program were more accurate and sensitive than those taken using the Emago program.

• Journal of the Korean Society of Radiology
• /
• v.13 no.1
• /
• pp.9-14
• /
• 2019

This study aimed to investigate the performance of the S-detect method in breast ultrasonography and to determine how to reduce unnecessary biopsy by comparing the results of the S-detect method and biopsy. Thirty patients who had undergone breast ultrasonography between August and October 2018 and were scheduled to undergo biopsy because of the presence of breast nodules were retrospectively analyzed. The McNemar test was performed to determine whether detection of a malignant breast mass significantly differed between the S-detect method and biopsy. The following results were obtained from the analysis of the S-detect method: sensitivity, 90.9%; specificity, 84.21%; validity, 86.66%; positive predictive value, 76.92%; and negative predictive value, 94.11%. Analysis of the degree of agreement between the S-detect method and biopsy revealed a kappa value as high as 0.724 (p < 0.05), exhibiting good agreement between the two methods. The S-detect method in breast ultrasonography is diagnostically valuable in terms of distinguishing between malignant and benign breast masses, and if used properly before breast biopsy, unnecessary biopsy can be reduced.

• Journal of Periodontal and Implant Science
• /
• v.32 no.1
• /
• pp.199-211
• /
• 2002

Digital substraction technique and computer-assisted densitometirc analysis detect minor change in bone density and thus increase the diagnostic accuracy. This advantage as well as high sensitivity and objectivity which precludes human bias have drawn interest in radiologic research area. The objectives of this study are to verify if Radiographic density can be recognized in linear pattern when density profile of standard periapical radiograph with the aluminium stepwedge as the reference, was investigated under varies circumstances which can be encountered in clinical situations, and in addition to that to obtain mutual relationship between the existing standard radiographic system, and future digital image systems, by confirming the corelationship between the standard radiograph and Digora system which is a digital image system currently being used. In order to make quantitative analysis of the bone tissue, digital image system which uses high resolution automatic slide scanner as an input device, and Digora system were compared and analyzed using multifunctional program, Brain3dsp. The following conclusions were obtained. 1. Under common clinical situation that is 70kVp, 0.2 sec., and focal distance 10cm, Al-Equivalent image equation was found to be Y=11.21X+46.62 $r^2=0.9898$ in standard radiographic system, and Y=12.68X+74.59, $r^2=0.9528$ in Digora system, and linear relation was confirmed in both the systems. 2. In standard radiographic system, when all conditions were maintained the same except for the condition of developing solution, Al-Equivalent image equation was Y=10.07X+41.64, $r^2=0.9861$ which shows high corelationship. 3. When all conditions were maintained the same except for the Kilovoltage peak, linear relationship was still maintained under 60kVp, and Al-Equivalent image equation was Y=14.60X+68.86, $r^2=0.9886$ in the standard radiograhic system, and Y=13.90X+80.68, $r^2=0.9238$ in Digora system. 4. When all conditions were maintained the same except for the exposure time which was varied from 0.01 sec. to 0.8 sec., Al-Equivalent image equation was found to be linear in both the standard radiographic system and Digora system. The R-square was distributed from 0.9188 to 0.9900, and in general, standard radiographic system showed higher R-square than Digora system. 5. When all conditions were maintained the same except for the focal distance which was varied from 5cm to 30cm, Al-Equivalent image equation was found to be linear in both the standard radiographic system and Digora system. The R-square was distributed from 0.9463 to 0.9925, and the standard radiographic system had the tendency to show higher R-square in shorter focal distances.