• Korean Journal of Radiology
• /
• v.25 no.4
• /
• pp.343-350
• /
• 2024

Objective: Artificial intelligence-based computer-aided diagnosis (AI-CAD) is increasingly used in mammography. While the continuous scores of AI-CAD have been related to malignancy risk, the understanding of how to interpret and apply these scores remains limited. We investigated the positive predictive values (PPVs) of the abnormality scores generated by a deep learning-based commercial AI-CAD system and analyzed them in relation to clinical and radiological findings. Materials and Methods: From March 2020 to May 2022, 656 breasts from 599 women (mean age 52.6 ± 11.5 years, including 0.6% [4/599] high-risk women) who underwent mammography and received positive AI-CAD results (Lunit Insight MMG, abnormality score ≥ 10) were retrospectively included in this study. Univariable and multivariable analyses were performed to evaluate the associations between the AI-CAD abnormality scores and clinical and radiological factors. The breasts were subdivided according to the abnormality scores into groups 1 (10-49), 2 (50-69), 3 (70-89), and 4 (90-100) using the optimal binning method. The PPVs were calculated for all breasts and subgroups. Results: Diagnostic indications and positive imaging findings by radiologists were associated with higher abnormality scores in the multivariable regression analysis. The overall PPV of AI-CAD was 32.5% (213/656) for all breasts, including 213 breast cancers, 129 breasts with benign biopsy results, and 314 breasts with benign outcomes in the follow-up or diagnostic studies. In the screening mammography subgroup, the PPVs were 18.6% (58/312) overall and 5.1% (12/235), 29.0% (9/31), 57.9% (11/19), and 96.3% (26/27) for score groups 1, 2, 3, and 4, respectively. The PPVs were significantly higher in women with diagnostic indications (45.1% [155/344]), palpability (51.9% [149/287]), fatty breasts (61.2% [60/98]), and certain imaging findings (masses with or without calcifications and distortion). Conclusion: PPV increased with increasing AI-CAD abnormality scores. The PPVs of AI-CAD satisfied the acceptable PPV range according to Breast Imaging-Reporting and Data System for screening mammography and were higher for diagnostic mammography.

• Korean Journal of Radiology
• /
• v.25 no.4
• /
• pp.328-330
• /
• 2024

• The Korean Journal of Pain
• /
• v.34 no.1
• /
• pp.124-131
• /
• 2021

Background: Sciatic nerve injury due to intramuscular injection (SNIII) is still a health problem. This study aimed to determine whether there is a correlation between neuropathic pain and electrodiagnostic findings in SNIII. Methods: Patients whose clinical and electrodiagnostic findings were compatible with SNIII participated in this retrospective cohort study. Compound muscle action potential (CMAP) and sensory nerve action potential (SNAP) amplitudes of the sural, superficial peroneal, peroneal, and tibial nerves were graded from 1 to 4. Leeds assessment of neuropathic symptoms and signs scale (LANSS) was applied to all patients. Results: Forty-eight patients were included in the study, 67% of whom had a LANSS score ≥ 12. Sural SNAP amplitude abnormalities were present in 8 (50%) out of 16 patients with a LANSS score < 12, and 28 (87.5%) out of 32 patients with a LANSS score ≥ 12, with significant differences between the groups (P = 0.011). There was a positive correlation between the LANSS score and the sural SNAP amplitude grading (P = 0.001, r = 0.476). A similar positive correlation was also found in the LANSS score and the tibial nerve CMAP amplitude grading (P = 0.004, r = 0.410). Conclusions: This study showed a positive correlation between the severity of tibial nerve CMAP/sural SNAP amplitude abnormality and LANSS score in SNIII. Neuropathic pain may be more common in SNIII patients with sural nerve SNAP amplitude abnormality.

• Journal of Korean Neurosurgical Society
• /
• v.45 no.3
• /
• pp.143-150
• /
• 2009

Objective : The purpose of this study was to investigate the reliable factors influencing the surgical outcome of the patients with traumatic acute subdural hematoma (ASDH) and to improve the functional outcome of these patients. Methods : A total of 256 consecutive patients who underwent surgical intervention for traumatic ASDH between March 1998 and March 2008 were reviewed. We evaluated the influence of perioperative variables on functional recovery and mortality using multivariate logistic regression analysis. Results : Functional recovery was achieved in 42.2% of patients and the overall mortality was 39.8%. Age (OR=4.91, p=0.002), mechanism of injury (OR=3.66, p=0.003), pupillary abnormality (OR=3.73, p=0.003), GCS score on admission (OR=5.64, p=0.000), and intraoperative acute brain swelling (ABS) (OR=3.71, p=0.009) were independent predictors for functional recovery. And preoperative pupillary abnormality (OR=2.60, p=0.023), GCS score (OR=4.66, p=0.000), and intraoperative ABS (OR=4.16, p=0.001) were independent predictors for mortality. Midline shift, thickness and volume of hematoma, type of surgery, and time to surgery showed no independent association with functional recovery, although these variables were correlated with functional recovery in univariate analyses. Conclusion : Functional recovery was more likely to be achieved in patients who were under 40 years of age, victims of motor vehicle collision and having preoperative reactive pupils, higher GCS score and the absence of ABS during surgery. These results would be helpful for neurosurgeon to improve outcomes from traumatic acute subdural hematomas.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.94-102
• /
• 2023

Anomaly detection in human movements can improve safety in indoor workplaces. In this paper, we design a framework for detecting anomalous trajectories of humans in indoor spaces based on a variational autoencoder (VAE) with Bi-LSTM layers. First, the VAE is trained to capture the latent representation of normal trajectories. Then the abnormality of a new trajectory is checked using the trained VAE. In this step, the anomaly score of the trajectory is determined using the trajectory reconstruction error through the VAE. If the anomaly score exceeds a threshold, the trajectory is detected as an anomaly. To select the anomaly threshold, a new metric called D-score is proposed, which measures the difference between recall and precision. The anomaly threshold is selected according to the minimum value of the D-score on the validation set. The MIT Badge dataset, which is a real trajectory dataset of workers in indoor space, is used to evaluate the proposed framework. The experiment results show that our framework effectively identifies abnormal trajectories with 81.22% in terms of the F1-score.

• Korean Journal of Radiology
• /
• v.22 no.5
• /
• pp.811-828
• /
• 2021

Following the introduction of a novel pathological concept of usual interstitial pneumonia (UIP) by Liebow and Carrington in 1969, diffuse interstitial pneumonia has evolved into UIP, nonspecific interstitial pneumonia (NSIP), and interstitial lung abnormality (ILA); the histopathological and CT findings of these conditions reflect the required multidisciplinary team approach, involving pulmonologists, radiologists, and pathologists, for their diagnosis and management. Concomitantly, traction bronchiectasis and bronchiolectasis have been recognized as the most persistent and important indices of the severity and prognosis of fibrotic lung diseases. The traction bronchiectasis index (TBI) can stratify the prognoses of patients with ILAs. In this review, the evolutionary concepts of UIP, NSIP, and ILAs are summarized in tables and figures, with a demonstration of the correlation between CT findings and pathologic evaluation. The CT-based UIP score is being proposed to facilitate a better understanding of the spectrum of pulmonary fibrosis, from ILAs to UIP, with emphasis on traction bronchiectasis/bronchiolectasis.

• The Korean Journal of Cytopathology
• /
• v.9 no.2
• /
• pp.139-146
• /
• 1998

The AutoPap 300 QC System is an automated device for the analysis and classification of conventional cervical cytology slides for quality control purpose. These studies evaluated the sensitivity of the AutoPap 300 QC System, and estimated morphologic features other than epithelial abnormality to identify a high quality control(QC) score with the AutoPap 300 QC System. The sensitivity of the AutoPap 300 QC System at 10% review rate for 210 cases of cervicovaginal cytology with low grade squamous intraepithelial lesion(LSIL) and higher grade lesion was assessed, and compared with a 10% random rescreening. The morphologic features, such as presence of endocervical component, dirty background, atrophy, abnormal ceil size, and celluiarity of single atypical cells were estimated in 45 cases of no review and 30 cases of QC review cases. The AutoPap 300 QC System identified 119(56.7%) out of 210 cases with LSIL and higher grade lesion at 10% review rate. It was more sensitive to squamous cell lesions$(50{\sim}62%)$ than to glandular lesions(10%). The dirty background and the scanty cellularity of single atypical cells were significantly related to low QC score. Conclusively, AutoPap 300 QC System is superior to human random rescreen for the identification of false negative smears. The upgrading of this device is required to enhance the defection of glandular lesion and certain Inadequate conditions of the slides.

• Nutrition Research and Practice
• /
• v.9 no.2
• /
• pp.199-206
• /
• 2015

BACKGROUND/OBJECTIVE: Even though the prevalence of metabolic syndrome in adolescents is increasing, little is presently known about this syndrome in adolescents. This study aimed to cluster metabolic risk factors as well as examine the associations between identified patterns and nutrient intake using data from the Korean National Health Examination and Nutritional Assessment (KNHANES). SUBJECTS/METHODS: A total of 2,958 subjects aged 10 to 18 years along with both biochemical and dietary data information were obtained from KNHANES 2007-2010. Six components of metabolic syndrome were used to identify any patterns via factor analysis. Individuals were categorized into quartile groups according to their pattern score. RESULTS: Three clustering patterns with high loadings were identified and named as follows: 1) high blood pressure, 2) dyslipidemia, and 3) glucose abnormality patterns. The high blood pressure pattern showed high loadings of systolic and diastolic blood pressures, the dyslipidemia pattern showed high loadings of triglyceride and HDL-cholesterol levels, and the glucose abnormality pattern showed high loadings of fasting blood glucose levels. Intakes of fat and riboflavin were significantly decreased, whereas those of sodium and niacin were significantly increased across the quartiles in the dyslipidemia pattern. No nutrient intake except that of thiamin was significantly associated with the high blood pressure or glucose abnormality pattern. CONCLUSION: Our findings show that metabolic syndrome risk factors in the Korean adolescent population are characterized by three distinct patterns, which are differentially associated with dietary factors. Characterizing metabolic risk factors and providing specific dietary guidelines for target groups are important.

• Journal of Korean Society for Quality Management
• /
• v.49 no.3
• /
• pp.327-340
• /
• 2021

Purpose: The purpose of this study is to propose a system predicting whether an electricity distribution system is abnormal by analyzing the temperature of the deteriorated system. Traditional electricity distribution system abnormality diagnosis was mainly limited to post-inspection. This research presents a remote monitoring system for detecting thermal images of the deteriorated electricity distribution system efficiently hereby providing safe and efficient abnormal diagnosis to electricians. Methods: In this study, an object detection algorithm (YOLOv5) is performed using 16,866 thermal images of electricity distribution systems provided by KEPCO(Korea Electric Power Corporation). Abnormality/Normality of the extracted system images from the algorithm are classified via the limit temperature. Each classification model, Random Forest, Support Vector Machine, XGBOOST is performed to explore 463,053 temperature datasets. The process capability index is employed to indicate the quality of the electricity distribution system. Results: This research performs case study with transformers representing the electricity distribution systems. The case study shows the following states: accuracy 100%, precision 100%, recall 100%, F1-score 100%. Also the case study shows the process capability index of the transformers with the following states: steady state 99.47%, caution state 0.16%, and risk state 0.37%. Conclusion: The sum of caution and risk state is 0.53%, which is higher than the actual failure rate. Also most transformer abnormalities can be detected through this monitoring system.

• Journal of the Korean Institute of Gas
• /
• v.18 no.3
• /
• pp.53-59
• /
• 2014

In this study, we suggest a system to build the monitoring model for compressed natural gas (CNG) stations, operated in only non-stationary modes, and perform the real-time monitoring and the abnormality diagnosis using principal component analysis (PCA) that is suitable for processing large amounts of multi-dimensional data among multivariate statistical analysis methods. We build the model by the calculation of the new characteristic variables, called as the major components, finding the factors representing the trend of process operation, or a combination of variables among 7 pressure sensor data and 5 temperature sensor data collected from a CNG station at every second. The real-time monitoring is performed reflecting the data of process operation measured in real-time against the built model. As a result of conducting the test of monitoring in order to improve the accuracy of the system and verification, all data in the normal operation were distinguished as normal. The cause of abnormality could be refined, when abnormality was detected successfully, by tracking the variables out of the score plot.