• Journal of Sensor Science and Technology
• /
• v.14 no.2
• /
• pp.69-77
• /
• 2005

The electronic nose (e-nose) has been used in food industry and quality controls in plastic packaging. Recently it finds its applications in medical diagnosis, specifically on detection of diabetes, pulmonary or gastrointestinal problem, or infections by examining odors in the breath or tissues with its odor characterizing ability. Moreover, the use of portable e-nose enables the on-site measurements and analysis of vapors without extra gas-sampling units. This is expected to widen the application of the e-nose in various fields including point-of-care-test or e-health. In this study, a PDA-based portable e-nose was developed using micro-machined gas sensor array and miniaturized electronic interfaces. The rich capacities of the PDA in its computing power and various interfaces are expected to provide the rapid and application specific development of the diagnostic devices, and easy connection to other facilities through information technology (IT) infra. For performance verification of the developed portable e-nose system, Six different vapors were measured using the system. Seven different carbon-black polymer composites were used for the sensor array. The results showed the reproducibility of the measured data and the distinguishable patterns between the vapor species. Additionally, the application of two typical pattern recognition algorithms verified the possibility of the automatic vapor recognition from the portable measurements. These validated the portable e-nose based on PDA developed in this study.

• Korean Chemical Engineering Research
• /
• v.57 no.4
• /
• pp.445-454
• /
• 2019

Layered double hydroxides (LDHs) nanoparticles have emerged as novel nanomaterials for bio-imaging applications due to its unique layered structure, physicochemical properties, and good biocompatibility. Bio-imaging is one of the most important fields for medical applications in clinical diagnostics and therapeutics of various diseases. Enhanced diagnostic techniques are needed to realize new paradigm for next-generation personalized medicine through nanoscale materials. When nanotechnology is introduced into bio-imaging system, nanoparticle probes can endow imaging techniques with enhanced ability to obtain information about biological system at the molecular level. In this review, we summarize structural features of LDH nanoparticles with current issues of bio-imaging system. LDH nanoparticle probes are also discussed through in vitro as well as in vivo studies in various bio-imaging techniques including fluorescence imaging, magnetic resonance imaging (MRI), positron emission tomography (PET), and computed X-ray tomography (CT), which will have the potential in the development of the advanced nanoparticles with high sensitivity and selectivity.

• Journal of Biomedical Engineering Research
• /
• v.39 no.6
• /
• pp.229-236
• /
• 2018

Liver cancer is one of the highest incidents in the world, and the mortality rate is the second most common disease after lung cancer. The purpose of this study is to evaluate the diagnostic ability of deep learning in the classification of malignant and benign tumors in CT images of patients with liver tumors. We also tried to identify the best data processing methods and deep learning models for classifying malignant and benign tumors in the liver. In this study, CT data were collected from 92 patients (benign liver tumors: 44, malignant liver tumors: 48) at the Gil Medical Center. The CT data of each patient were used for cross-sectional images of 3,024 liver tumors. In AlexNet and VggNet, the average of the overall accuracy at each image size was calculated: the average of the overall accuracy of the $200{\times}200$ image size is 69.58% (AlexNet), 69.4% (VggNet), $150{\times}150$ image size is 71.54%, 67%, $100{\times}100$ image size is 68.79%, 66.2%. In conclusion, the overall accuracy of each does not exceed 80%, so it does not have a high level of accuracy. In addition, the average accuracy in benign was 90.3% and the accuracy in malignant was 46.2%, which is a significant difference between benign and malignant. Also, the time it takes for AlexNet to learn is about 1.6 times faster than VggNet but statistically no different (p > 0.05). Since both models are less than 90% of the overall accuracy, more research and development are needed, such as learning the liver tumor data using a new model, or the process of pre-processing the data images in other methods. In the future, it will be useful to use specialists for image reading using deep learning.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.89-103
• /
• 2023

Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG-derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient's sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.50 no.3
• /
• pp.263-276
• /
• 2023

The purpose of this study was to evaluate the performance of a model using You Only Look Once (YOLO) for object detection of proximal caries in periapical radiographs of children. A total of 2016 periapical radiographs in primary dentition were selected from the M6 database as a learning material group, of which 1143 were labeled as proximal caries by an experienced dentist using an annotation tool. After converting the annotations into a training dataset, YOLO was trained on the dataset using a single convolutional neural network (CNN) model. Accuracy, recall, specificity, precision, negative predictive value (NPV), F1-score, Precision-Recall curve, and AP (area under curve) were calculated for evaluation of the object detection model's performance in the 187 test datasets. The results showed that the CNN-based object detection model performed well in detecting proximal caries, with a diagnostic accuracy of 0.95, a recall of 0.94, a specificity of 0.97, a precision of 0.82, a NPV of 0.96, and an F1-score of 0.81. The AP was 0.83. This model could be a valuable tool for dentists in detecting carious lesions in periapical radiographs.

• Journal of the Korean Society of Radiology
• /
• v.17 no.6
• /
• pp.835-841
• /
• 2023

The aim of this study is to evaluate the diagnostic ability of dual-energy computed tomography (DECT) for Composition determination of urinary stones in phantom model. Seventeen cases with urinary stones who underwent DECT were enrolled in the study. The composition of the urinary stones was extracted from the seventeen patients were analyzed with DECT in phantom model with fresh pork. The volume scan method using Dual-energy software was used and the scanned image sets were assessed. All 17 urinary stones of the phantom model were analyzed according to the stone composition using DE stone Analysis were divided into uric acid stones (n=6, 35.29%) and non-uric acid stones (n=11, 64.71%). These urinary stones were pathologically confirmed. The mean attenuation values of uric acid stones at 135 kV, 100 kV and 80 kV was 348.87 ± 166.37 HU, 345.33 ± 151.18 HU and 337.94 ± 172.77 HU, respectively. The mean attenuation values of non-uric acid stones at 135 kV, 100 kV and 80 kV was 551.93 ± 297.09 HU, 747.04 ± 351.31 HU and 958.19 ± 424.72 HU, respectively. At 80 kV, uric acid stones and non-uric acid stones showed significant difference in the attenuation values(P<0.05). The attenuation values of DECT could differentiate the compositions of urinary stones between uric acid and non-uric acid stones at 80 kV in phantom model.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.129-136
• /
• 2023

The government of the Republic of Korea is conducting quality management of public open data by conducting a public data quality management level evaluation. Public open data is provided in various open formats such as XML, JSON, and CSV, with CSV format accounting for the majority. When diagnosing the quality of public open data in CSV format, the quality diagnosis manager determines and diagnoses the domain for each field based on the field name and data within the field of the public open data file. However, it takes a lot of time because quality diagnosis is performed on large amounts of open data files. Additionally, in the case of fields whose meaning is difficult to understand, the accuracy of quality diagnosis is affected by the quality diagnosis person's ability to understand the data. This paper proposes a domain discrimination model for public open data in CSV format using field names and data distribution statistics to ensure consistency and accuracy so that quality diagnosis results are not influenced by the capabilities of the quality diagnosis person in charge, and to support shortening of diagnosis time. As a result of applying the model in this paper, the correct answer rate was about 77%, which is 2.8% higher than the file format open data diagnostic tool provided by the Ministry of Public Administration and Security. Through this, we expect to be able to improve accuracy when applying the proposed model to diagnosing and evaluating the quality management level of public data.

• Journal of the Korean Society of Radiology
• /
• v.82 no.1
• /
• pp.173-181
• /
• 2021

Purpose To evaluate the ability of the Hounsfield unit (HU) measurement of the femoral neck during multidetector computed tomography (MDCT) for assessing osteoporosis compared with dual-energy X-ray absorptiometry (DXA). Materials and Methods Forty-two patients with femoral neck fractures who underwent MDCT and DXA from July to December 2016 were included in this study. HU measurements were made of the cancellous portions of the normal contralateral femoral neck on MDCT. Bone mineral density (BMD) and T-scores were obtained at the femur DXA. Correlations of HU values with BMD and T-scores were analyzed using Spearman's correlation test. Results The mean BMD and T-score of the femoral neck were 0.650 g/cm² and -2.4, respectively. The mean HU values for the normal, osteopenia, and osteoporosis groups were 131.9, 98.9, and 41.3, respectively. HU values at the femoral neck were positively correlated with BMD (r² = 0.670; p < 0.001) and T-scores (r² = 0.676; p < 0.001). Conclusion The HU values of the femoral neck on MDCT are significantly correlated with BMD and T-scores of femur DXA. The HU values may serve as a diagnostic tool for the screening of regional bone quality when MDCT is performed for other reasons.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.1009-1018
• /
• 2022

Objective: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment. Materials and Methods: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI). Results: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity. Conclusion: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

• Korean Journal of Radiology
• /
• v.23 no.4
• /
• pp.466-478
• /
• 2022

Objective: ¹⁸F-fluorodeoxyglucose (FDG) PET/CT is often used for detecting malignancy in patients with newly diagnosed hemophagocytic lymphohistiocytosis (HLH), with acceptable sensitivity but relatively low specificity. The aim of this study was to improve the diagnostic ability of ¹⁸F-FDG PET/CT in identifying malignancy in patients with HLH by combining ¹⁸F-FDG PET/CT and clinical parameters. Materials and Methods: Ninety-seven patients (age ≥ 14 years) with secondary HLH were retrospectively reviewed and divided into the derivation (n = 71) and validation (n = 26) cohorts according to admission time. In the derivation cohort, 22 patients had malignancy-associated HLH (M-HLH) and 49 patients had non-malignancy-associated HLH (NM-HLH). Data on pretreatment ¹⁸F-FDG PET/CT and laboratory results were collected. The variables were analyzed using the Mann-Whitney U test or Pearson's chi-square test, and a nomogram for predicting M-HLH was constructed using multivariable binary logistic regression. The predictors were also ranked using decision-tree analysis. The nomogram and decision tree were validated in the validation cohort (10 patients with M-HLH and 16 patients with NM-HLH). Results: The ratio of the maximal standardized uptake value (SUVmax) of the lymph nodes to that of the mediastinum, the ratio of the SUVmax of bone lesions or bone marrow to that of the mediastinum, and age were selected for constructing the model. The nomogram showed good performance in predicting M-HLH in the validation cohort, with an area under the receiver operating characteristic curve of 0.875 (95% confidence interval, 0.686-0.971). At an appropriate cutoff value, the sensitivity and specificity for identifying M-HLH were 90% (9/10) and 68.8% (11/16), respectively. The decision tree integrating the same variables showed 70% (7/10) sensitivity and 93.8% (15/16) specificity for identifying M-HLH. In comparison, visual analysis of ¹⁸F-FDG PET/CT images demonstrated 100% (10/10) sensitivity and 12.5% (2/16) specificity. Conclusion: ¹⁸F-FDG PET/CT may be a practical technique for identifying M-HLH. The model constructed using ¹⁸F-FDG PET/CT features and age was able to detect malignancy with better accuracy than visual analysis of ¹⁸F-FDG PET/CT images.