Biopsy ; Classification ; Dataset ; Sensitivity and Specificity ; Thyroid Gland ; Thyroid Neoplasms ; Thyroid Nodule ; Ultrasonography

dataset of 883 CT scans from 467 subjects. Axial CT images obtained at the inferior endplate level of the 3rd lumbar vertebra were used for the analysis. Manually drawn segmentation maps of the skeletal muscle, visceral fat, and subcutaneous fat were created to serve as ground truth data. The performance of the fully convolutional network-based segmentation system was evaluated using the Dice similarity coefficient and cross-sectional area error, for both a separate internal validation dataset (426 CT scans from 308 subjects) and an external validation dataset (171 CT scans from 171 subjects from two outside hospitals).RESULTS: The mean Dice similarity coefficients for muscle, subcutaneous fat, and visceral fat were high for both the internal (0.96, 0.97, and 0.97, respectively) and external (0.97, 0.97, and 0.97, respectively) validation datasets, while the mean cross-sectional area errors for muscle, subcutaneous fat, and visceral fat were low for both internal (2.1%, 3.8%, and 1.8%, respectively) and external (2.7%, 4.6%, and 2.3%, respectively) validation datasets.CONCLUSION: The fully convolutional network-based segmentation system exhibited high performance and accuracy in the automatic segmentation of abdominal muscle and fat on CT images.]]>
Abdominal Muscles ; Adipose Tissue ; Artificial Intelligence ; Dataset ; Intra-Abdominal Fat ; Learning ; Muscle, Skeletal ; Muscles ; Sarcopenia ; Spine ; Subcutaneous Fat ; Tomography, X-Ray Computed

dataset from patient-derived xenograft model for TKI-treated ccRCC (GSE76068) was retrieved. Commonly altered pathways between the datasets were investigated by Ingenuity Pathway Analysis using commonly regulated differently expressed genes (DEGs). The significance of candidate DEG on intrinsic TKI resistance was assessed through immunohistochemistry in a separate cohort of 101 TKI-treated ccRCC cases.RESULTS: TNFRSF1A gene expression and tumor necrosis factor (TNF)-α pathway were upregulated in ccRCCs with acquired TKI resistance in both microarray datasets. Also, high expression (> 10% of labeled tumor cells) of TNF receptor 1 (TNFR1), the protein product of TNFRSF1A gene, was correlated with sarcomatoid dedifferentiation and was an independent predictive factor of clinically unfavorable response and shorter survivals in separated TKI-treated ccRCC cohort.CONCLUSION: TNF-α signaling may play a role in TKI resistance, and TNFR1 expression may serve as a predictive biomarker for clinically unfavorable TKI responses in ccRCC.]]>
Biomarkers ; Carcinoma, Renal Cell ; Cohort Studies ; Dataset ; Drug Resistance ; Gene Expression ; Gene Expression Profiling ; Heterografts ; Humans ; Immunohistochemistry ; Protein-Tyrosine Kinases ; Receptors, Tumor Necrosis Factor ; Receptors, Tumor Necrosis Factor, Type I ; Tumor Necrosis Factor-alpha

Although microscopic analysis of tissue slides has been the basis for disease diagnosis for decades, intra- and inter-observer variabilities remain issues to be resolved. The recent introduction of digital scanners has allowed for using deep learning in the analysis of tissue images because many whole slide images (WSIs) are accessible to researchers. In the present study, we investigated the possibility of a deep learning-based, fully automated, computer-aided diagnosis system with WSIs from a stomach adenocarcinoma dataset. Three different convolutional neural network architectures were tested to determine the better architecture for tissue classifier. Each network was trained to classify small tissue patches into normal or tumor. Based on the patch-level classification, tumor probability heatmaps can be overlaid on tissue images. We observed three different tissue patterns, including clear normal, clear tumor and ambiguous cases. We suggest that longer inspection time can be assigned to ambiguous cases compared to clear normal cases, increasing the accuracy and efficiency of histopathologic diagnosis by pre-evaluating the status of the WSIs. When the classifier was tested with completely different WSI dataset, the performance was not optimal because of the different tissue preparation quality. By including a small amount of data from the new dataset for training, the performance for the new dataset was much enhanced. These results indicated that WSI dataset should include tissues prepared from many different preparation conditions to construct a generalized tissue classifier. Thus, multi-national/multi-center dataset should be built for the application of deep learning in the real world medical practice.
Adenocarcinoma ; Classification ; Dataset ; Diagnosis ; Learning ; Observer Variation ; Stomach

OBJECTIVE: To investigate pathologic discrepancies between colposcopy-directed biopsy (CDB) of the cervix and loop electrosurgical excision procedure (LEEP) in women with cytologic high-grade squamous intraepithelial lesions (HSILs).METHODS: We retrospectively identified 297 patients who underwent both CDB and LEEP for HSILs in cervical cytology between 2015 and 2018, and compared their pathologic results. Considering the LEEP to be the gold standard, we evaluated the diagnostic performance of CDB for identifying cervical intraepithelial neoplasia (CIN) grades 2 and 3, adenocarcinoma in situ, and cancer (HSIL+). We also performed age subgroup analyses.RESULTS: Among the study population, 90.9% (270/297) had pathologic HSIL+ using the LEEP. The diagnostic performance of CDB for identifying HSIL+ was as follows: sensitivity, 87.8%; specificity, 59.3%; balanced accuracy, 73.6%; positive predictive value, 95.6%; and negative predictive value, 32.7%. Thirty-three false negative cases of CDB included CIN2,3 (n=29) and cervical cancer (n=4). The pathologic HSIL+ rate in patients with HSIL− by CDB was 67.3% (33/49). CDB exhibited a significant difference in the diagnosis of HSIL+ compared to LEEP in all patients (p<0.001). In age subgroup analyses, age groups <35 years and 35–50 years showed good agreement with the entire data set (p=0.496 and p=0.406, respectively), while age group ≥50 years did not (p=0.036).CONCLUSION: A significant pathologic discrepancy was observed between CDB and LEEP results in women with cytologic HSILs. The diagnostic inaccuracy of CDB increased in those ≥50 years of age.
Adenocarcinoma in Situ ; Biopsy ; Cervical Intraepithelial Neoplasia ; Cervix Uteri ; Colposcopy ; Conization ; Dataset ; Diagnosis ; Early Detection of Cancer ; Female ; Humans ; Papanicolaou Test ; Retrospective Studies ; Sensitivity and Specificity ; Squamous Intraepithelial Lesions of the Cervix ; Uterine Cervical Neoplasms

PURPOSE: We determined whether elevated serum alkaline phosphatase (ALP) was related to prevalence, location, type, length, and recurrence of pterygium in a population from the Republic of Korea.METHODS: A nationwide cross-sectional dataset, the Korean National Health and Nutrition Examination Survey (2008–2011), was used in this study. All participants were > 30 years of age and underwent the ALP test and ophthalmic evaluation (n = 22,359). One-way analysis of variance, the chi-square test, and Fisher's exact test were used to compare characteristics and outcomes among participants. Multivariable logistic regression was used to examine the possible associations between serum ALP levels and various types of pterygium. Data were adjusted for known risk factors for development of pterygium and ALP elevation (age, sex, residence, sunlight exposure, drinking, smoking, hypertension, diabetes, BMI, AST, ALT, vitamin D, and HDL).RESULTS: The overall prevalence of pterygium was 8.1%, and participants with pterygium had higher levels of serum ALP (p < 0.001). Participants with higher serum ALP had a significantly higher prevalence of all types of pterygium than those in the lower serum ALP quartiles. After adjusting for potential confounding factors, multivariate logistic regression analysis revealed that ALP was associated with the prevalence of pterygium (odds ratio [OR], 1.001; p = 0.038). Trend analysis between the OR and ALP quartiles revealed a linear trend in overall prevalence and in the intermediate type of pterygium. Subgroup analysis revealed a stronger correlation in participants > 50 years of age. One-way analysis of variance revealed an association between the size of pterygium and serum ALP quartile levels. Serum ALP was not associated with recurrence of pterygium.CONCLUSIONS: Increased serum ALP was associated with the prevalence and size of pterygium.
Alkaline Phosphatase ; Cross-Sectional Studies ; Dataset ; Drinking ; Hypertension ; Korea ; Logistic Models ; Nutrition Surveys ; Prevalence ; Pterygium ; Recurrence ; Republic of Korea ; Risk Factors ; Smoke ; Smoking ; Sunlight ; Vitamin D

OBJECTIVE: Bone mineral density (BMD) is an important consideration during fusion surgery. Although dual X-ray absorptiometry is considered as the gold standard for assessing BMD, quantitative computed tomography (QCT) provides more accurate data in spine osteoporosis. However, QCT has the disadvantage of additional radiation hazard and cost. The present study was to demonstrate the utility of artificial intelligence and machine learning algorithm for assessing osteoporosis using Hounsfield units (HU) of preoperative lumbar CT coupling with data of QCT.METHODS: We reviewed 70 patients undergoing both QCT and conventional lumbar CT for spine surgery. The T-scores of 198 lumbar vertebra was assessed in QCT and the HU of vertebral body at the same level were measured in conventional CT by the picture archiving and communication system (PACS) system. A multiple regression algorithm was applied to predict the T-score using three independent variables (age, sex, and HU of vertebral body on conventional CT) coupling with T-score of QCT. Next, a logistic regression algorithm was applied to predict osteoporotic or non-osteoporotic vertebra. The Tensor flow and Python were used as the machine learning tools. The Tensor flow user interface developed in our institute was used for easy code generation.RESULTS: The predictive model with multiple regression algorithm estimated similar T-scores with data of QCT. HU demonstrates the similar results as QCT without the discordance in only one non-osteoporotic vertebra that indicated osteoporosis. From the training set, the predictive model classified the lumbar vertebra into two groups (osteoporotic vs. non-osteoporotic spine) with 88.0% accuracy. In a test set of 40 vertebrae, classification accuracy was 92.5% when the learning rate was 0.0001 (precision, 0.939; recall, 0.969; F1 score, 0.954; area under the curve, 0.900).CONCLUSION: This study is a simple machine learning model applicable in the spine research field. The machine learning model can predict the T-score and osteoporotic vertebrae solely by measuring the HU of conventional CT, and this would help spine surgeons not to under-estimate the osteoporotic spine preoperatively. If applied to a bigger data set, we believe the predictive accuracy of our model will further increase. We propose that machine learning is an important modality of the medical research field.
Absorptiometry, Photon ; Artificial Intelligence ; Boidae ; Bone Density ; Classification ; Dataset ; Humans ; Learning ; Logistic Models ; Machine Learning ; Osteoporosis ; Spine ; Surgeons

OBJECTIVE: Since less invasive endovascular treatment was introduced to South Korea in 1994, a considerable proportion of endovascular treatments have been performed by neuroradiology doctors, and endovascular treatments by vascular neurosurgeons have recently increased. However, few specific statistics are known regarding how many endovascular treatments are performed by neurosurgeons. Thus, authors compared endovascular treatments collaboratively performed by vascular neurosurgeons with all cases throughout South Korea from 2013 to 2017 to elucidate the role of neurosurgeons in the field of endovascular treatment in South Korea.METHODS: The Society of Korean Endovascular Neurosurgeons (SKEN) has issued annual reports every year since 2014. These reports cover statistics on endovascular treatments collaboratively or individually performed by SKEN members from 2013 to 2017. The data was requested and collected from vascular neurosurgeons in various hospitals. The study involved 77 hospitals in its first year, and 100 in its last. National statistics on endovascular treatment from all over South Korea were obtained from the Healthcare Bigdata Hub website of the Health Insurance Review & Assessment Service based on the Electronic Data Interchange (EDI) codes (in the case of intra-arterial (IA) thrombolysis, however, statistics were based on a combination of the EDI and I63 codes, a cerebral infarction disease code) from 2013 to 2017. These two data sets were directly compared and the ratios were obtained.RESULTS: Regionally, during the entire study period, endovascular treatments by SKEN members were most common in Gyeonggi-do, followed by Seoul and Busan. Among the endovascular treatments, conventional cerebral angiography was the most common, followed by cerebral aneurysmal coiling, endovascular treatments for ischemic stroke, and finally endovascular treatments for vascular malformation and tumor embolization. The number of endovascular treatments performed by SKEN members increased every year.CONCLUSION: The SKEN members have been responsible for the major role of endovascular treatments in South Korea for the recent 5 years. This was achieved through the perseverance of senior members who started out in the midst of hardship, the establishment of standards for the training/certification of endovascular neurosurgery, and the enthusiasm of current SKEN members who followed. To provide better treatment to patients, we will have to make further progress in SKEN.
Busan ; Cerebral Angiography ; Cerebral Infarction ; Data Interpretation, Statistical ; Dataset ; Delivery of Health Care ; Endovascular Procedures ; Gyeonggi-do ; Humans ; Insurance, Health ; Intracranial Aneurysm ; Korea ; Neurosurgeons ; Neurosurgery ; Seoul ; Stroke ; Vascular Malformations

BACKGROUND: This study investigates the association between sleep duration and diabetes mellitus (DM) in a large representative population-based survey in South Korea. METHODS: The fourth (2007–2009), fifth (2010–2012), and sixth (2013) Korea National Health and Nutrition Examination Survey data sets were used. A total of 37,989 individuals were selected for the study. Chi-square tests and multivariate logistic regression analyses were used to analyze whether general characteristics, health status, and health risk behaviors were associated with DM. RESULTS: After adjusting for confounders, the odds of DM in short sleepers (≤5 hr/day) and long sleepers (≥9 hr/day) were 1.033-times higher (95% confidence interval [CI], 0.913–1.169) and 1.334-times higher (95% CI, 1.140–1.562), respectively, compared with individuals who slept 7 hr/day. Subgroup analysis according to gender showed a U-shaped association for both genders, although it appeared stronger in men. CONCLUSION: This study identified a U-shaped association between sleep duration and the risk for DM. Additional studies should help clarify the important information in this study.
Dataset ; Diabetes Mellitus ; Humans ; Korea ; Logistic Models ; Male ; Nutrition Surveys ; Risk-Taking

OBJECTIVES: Biosignal data captured by patient monitoring systems could provide key evidence for detecting or predicting critical clinical events; however, noise in these data hinders their use. Because deep learning algorithms can extract features without human annotation, this study hypothesized that they could be used to screen unacceptable electrocardiograms (ECGs) that include noise. To test that, a deep learning-based model for unacceptable ECG screening was developed, and its screening results were compared with the interpretations of a medical expert. METHODS: To develop and apply the screening model, we used a biosignal database comprising 165,142,920 ECG II (10-second lead II electrocardiogram) data gathered between August 31, 2016 and September 30, 2018 from a trauma intensive-care unit. Then, 2,700 and 300 ECGs (ratio of 9:1) were reviewed by a medical expert and used for 9-fold cross-validation (training and validation) and test datasets. A convolutional neural network-based model for unacceptable ECG screening was developed based on the training and validation datasets. The model exhibiting the lowest cross-validation loss was subsequently selected as the final model. Its performance was evaluated through comparison with a test dataset. RESULTS: When the screening results of the proposed model were compared to the test dataset, the area under the receiver operating characteristic curve and the F1-score of the model were 0.93 and 0.80 (sensitivity = 0.88, specificity = 0.89, positive predictive value = 0.74, and negative predictive value = 0.96). CONCLUSIONS: The deep learning-based model developed in this study is capable of detecting and screening unacceptable ECGs efficiently.
Dataset ; Electrocardiography ; Humans ; Learning ; Mass Screening ; Monitoring, Physiologic ; Noise ; ROC Curve ; Sensitivity and Specificity ; Signal Detection, Psychological