Objective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version 1.1.7.2) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics.The results of SM and FFDM were compared. Results: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P < 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P < 0.001), higher specificity (95.5% vs.91.8%, P < 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM in asymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts. Conclusion AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM.Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.

This review examines the challenges associated with occupational disease surveillance in Korea, particularly emphasizing the limitations of current data sources such as the Industrial Accident Compensation Insurance (IACI) statistics and special health examinations. The IACI system undercounts cases due to its emphasis on severe diseases and restrictions on approvals. Special health examinations, although they cover a broad workforce, are constrained by their annual scheduling, which leads to missed acute illnesses and subclinical conditions. The paper also explores the history of occupational disease surveillance in Korea, highlighting the fragmented and disease-specific approach of earlier systems. The authors introduce the newly established Korea Occupational Disease Surveillance Center (KODSC), a comprehensive nationwide system designed to gather, analyze, and interpret data on occupational diseases through a network of regional centers. By incorporating hospital-based surveillance and focusing on acute poisonings and other sentinel events, the KODSC aims to overcome the limitations of previous systems and promote collaboration with various agencies. Although it is still in the early stages of implementation, the KODSC demonstrates potential for improving data accuracy and contributing valuable insights for public health policy.

The prevalence of postpartum depression (PPD) in Asia is reported to range from 13.53% to 22.31%. However, there remains a gap in the identification of PPD, particularly regarding cultural cutoff points. Therefore, the purpose of this scoping review was to determine the prevalence and associated factors of PPD in Eastern, South-eastern, Western, and Southern Asian countries and analyze the cutoff points of the Edinburgh Postnatal Depression Scale (EPDS) used across these countries. Following Arksey and O'Malley’s five-step scoping review framework, the population was defined as mothers, the concept as the EPDS, and the context as the Asian region. A literature search was conducted using PubMed, Embase, CINAHL, PsycINFO, and Web of Science. The data analysis focused on demographic characteristics, EPDS cutoffs and features, PPD prevalence, and its associated factors. Nineteen studies were selected. Most countries used translated versions of the EPDS with demonstrated reliability and validity. The cutoff scores varied, with most using scores of 10 or higher. The prevalence of PPD ranged from 5.1% to 78.7%. Key associated factors for PPD included cultural factors such as relationships with in-laws and preferences for the newborn’s sex. To improve the accuracy of PPD screening in Asia, the EPDS should be used consistently, and appropriate cutoff criteria must be established. In addition, prevention strategies and programs that reflect the cultural characteristics and social context of Asia need to be developed for the early detection and prevention of PPD.

Purpose: This study evaluated the postoperative quality of life (QoL) after various types of gastrectomy for gastric cancer. Materials and Methods: A multicenter prospective observational study was conducted in Korea using the Korean Quality of Life in Stomach Cancer Patients Study (KOQUSS)-40, a new QoL assessment tool focusing on postgastrectomy syndrome. Overall, 496 patients with gastric cancer were enrolled, and QoL was assessed at 5 time points: preoperatively and at 1, 3, 6, and 12 months after surgery. Results: Distal gastrectomy (DG) and pylorus-preserving gastrectomy (PPG) showed significantly better outcomes than total gastrectomy (TG) and proximal gastrectomy (PG) with regard to total score, indigestion, and dysphagia. DG, PPG, and TG also showed significantly better outcomes than PG in terms of dumping syndrome and worry about cancer. Postoperative QoL did not differ significantly according to anastomosis type in DG, except for Billroth I anastomosis, which achieved better bowel habit change scores than the others. No domains differed significantly when comparing double tract reconstruction and esophagogastrostomy after PG. The total QoL score correlated significantly with postoperative body weight loss (more than 10%) and extent of resection (P<0.05 for both).Reflux as assessed by KOQUSS-40 did not correlate significantly with reflux observed on gastroscopy 1 year postoperatively (P=0.064). Conclusions Our prospective observation using KOQUSS-40 revealed that DG and PPG lead to better QoL than TG and PG. Further study is needed to compare postoperative QoL according to anastomosis type in DG and PG.

Background: This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules. Methods: This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images. Results: Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity. Conclusion CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.

Background: This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules. Methods: This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images. Results: Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity. Conclusion CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.

Background: This study aimed to evaluate the applicability of deep learning technology to thyroid ultrasound images for classification of thyroid nodules. Methods: This retrospective analysis included ultrasound images of patients with thyroid nodules investigated by fine-needle aspiration at the thyroid clinic of a single center from April 2010 to September 2012. Thyroid nodules with cytopathologic results of Bethesda category V (suspicious for malignancy) or VI (malignant) were defined as thyroid cancer. Multiple deep learning algorithms based on convolutional neural networks (CNNs) —ResNet, DenseNet, and EfficientNet—were utilized, and Siamese neural networks facilitated multi-view analysis of paired transverse and longitudinal ultrasound images. Results: Among 1,048 analyzed thyroid nodules from 943 patients, 306 (29%) were identified as thyroid cancer. In a subgroup analysis of transverse and longitudinal images, longitudinal images showed superior prediction ability. Multi-view modeling, based on paired transverse and longitudinal images, significantly improved the model performance; with an accuracy of 0.82 (95% confidence intervals [CI], 0.80 to 0.86) with ResNet50, 0.83 (95% CI, 0.83 to 0.88) with DenseNet201, and 0.81 (95% CI, 0.79 to 0.84) with EfficientNetv2_ s. Training with high-resolution images obtained using the latest equipment tended to improve model performance in association with increased sensitivity. Conclusion CNN algorithms applied to ultrasound images demonstrated substantial accuracy in thyroid nodule classification, indicating their potential as valuable tools for diagnosing thyroid cancer. However, in real-world clinical settings, it is important to aware that model performance may vary depending on the quality of images acquired by different physicians and imaging devices.

Objective: To test the performance of an artificial intelligence-based computer-aided diagnosis (AI-CAD) designed for fullfield digital mammography (FFDM) when applied to synthetic mammography (SM). Materials and Methods: We analyzed 501 women (mean age, 57 ± 11 years) who underwent preoperative mammography and breast cancer surgery. This cohort consisted of 1002 breasts, comprising 517 with cancer and 485 without. All patients underwent digital breast tomosynthesis (DBT) and FFDM during the preoperative workup. The SM is routinely reconstructed using DBT. Commercial AI-CAD (Lunit Insight MMG, version 1.1.7.2) was retrospectively applied to SM and FFDM to calculate the abnormality scores for each breast. The median abnormality scores were compared for the 517 breasts with cancer using the Wilcoxon signed-rank test. Calibration curves of abnormality scores were evaluated. The discrimination performance was analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 10% preset threshold. Sensitivity and specificity were further analyzed according to the mammographic and pathological characteristics.The results of SM and FFDM were compared. Results: AI-CAD demonstrated a significantly lower median abnormality score (71% vs. 96%, P < 0.001) and poorer calibration performance for SM than for FFDM. SM exhibited lower sensitivity (76.2% vs. 82.8%, P < 0.001), higher specificity (95.5% vs.91.8%, P < 0.001), and comparable AUC (0.86 vs. 0.87, P = 0.127) than FFDM. SM showed lower sensitivity than FFDM in asymptomatic breasts, dense breasts, ductal carcinoma in situ, T1, N0, and hormone receptor-positive/human epidermal growth factor receptor 2-negative cancers but showed higher specificity in non-cancerous dense breasts. Conclusion AI-CAD showed lower abnormality scores and reduced calibration performance for SM than for FFDM.Furthermore, the 10% preset threshold resulted in different discrimination performances for the SM. Given these limitations, off-label application of the current AI-CAD to SM should be avoided.

This review examines the challenges associated with occupational disease surveillance in Korea, particularly emphasizing the limitations of current data sources such as the Industrial Accident Compensation Insurance (IACI) statistics and special health examinations. The IACI system undercounts cases due to its emphasis on severe diseases and restrictions on approvals. Special health examinations, although they cover a broad workforce, are constrained by their annual scheduling, which leads to missed acute illnesses and subclinical conditions. The paper also explores the history of occupational disease surveillance in Korea, highlighting the fragmented and disease-specific approach of earlier systems. The authors introduce the newly established Korea Occupational Disease Surveillance Center (KODSC), a comprehensive nationwide system designed to gather, analyze, and interpret data on occupational diseases through a network of regional centers. By incorporating hospital-based surveillance and focusing on acute poisonings and other sentinel events, the KODSC aims to overcome the limitations of previous systems and promote collaboration with various agencies. Although it is still in the early stages of implementation, the KODSC demonstrates potential for improving data accuracy and contributing valuable insights for public health policy.

The prevalence of postpartum depression (PPD) in Asia is reported to range from 13.53% to 22.31%. However, there remains a gap in the identification of PPD, particularly regarding cultural cutoff points. Therefore, the purpose of this scoping review was to determine the prevalence and associated factors of PPD in Eastern, South-eastern, Western, and Southern Asian countries and analyze the cutoff points of the Edinburgh Postnatal Depression Scale (EPDS) used across these countries. Following Arksey and O'Malley’s five-step scoping review framework, the population was defined as mothers, the concept as the EPDS, and the context as the Asian region. A literature search was conducted using PubMed, Embase, CINAHL, PsycINFO, and Web of Science. The data analysis focused on demographic characteristics, EPDS cutoffs and features, PPD prevalence, and its associated factors. Nineteen studies were selected. Most countries used translated versions of the EPDS with demonstrated reliability and validity. The cutoff scores varied, with most using scores of 10 or higher. The prevalence of PPD ranged from 5.1% to 78.7%. Key associated factors for PPD included cultural factors such as relationships with in-laws and preferences for the newborn’s sex. To improve the accuracy of PPD screening in Asia, the EPDS should be used consistently, and appropriate cutoff criteria must be established. In addition, prevention strategies and programs that reflect the cultural characteristics and social context of Asia need to be developed for the early detection and prevention of PPD.