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.

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: We aimed to examine the prevalence of burnout among imaging cardiologists in Korea and to identify its associated factors. Methods: An online survey of imaging cardiologists affiliated with university hospitals in Korea was conducted using SurveyMonkey ® in November 2023. The validated Korean version of the Maslach Burnout Inventory-Human Service Survey was used to assess burnout across three dimensions: emotional exhaustion, depersonalization, and lack of personal accomplishment. Data on demographics, work environment factors, and job satisfaction were collected using structured questionnaires. Results: A total of 128 imaging cardiologists (46.1% men; 76.6% aged ≤ 50 years) participated in the survey. Regarding workload, 74.2% of the respondents interpreted over 50 echocardiographic examinations daily, and 53.2% allocated > 5 of 10 working sessions per week to echocardiographic laboratory duties. Burnout levels were high, with a significant proportion of participants experiencing emotional exhaustion (28.1%), depersonalization (63.3%), and a lack of personal accomplishment (92.2%). Younger age (< 50 years) was correlated with higher emotional exhaustion risk, while more research time was protective against burnout in the depersonalization domain. Factors, such as being single, living with family, and specific job satisfaction facets, including uncontrollable workload and value mismatch, were associated with varying levels of burnout risk across different dimensions Conclusion Our study underscores the high burnout rates among Korean imaging cardiologists, attributed to factors such as the subjective environment and job satisfaction.Hence, evaluating and supporting cardiologists in terms of individual values and subjective factors are important to effectively prevent burnout..

Background/Aims: Combi-elastography is a B-mode ultrasound-based method in which two elastography modalities are utilized simultaneously to assess metabolic dysfunction-associated steatotic liver disease (MASLD). However, the performance of combi-elastography for diagnosing metabolic dysfunction-associated steatohepatitis (MASH) and determining fibrosis severity is unclear. This study compared the diagnostic performances of combi-elastography and vibrationcontrolled transient elastography (VCTE) for identifying hepatic steatosis, fibrosis, and high-risk MASH. Methods: Participants who underwent combi-elastography, VCTE, and liver biopsy were selected from a prospective cohort of patients with clinically suspected MASLD. Combi-elastographyrelated parameters were acquired, and their performances were evaluated using area under the receiver-operating characteristic curve (AUROC) analysis. Results: A total of 212 participants were included. The diagnostic performance for hepatic steatosis of the attenuation coefficient adjusted by covariates from combi-elastography was comparable to that of the controlled attenuation parameter measured by VCTE (AUROC, 0.85 vs 0.85; p=0.925). The performance of the combi-elastography-derived fibrosis index adjusted by covariates for diagnosing significant fibrosis was comparable to that of liver stiffness measured by VCTE (AUROC, 0.77 vs 0.80; p=0.573). The activity index from combi-elastography adjusted by covariates was equivalent to the FibroScan-aspartate aminotransferase score in diagnosing high-risk MASH among participants with MASLD (AUROC, 0.72 vs 0.74; p=0.792). Conclusions The performance of combi-elastography is similar to that of VCTE when evaluating histology of MASLD.

Background: We aimed to examine the prevalence of burnout among imaging cardiologists in Korea and to identify its associated factors. Methods: An online survey of imaging cardiologists affiliated with university hospitals in Korea was conducted using SurveyMonkey ® in November 2023. The validated Korean version of the Maslach Burnout Inventory-Human Service Survey was used to assess burnout across three dimensions: emotional exhaustion, depersonalization, and lack of personal accomplishment. Data on demographics, work environment factors, and job satisfaction were collected using structured questionnaires. Results: A total of 128 imaging cardiologists (46.1% men; 76.6% aged ≤ 50 years) participated in the survey. Regarding workload, 74.2% of the respondents interpreted over 50 echocardiographic examinations daily, and 53.2% allocated > 5 of 10 working sessions per week to echocardiographic laboratory duties. Burnout levels were high, with a significant proportion of participants experiencing emotional exhaustion (28.1%), depersonalization (63.3%), and a lack of personal accomplishment (92.2%). Younger age (< 50 years) was correlated with higher emotional exhaustion risk, while more research time was protective against burnout in the depersonalization domain. Factors, such as being single, living with family, and specific job satisfaction facets, including uncontrollable workload and value mismatch, were associated with varying levels of burnout risk across different dimensions Conclusion Our study underscores the high burnout rates among Korean imaging cardiologists, attributed to factors such as the subjective environment and job satisfaction.Hence, evaluating and supporting cardiologists in terms of individual values and subjective factors are important to effectively prevent burnout..

Purpose: Vascular endothelial growth factor tyrosine kinase inhibitors (TKIs) have been the standard of care for advanced and metastatic clear cell renal cell carcinoma (ccRCC). However, the therapeutic effect of TKI monotherapy remains unsatisfactory given the high rates of acquired resistance to TKI therapy despite favorable initial tumor response. Materials and Methods: To define the TKI-resistance mechanism and identify new therapeutic target for TKI-resistant ccRCC, an integrative differential gene expression analysis was performed using acquired resistant cohort and a public dataset. Sunitinib-resistant RCC cell lines were established and used to test their malignant behaviors of TKI resistance through in vitro and in vivo studies. Immunohistochemistry was conducted to compare expression between the tumor and normal kidney and verify expression of pathway-related proteins. Results: Integrated differential gene expression analysis revealed increased interferon-induced transmembrane protein 3 (IFITM3) expression in post-TKI samples. IFITM3 expression was increased in ccRCC compared with the normal kidney. TKI-resistant RCC cells showed high expression of IFITM3 compared with TKI-sensitive cells and displayed aggressive biologic features such as higher proliferative ability, clonogenic survival, migration, and invasion while being treated with sunitinib. These aggressive features were suppressed by the inhibition of IFITM3 expression and promoted by IFITM3 overexpression, and these findings were confirmed in a xenograft model. IFITM3-mediated TKI resistance was associated with the activation of TRAF6 and MAPK/AP-1 pathways. Conclusions These results demonstrate IFITM3-mediated activation of the TRAF6/MAPK/AP-1 pathways as a mechanism of acquired TKI resistance, and suggest IFITM3 as a new target for TKI-resistant ccRCC.

Background/Aims: Combi-elastography is a B-mode ultrasound-based method in which two elastography modalities are utilized simultaneously to assess metabolic dysfunction-associated steatotic liver disease (MASLD). However, the performance of combi-elastography for diagnosing metabolic dysfunction-associated steatohepatitis (MASH) and determining fibrosis severity is unclear. This study compared the diagnostic performances of combi-elastography and vibrationcontrolled transient elastography (VCTE) for identifying hepatic steatosis, fibrosis, and high-risk MASH. Methods: Participants who underwent combi-elastography, VCTE, and liver biopsy were selected from a prospective cohort of patients with clinically suspected MASLD. Combi-elastographyrelated parameters were acquired, and their performances were evaluated using area under the receiver-operating characteristic curve (AUROC) analysis. Results: A total of 212 participants were included. The diagnostic performance for hepatic steatosis of the attenuation coefficient adjusted by covariates from combi-elastography was comparable to that of the controlled attenuation parameter measured by VCTE (AUROC, 0.85 vs 0.85; p=0.925). The performance of the combi-elastography-derived fibrosis index adjusted by covariates for diagnosing significant fibrosis was comparable to that of liver stiffness measured by VCTE (AUROC, 0.77 vs 0.80; p=0.573). The activity index from combi-elastography adjusted by covariates was equivalent to the FibroScan-aspartate aminotransferase score in diagnosing high-risk MASH among participants with MASLD (AUROC, 0.72 vs 0.74; p=0.792). Conclusions The performance of combi-elastography is similar to that of VCTE when evaluating histology of MASLD.