Radiofrequency ablation (RFA) is a minimally invasive treatment modality used as an alternative to surgery in patients with benign thyroid nodules, recurrent thyroid cancers (RTCs), and primary thyroid microcarcinomas. The Korean Society of Thyroid Radiology (KSThR) initially developed recommendations for the optimal use of RFA for thyroid tumors in 2009 and revised them in 2012 and 2017. As new meaningful evidence has accumulated since 2017 and in response to a growing global interest in the use of RFA for treating malignant thyroid lesions, the task force committee members of the KSThR decided to update the guidelines on the use of RFA for the management of RTCs based on a comprehensive analysis of current literature and expert consensus.

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.

Purpose: Pancreatic cancer has a poor prognosis; however, the implementation of neoadjuvant treatment enables borderline resectable cases to undergo curative resection and improves the overall survival rate. Attempts have been made to expand the eligibility criteria for neoadjuvant treatment, even in resectable cases. Some studies have suggested a correlation between vein abutment and poor prognosis or that the abutment angle may affect prognosis. This study investigated the anatomical factors affecting the vessel abutment angle and its prognostic value in pancreatic cancer. Methods: Patients with pancreatic ductal adenocarcinoma who underwent surgery between 2012 and 2017 were included in this study. Patients who underwent neoadjuvant treatment were excluded. Data from only the intent-to-treat pancreaticoduodenectomy group were included in the analysis. Clinicopathological characteristics; preoperative factors such as CA 19-9, preoperative biliary drainage, American Society of Anesthesiologists physical status classification, portal vein/superior mesenteric vein contact angle measured via CT scan; and intraoperative factors were collected for analysis. Results: A total of 365 patients were included in this study, and the abutment group included 92 patients (25.2%). The abutment and no-contact groups did not show any significant differences in terms of the overall survival or diseasefree survival rate. Among the abutment groups, patients with less than 90° and 90°–180° did not show any significant differences. In the multivariate analysis, the only preoperative factor that had a prognostic effect was CA 19-9, a biological factor. Conclusion When there is no vessel invasion in the abutment group, upfront surgery should be considered because the angle does not affect the overall prognosis.

Radiofrequency ablation (RFA) is a minimally invasive treatment modality used as an alternative to surgery in patients with benign thyroid nodules, recurrent thyroid cancers (RTCs), and primary thyroid microcarcinomas. The Korean Society of Thyroid Radiology (KSThR) initially developed recommendations for the optimal use of RFA for thyroid tumors in 2009 and revised them in 2012 and 2017. As new meaningful evidence has accumulated since 2017 and in response to a growing global interest in the use of RFA for treating malignant thyroid lesions, the task force committee members of the KSThR decided to update the guidelines on the use of RFA for the management of RTCs based on a comprehensive analysis of current literature and expert consensus.

Radiofrequency ablation (RFA) is a minimally invasive treatment modality used as an alternative to surgery in patients with benign thyroid nodules, recurrent thyroid cancers (RTCs), and primary thyroid microcarcinomas. The Korean Society of Thyroid Radiology (KSThR) initially developed recommendations for the optimal use of RFA for thyroid tumors in 2009 and revised them in 2012 and 2017. As new meaningful evidence has accumulated since 2017 and in response to a growing global interest in the use of RFA for treating malignant thyroid lesions, the task force committee members of the KSThR decided to update the guidelines on the use of RFA for the management of RTCs based on a comprehensive analysis of current literature and expert consensus.

Lecanemab and donanemab have received full U.S. Food and Drug Administration (FDA) approval, and subsequently, lecanemab has been approved by the Korean FDA and it has recently entered commercial use in Korea. This has increased interest in anti-amyloid immunotherapy for Alzheimer’s disease. Anti-amyloid immunotherapy has shown potential to modify the progression of the disease by specifically binding to amyloid β, a key pathological product in Alzheimer’s disease, and eliminating accumulated amyloid plaques in the brain. However, this treatment can be accompanied by a side-effect, amyloid-related imaging abnormalities (ARIA), which requires periodic monitoring by MRI. It is crucial to detect ARIA and accurately assess the severity by radiology. The role of the radiologist is important in this context, requiring proficiency in basic knowledge of ARIA, and in diagnosing/evaluating ARIA. This review aims to comprehensively cover aspects of ARIA, including its definition, pathophysiology, incidence, risk factors, assessment of severity by radiology, differential diagnosis, and management.

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.

Purpose: Pancreatic cancer has a poor prognosis; however, the implementation of neoadjuvant treatment enables borderline resectable cases to undergo curative resection and improves the overall survival rate. Attempts have been made to expand the eligibility criteria for neoadjuvant treatment, even in resectable cases. Some studies have suggested a correlation between vein abutment and poor prognosis or that the abutment angle may affect prognosis. This study investigated the anatomical factors affecting the vessel abutment angle and its prognostic value in pancreatic cancer. Methods: Patients with pancreatic ductal adenocarcinoma who underwent surgery between 2012 and 2017 were included in this study. Patients who underwent neoadjuvant treatment were excluded. Data from only the intent-to-treat pancreaticoduodenectomy group were included in the analysis. Clinicopathological characteristics; preoperative factors such as CA 19-9, preoperative biliary drainage, American Society of Anesthesiologists physical status classification, portal vein/superior mesenteric vein contact angle measured via CT scan; and intraoperative factors were collected for analysis. Results: A total of 365 patients were included in this study, and the abutment group included 92 patients (25.2%). The abutment and no-contact groups did not show any significant differences in terms of the overall survival or diseasefree survival rate. Among the abutment groups, patients with less than 90° and 90°–180° did not show any significant differences. In the multivariate analysis, the only preoperative factor that had a prognostic effect was CA 19-9, a biological factor. Conclusion When there is no vessel invasion in the abutment group, upfront surgery should be considered because the angle does not affect the overall prognosis.

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.