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.

This phase 3 study evaluated the efficacy and safety of 6-month treatment with romosozumab in Korean postmenopausal women with osteoporosis. Sixty-seven postmenopausal women with osteoporosis (bone mineral density [BMD] T-scores ≤-2.5 at the lumbar spine, total hip, or femoral neck) were randomized (1:1) to receive monthly subcutaneous injections of romosozumab (210 mg; n=34) or placebo (n=33) for 6 months. At month 6, the difference in the least square (LS) mean percent change from baseline in lumbar spine BMD (primary efficacy endpoint) between the romosozumab (9.5%) and placebo (-0.1%) groups was significant (9.6%; 95% confidence interval, 7.6 to 11.5; P<0.001). The difference in the LS mean percent change from baseline was also significant for total hip and femoral neck BMD (secondary efficacy endpoints). After treatment with romosozumab, the percent change from baseline in procollagen type 1 N-terminal propeptide transiently increased at months 1 and 3, while that in C-terminal telopeptide of type 1 collagen showed a sustained decrease. No events of cancer, hypocalcemia, injection site reaction, positively adjudicated atypical femoral fracture or osteonecrosis of the jaw, or positively adjudicated serious cardiovascular adverse events were observed. At month 9, 17.6% and 2.9% of patients in the romosozumab group developed binding and neutralizing antibodies, respectively. Treatment with romosozumab for 6 months was well tolerated and significantly increased lumbar spine, total hip, and femoral neck BMD compared with placebo in Korean postmenopausal women with osteoporosis (ClinicalTrials.gov identifier NCT02791516).

This review article investigates solid organ transplantation-induced osteoporosis, a critical yet often overlooked issue, emphasizing its significance in post-transplant care. The initial sections provide a comprehensive understanding of the prevalence and multifactorial pathogenesis of transplantation osteoporosis, including factors such as deteriorating post-transplantation health, hormonal changes, and the impact of immunosuppressive medications. Furthermore, the review is dedicated to organ-specific considerations in transplantation osteoporosis, with separate analyses for kidney, liver, heart, and lung transplantations. Each section elucidates the unique challenges and management strategies pertinent to transplantation osteoporosis in relation to each organ type, highlighting the necessity of an organ-specific approach to fully understand the diverse manifestations and implications of transplantation osteoporosis. This review underscores the importance of this topic in transplant medicine, aiming to enhance awareness and knowledge among clinicians and researchers. By comprehensively examining transplantation osteoporosis, this study contributes to the development of improved management and care strategies, ultimately leading to improved patient outcomes in this vulnerable group. This detailed review serves as an essential resource for those involved in the complex multidisciplinary care of transplant recipients.