Korean journal of radiology : official journal of the Korean Radiological Society
-
The artificial neural network (ANN)-a machine learning technique inspired by the human neuronal synapse system-was introduced in the 1950s. However, the ANN was previously limited in its ability to solve actual problems, due to the vanishing gradient and overfitting problems with training of deep architecture, lack of computing power, and primarily the absence of sufficient data to train the computer system. ⋯ Recent studies on this technology suggest its potentially to perform better than humans in some visual and auditory recognition tasks, which may portend its applications in medicine and healthcare, especially in medical imaging, in the foreseeable future. This review article offers perspectives on the history, development, and applications of deep learning technology, particularly regarding its applications in medical imaging.
-
Radiofrequency ablation (RFA) is a well-known, effective, and safe method for treating benign thyroid nodules and recurrent thyroid cancers. Thyroid-dedicated devices and basic techniques for thyroid RFA were introduced by the Korean Society of Thyroid Radiology (KSThR) in 2012. ⋯ To optimize the treatment efficacy and patient safety, understanding the basic and advanced RFA techniques and selecting the optimal treatment strategy are critical. The goal of this review is to therefore provide updates and analysis of current devices and advanced techniques for RFA treatment of benign thyroid nodules and recurrent thyroid cancers.
-
The corpus callosum (CC) is the largest white matter structure in the brain, consisting of more than 200-250 million axons that provide a large connection mainly between homologous cerebral cortical areas in mirror image sites. The posterior end of the CC is the thickest part, which is called the splenium. ⋯ MR imaging is useful for the detection and differential diagnosis of splenial lesions of the CC. In this study, we classify the disease entities and describe imaging findings of lesions involving the splenium of the CC based on our experiences and a review of the literature.