Korean Journal of Radiology 

About: Korean Journal of Radiology is an academic journal published by Korean Society of Radiology. The journal publishes majorly in the area(s): Medicine & Magnetic resonance imaging. It has an ISSN identifier of 1229-6929. Over the lifetime, 2406 publications have been published receiving 50026 citations.

Deep Learning in Medical Imaging: General Overview.

Abstract: 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. Interest in this concept has lately resurfaced, due to the availability of big data, enhanced computing power with the current graphics processing units, and novel algorithms to train the deep neural network. 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.

Receiver Operating Characteristic (ROC) Curve: Practical Review for Radiologists

Abstract: The receiver operating characteristic (ROC) curve, which is defined as a plot of test sensitivity as they coordinate versus its 1-specificity or false positive rate (FPR) as the x coordinate, is an effective method of evaluating the performance of diagnostic tests. The purpose of this article is to provide a nonmathematical introduction to ROC analysis. Important concepts involved in the correct use and interpretation of this analysis, such as smooth and empirical ROC curves, parametric and nonparametric methods, the area under the ROC curve and its 95% confidence interval, the sensitivity at a particular FPR, and the use of a partial area under the ROC curve are discussed. Various considerations concerning the collection of data in radiological ROC studies are briefly discussed. An introduction to the software frequently used for performing ROC analyses is also presented.

Ultrasonography Diagnosis and Imaging-Based Management of Thyroid Nodules: Revised Korean Society of Thyroid Radiology Consensus Statement and Recommendations

Abstract: The rate of detection of thyroid nodules and carcinomas has increased with the widespread use of ultrasonography (US), which is the mainstay for the detection and risk stratification of thyroid nodules as well as for providing guidance for their biopsy and nonsurgical treatment. The Korean Society of Thyroid Radiology (KSThR) published their first recommendations for the US-based diagnosis and management of thyroid nodules in 2011. These recommendations have been used as the standard guidelines for the past several years in Korea. Lately, the application of US has been further emphasized for the personalized management of patients with thyroid nodules. The Task Force on Thyroid Nodules of the KSThR has revised the recommendations for the ultrasound diagnosis and imaging-based management of thyroid nodules. The review and recommendations in this report have been based on a comprehensive analysis of the current literature and the consensus of experts.

Chest Radiographic and CT Findings of the 2019 Novel Coronavirus Disease (COVID-19): Analysis of Nine Patients Treated in Korea.

Abstract: OBJECTIVE: This study presents a preliminary report on the chest radiographic and computed tomography (CT) findings of the 2019 novel coronavirus disease (COVID-19) pneumonia in Korea. MATERIALS AND METHODS: As part of a multi-institutional collaboration coordinated by the Korean Society of Thoracic Radiology, we collected nine patients with COVID-19 infections who had undergone chest radiography and CT scans. We analyzed the radiographic and CT findings of COVID-19 pneumonia at baseline. Fisher's exact test was used to compare CT findings depending on the shape of pulmonary lesions. RESULTS: Three of the nine patients (33.3%) had parenchymal abnormalities detected by chest radiography, and most of the abnormalities were peripheral consolidations. Chest CT images showed bilateral involvement in eight of the nine patients, and a unilobar reversed halo sign in the other patient. In total, 77 pulmonary lesions were found, including patchy lesions (39%), large confluent lesions (13%), and small nodular lesions (48%). The peripheral and posterior lung fields were involved in 78% and 67% of the lesions, respectively. The lesions were typically ill-defined and were composed of mixed ground-glass opacities and consolidation or pure ground-glass opacities. Patchy to confluent lesions were primarily distributed in the lower lobes (p = 0.040) and along the pleura (p < 0.001), whereas nodular lesions were primarily distributed along the bronchovascular bundles (p = 0.006). CONCLUSION: COVID-19 pneumonia in Korea primarily manifested as pure to mixed ground-glass opacities with a patchy to confluent or nodular shape in the bilateral peripheral posterior lungs. A considerable proportion of patients with COVID-19 pneumonia had normal chest radiographs.

Ultrasonography and the Ultrasound-Based Management of Thyroid Nodules: Consensus Statement and Recommendations

Abstract: The detection of thyroid nodules has become more common with the widespread use of ultrasonography (US). US is the mainstay for detecting and making the differential diagnosis of thyroid nodules as well as for providing guidance for a biopsy. The Task Force on Thyroid Nodules of the Korean Society of Thyroid Radiology has developed recommendations for the US diagnosis and US-based management of thyroid nodules. The review and recommendations in this report have been based on a comprehensive analysis of the current literature, the results of multicenter studies and from the consensus of experts.