Radiology

Latest Articles

Original Research

Breast Imaging   Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms   A deep learning algorithm trained on a linked data set of mammograms and electronic health records achieved breast cancer detection accuracy comparable to radiologists as defined by the Breast Cancer Surveillance Consortium benchmark for screening digital mammography and revealed additional clinical risk features.      Ayelet Akselrod-Ballin, Michal Chorev...Michal Guindy

Performance and Reading Time of Automated Breast US with or without Computer-aided Detection   Both the second-reading mode and concurrent-reading mode have the potential to improve novice readers' performance for breast cancer screening on an automated breast US.   Shanling Yang, Xican Gao...Hongping Song

Editorial: Does Computer-aided Detection Help in Interpretation of Automated Breast US? Priscilla J. Slanetz

Computer Applications   Deep Learning–based Image Conversion of CT Reconstruction Kernels Improves Radiomics Reproducibility for Pulmonary Nodules or Masses   CT image conversion using a convolutional neural network can reduce the effect of different reconstruction kernels on radiomic parameters. This will facilitate comparison of image features derived from different CT scanners.     Jooae Choe, Sang Min Lee...Joon Beom Seo

Editorial: Can Artificial Intelligence Fix the Reproducibility Problem of Radiomics? Chang Min Park

Gastrointestinal Imaging   Validation of US Liver Imaging Reporting and Data System Version 2017 in Patients at High Risk for Hepatocellular Carcinoma   The US visualization score of C had higher false-negative rates than scores A or B for detecting hepatocellular carcinoma. Patients with risk factors for a poor visualization score (US visualization score of C), namely high body weight, Child-Pugh score B, and moderate to severe fatty liver, may present limitations for US surveillance.    Jung Hee Son, Sang Hyun Choi...Young Suk Lim

Editorial: Does Hepatocellular Carcinoma Screening with US Work? Using the US LI-RADS Algorithm Laurent Milot

Neuroradiology   Reproducibility and Repeatability of MR Fingerprinting Relaxometry in the Human Brain   Relaxation times in solid compartments of the human brain measured with fast imaging with steady-state free precession MR fingerprinting varied less than 8.0% (95% confidence intervals: -8.0%, 8.0%) across multiple 3.0-T scanners from a single vendor at different sites.   Gregor Körzdörfer, Rainer Kirsch...Mathias Nittka

Editorial: Reproducing Fingerprints: A Step toward Clinical Adoption Frederik Barkhof, Geoff J. M. Parker

Special Report   Bosniak Classification of Cystic Renal Masses, Version 2019: An Update Proposal and Needs Assessment   It is hoped that this review of the current Bosniak classification and the proposed update will enhance the classification's clarity and specificity, be useful in clinical practice, serve as substrate for future study, and lead to future updates that emphasize the clinical significance of the cancers the classification aims to diagnose.   Stuart G. Silverman, Ivan Pedrosa...Matthew S. Davenport

Reviews and Commentary

Images in Radiology   Inferior Vena Cava Thrombosis in Behçet Disease   Furkan Ufuk