Radiology: Artificial Intelligence,

November 2019 Volume 1, Issue 6

Meet Dr. Kahn at RSNA on Monday, December 2 at 2:00 PM CST in the Publications Booth (booth 1119)!

Editorials

Looking Ahead Charles E. Kahn, Jr

Special Feature   Magician's Corner 3: Image Wrangling Bradley J. Erickson

Original Research

Fully Automated CT Quantification of Epicardial Adipose Tissue by Deep Learning: A Multicenter Study   Deep learning allows for fast, robust, and fully automated quantification of epicardial adipose tissue from non–contrast material–enhanced calcium-scoring CT.     Frederic Commandeur, Markus Goeller...Damini Dey

Commentary: Greasing the Skids: Deep Learning for Fully Automated Quantification of Epicardial Fat U. Joseph Schoepf, Andres F. Abadia

Deep Learning–based CT Image Reconstruction: Initial Evaluation Targeting Hypovascular Hepatic Metastases   A deep learning–based reconstruction method can quantitatively and qualitatively improve the quality of abdominal CT images for the evaluation of hypovascular hepatic metastases.     Yuko Nakamura, Toru Higaki...Kazuo Awai

Improving Low-Dose Pediatric Abdominal CT by Using Convolutional Neural Networks   Convolutional neural networks can reduce image noise and artifacts to improve low-dose pediatric abdominal CT images reconstructed with filtered back projection.     Robert D. MacDougall, Yanbo Zhang...Hengyong Yu

Deep Learning–based Prescription of Cardiac MRI Planes   Deep learning–based localization is a feasible strategy for planning cardiac MRI planes.     Kevin Blansit, Tara Retson...Albert Hsiao

Improving Automated Pediatric Bone Age Estimation Using Ensembles of Models from the 2017 RSNA Machine Learning Challenge   Ensembles created using models submitted to an open competition convincingly outperformed single-model prediction for bone age assessment.     Ian Pan, Hans Henrik Thodberg...David B. Larson

Commentary: Making AI Even Smarter Using Ensembles: A Challenge to Future Challenges and Implications for Clinical Care Eliot L. Siegel

Technical Development

A User Interface for Optimizing Radiologist Engagement in Image Data Curation for Artificial Intelligence   A graphical user interface promoted involvement of local-expert subspecialty radiologists in ongoing image data curation, including case-by-case annotation, potentially concurrent with artificial intelligence–enhanced routine image review in support of ongoing model learning.     Mutlu Demirer, Sema Candemir...Barbaros S. Erdal