Radiology in public focus
Press releases were sent to the medical news media for the following articles appearing in a recent issue of Radiology.
Deep Learning Model Classifies Brain Tumors with Single MRI Scan
A team of researchers at Washington University School of Medicine have developed a deep learning model that is capable of classifying a brain tumor as one of six common types using a single 3D MRI scan, according to a study in Radiology: Artificial Intelligence.
“This is the first study to address the most common intracranial tumors and to directly determine the tumor class or the absence of tumor from a 3D MRI volume,” said Satrajit Chakrabarty, MS, a doctoral student under the direction of Aristeidis Sotiras, PhD, and Daniel Marcus, PhD, in Mallinckrodt Institute of Radiology’s Computational Imaging Lab at Washington University School of Medicine in St. Louis.
To build their machine learning model, Chakrabarty and researchers from Mallinckrodt Institute of Radiology developed a large, multi-institutional dataset of intracranial 3D MRI scans from four publicly available sources. Using the internal testing data, the model achieved an accuracy of 93.35% (337 of 361) across seven imaging classes (a healthy class and six tumor classes).
“These results suggest that deep learning is a promising approach for automated classification and evaluation of brain tumors,” Chakrabarty said. “The model achieved high accuracy on a heterogeneous dataset and showed excellent generalization capabilities on unseen testing data.”
For More Information
Access the Radiology: Artificial Intelligence study, “MRI-based Identification and Classification of Major Intracranial Tumor Types Using a 3D Convolutional Neural Network: A Retrospective Multi-Institutional Analysis."
Prediction Models May Reduce False-Positives in MRI Breast Cancer Screening
Prediction models based on clinical characteristics and imaging findings may help reduce the false-positive rate in women with dense breasts who undergo supplemental breast cancer screening with MRI, according to a new study in Radiology.
“The reduction of the false-positive recall rate is an important issue when considering the use of breast MRI as a screening tool,” said study lead author Bianca M. den Dekker, MD, from the University Medical Center Utrecht in Utrecht, the Netherlands.
In the new study, Dr. den Dekker and colleagues developed prediction models to distinguish true-positive MRI screening from false-positives. Of the 454 women who had a positive MRI result in a first supplemental MRI screening round, 79 were diagnosed with breast cancer, meaning that 375 women had false-positive MRI examinations. The full prediction model, based on all collected clinical characteristics and MRI findings, could have prevented 45.5% of false-positive recalls and 21.3% of benign biopsies, without missing any cancers. The model solely based on readily available MRI findings and age had a comparable performance and could have prevented 35.5% of false-positive MRI screenings and 13.0% of benign biopsies.
“Our prediction models may identify a substantial number of false-positives after first-round supplemental MRI screenings, reducing false-positive recalls and benign biopsies without missing any cancers,” Dr. den Dekker said. “This brings supplemental screening MRI for women with dense breasts one step closer to implementation.”
For More Information
Media Coverage of RSNA
In June, 1,097 RSNA-related news stories were tracked in the media. These stories reached an audience of 393 million.
Coverage included the Chicago Tribune, Houston Chronicle, The Arizona Republic, Pittsburgh Post-Gazette, ScienceDaily, MedPage Today, Medscape, Diagnostic Imaging, Applied Radiology, Healthcare Business News, Imaging Technology News, Radiology Business and Health Imaging News.