In order to properly train and validate algorithms, developers need high volumes of quality-labeled data. But such datasets are not easy to obtain.

A convolutional neural network (CNN) approach can accurately identify and sub-classify suspected tuberculosis (TB) on chest radiographs, according to research presented at the Society for Imaging Informatics in Medicine (SIIM) annual meeting.

Positron emission tomography/computed tomography (PET/CT) shows a strong correlation between severe obstructive sleep apnea (OSA) and impaired coronary flow, making it an important tool for helping to avert cardiac complications that occur when OSA is left untreated.

Predictions of heart attacks and deaths based on coronary computed tomography angiography (CCTA) are more accurate when made using an artificial intelligence (AI) algorithm than with the Coronary Artery Disease Reporting and Data System (CAD-RADS) or other risk assessment methods.

Supplemental training can improve radiologists’ performance in reading screening mammograms, according to a recent study.

A new CT- and PET-imaging-based approach—one that entails applying big data to personalizing treatment protocols—is needed to better identify which head and neck carcinoma (HNC) patient subgroups respond to which specific therapies.

The National Electrical Manufacturers Association (NEMA) has published an updated edition of its manual for measuring and reporting performance parameters of SPECT scanners.  

Adding a scan during a patient’s prostate cancer therapy can help personalize treatment, according to research presented at the Society of Nuclear Medicine and Molecular Imaging (SNMMI)’s 2019 Annual Meeting in Anaheim, Calif.

Although most studies demonstrating the benefits of digital breast tomosynthesis (DBT) have been observational, use of the modality has risen dramatically over the past few years, according to a study of more than nine million women published in JAMA Internal Medicine.