BI-RADS 4 lesions are considered among the most difficult and suspicious category of breast lesions.

“With the ability to understand each of the different domains and translate between the experts in these domains, imaging informaticists are now essential players in the development, evaluation and deployment of AI in the clinical environment.”

Trained on nearly 1 million screening mammography images, researchers from New York University found their algorithm could push radiologists’ ability to accurately identify breast cancer to nearly 90%.

"The AI we use works almost like magic—and it will help radiologists save lives," said Antonio Sze-To, a postdoctoral fellow who worked on the project.

Santa Clara, California-based NVIDIA and King's College London are teaming up to create a new federated learning system to advance medical imaging research.

Images of patients with traumatic head injuries revealed that microbleeds appear in the form of small, dark lesions and may predict worse outcomes, according to a new study published in Brain.

Researchers found measurements performed with their full-scale airway network flow model based on CT imaging data compared similarly to measurements derived from functional lung imaging. In addition to improving COPD analysis, the platform can help shed light on many forms of lung disease.

Deep learning offers similar detection of prostate cancer on MRI compared to prostate imaging reporting and data system (PI-RADS) assessments, according to new research out of Germany.