The deep learning-based model yielded a lower false-negative rate for more aggressive cancers compared to traditional approaches.

AI holds tremendous promise for making radiologists more efficient, but when it comes to cancer care, a few experts believe the coming tech revolution may encounter a few problems.

More than 6.1 million children were diagnosed with ADHD in 2016. Despite these numbers, there is no single test or imaging exam that can confidently diagnose a patient.

The tool, detailed in an EBioMedicine study published last month, can sift through the multitudes of cells in a tissue sample and identify tumors’ growth patterns, along with other highly useful information for predicting health outcomes.

The public workshop will take place this upcoming February and will discuss computer-aided detection and diagnosis software, computer-aided triage systems and image quality enhancement algorithms, among other topics.

The technique combines AI with patient-specific health and cost information for a rough estimate on an individual's five-year healthcare expenditures.

The challenge tasked teams with developing an algorithm capable of identifying and classifying subtypes of hemorrhages on head CT scans.

Massachusetts Institute of Technology researchers harnessed machine learning to create conditional atlases that can help clinicians diagnose a wider subset of patients. 

The models encompass a wide variety of diagnostic tasks, including pneumothorax detection on chest x-rays and highlighting brain segments on MRI scans.

Experts have long talked about an ideal future in which radiologists work alongside AI. A new platform may have the answer, combining the intelligence of man and machine to better diagnose pneumonia.

In an exclusive conversation with HealthImaging, John D. Banja, a professor of medical ethics at Emory University, discusses plans to launch a series of audio chats with radiologists, exploring one of the profession's stickiest issues.

In fact, clinicians who took a second look at x-rays using the deep learning software improved their sensitivity, on average, by 5.2%.