"Radiologists developing convolutional neural networks should recognize and preemptively address this pitfall," experts explained in AJR.

AI proved useful for detecting axillary lymph node metastases but isn’t yet ready for clinics, experts said recently.

The neural network may best serve as a supportive tool for radiologists assessing sacroiliac joints, researchers said recently.

The tool may lead to substantial clinical management benefits for those with the disease, according to a new study in JAMA Network Open.

CAD surpassed three radiologists at identifying two out of seven chest findings, including pulmonary nodules and infectious consolidation, a new study shows.

The platform utilizing both image types detected cancer with a positive predictive value of 44%, beating out a contrast-only approach.

The specialty needs to work together and address a number of issues surrounding the disruptive technology, Yale Director of MRI Services Jeffrey C. Weinreb, MD, argued.

The development involves ultrafast photon detectors and doesn't rely on conventional tomography, researchers reported recently in Nature Photonics.

Diagnostic scores assigned to chest CT scans can be used as a sign that providers must carefully inspect images for abnormalities, researchers said in Radiology: Artificial Intelligence.

The X-ray technique may reduce patients’ radiation dose by a factor of fifty, according to a new study published in The Lancet Digital Health.

The J-PET scanner will enable total-body positron emission tomography machines to be produced five times cheaper than traditional crystal-based technologies, experts said recently.

The AI approach may prove more effective than PET/CT, which can only diagnose N2 disease with 70-85% sensitivity, researchers reported Tuesday in Radiology.