Using brain MRI and a deep learning network, researchers have achieved 97% accuracy at classifying a gene mutation indicative of growth in localized gliomas.

A deep-learning algorithm has accurately measured 26 pairs of uneven leg lengths on children’s x-rays at a rate 96 times faster than that recorded by an experienced, subspecialty-trained pediatric radiologist using manual means.

For finding microcalcifications in screening exams, full-field digital mammography now has little to recommend it over reduced-radiation 2D synthetic mammography.

As an aid to tumor-resection neurosurgery and its planning, fluorescence imaging has been limited by its tendency to scatter light. Researchers are working on technology that would overcome this shortcoming.

As the research mounts on AI matching or besting radiologists in discrete interpretive tasks, so does the excitement in the popular press. Now comes a study showing many of these studies only invite the hype.  

In the face of the coronavirus crisis, all radiologists can do for some of their pathologist peers is stand, salute and express solidarity.

Imaging experts are concerned artificial intelligence is not being trained on robust datasets, while developers say their platforms are already working in real-world situations.

“This is one of the first times that artificial intelligence has been used to better define the different parts of a newborn's brain on an MRI," Canadian researchers explained March 26 in Frontiers in Neuroscience.