A convolutional neural network (CNN) model performed as well as clinicians in classifying the area of concern in retinal fundus images and provided evidence for why those choices were made—a common problem for artificial intelligence (AI) technology.
MIT researchers have developed an artificial intelligence-(AI) based algorithm that can register three-dimensional (3D) images 1,000 times more quickly than standard medical image registration techniques.
Research presented at ASCO 2018 found that using contrast perfusion-weighted MRI enhanced by artificial intelligence (AI) and texture analysis can differentiate between brain tumors according to their mutation status.
“The most striking thing to me as a researcher crafting these attacks was probably how easy they were to carry out," said study lead author Samuel Finlayson, a computer scientist and biomedical informatician at Harvard Medical School in Boston, in an IEEE Spectrum story.
Artificial intelligence (AI) is poised to change transportation with self-driving vehicles, Kimberly Powell, with the Nvidia Corporation, and colleagues believe their work on the subject can also be applied to radiology.
The Society for Imaging Informatics in Medicine’s 2018 annual meeting wrapped up with a keynote address from Curt Langlotz, MD, PhD, with Stanford University, on the rise of artificial intelligence (AI).
A professor of radiology at Johns Hopkins Medicine in Baltimore and computer science students are developing a tumor-detecting AI algorithm that can be built into computed tomography (CT) scanner software to recognize and differentiate between a normal pancreas and one that's cancerous.
When compared to the performance of 58 dermatologists from 17 different countries around the world, AI missed fewer melanomas and misdiagnosed benign moles less often, according to a study published in the Annals of Oncology.
Theresa May, Prime Minister of the United Kingdom, has pledged millions toward government funding that will develop a "new weapon"—artificial intelligence (AI) able to improve cancer and chronic disease diagnosis.
Researchers utilized a machine learning algorithm to determine that a higher rate of change—rather than actual value of cancer antigen 125 (CA125)—is associated with abdominal recurrence of ovarian cancer. Findings may help identify patients most likely to benefit from imaging surveillance of the disease.
University College London Hospital (UCLH) and the Alan Turing Institute in London have entered a three-year partnership to allow artificial intelligence (AI) to perform a variety of clinical tasks otherwise done by nurses and physicians.