An assistant professor of medicine at the University of California, San Francisco, Arnaout is focusing on the potential of AI to analyze cardiac ultrasounds and detect congenital heart disease from fetal ultrasounds.
“In medicine, a picture is worth more than a thousand words,” she said. “It really can be worth a patient’s life, in some cases.”
What Can AI Do to Help?
Arnaout outlined a few key challenges for humans analyzing medical images. For one, people sometimes make mistakes. There’s also a physical limit to how much data cardiac imaging specialists like cardiologists and radiologists can analyze.
“We cannot allow those kinds of shortcomings,” she said. “We need accuracy, precision, and we need it delivered at scale.”
While AI models are not without their limitations, Arnaout said, they can help clinicians use medical imaging techniques like ultrasound to their full potential.
She turned to echocardiogram data because “it’s balanced in terms of information richness and clinical volume compared to other cardiovascular imaging tools.” Since echocardiograms can be used for the diagnosis and management of almost every cardiovascular disease, she said, there’s very little selection bias in the datasets.
Echocardiograms are a challenging training dataset, however, because one ultrasound study consists of still images and videos captured from over a dozen angles. A study Arnaout’s team published in npj Digital Medicine used deep learning to classify 15 of these standard views, achieving 91.7 percent accuracy on low-resolution images.
Image Credit: Photo by Kjetil Lenes/Ekko, licensed under public domain on Wikimedia Commons.
News This Week
What if you didn’t need surgery to implant a pacemaker on a faulty heart? What if you could control your blood sugar levels without an injection of insulin, or mitigate the onset of a [...]
Guided by artificial intelligence and powered by a robotic platform, a system developed by MIT researchers moves a step closer to automating the production of small molecules that could be used in medicine, solar [...]
Thin, flexible fibers made of carbon nanotubes have now proven able to bridge damaged heart tissues and deliver the electrical signals needed to keep those hearts beating. Scientists at Texas Heart Institute (THI) report they have [...]
The lab of Cheryl Kerfeld at Michigan State University has created a synthetic nano-sized factory, based on natural ones found in bacteria. This research could someday lead to new medical, industrial or bioenergy [...]
Melanoma in skin biopsy with H&E stain — this case may represent superficial spreading melanoma. Credit: Wikipedia/CC BY-SA 3.0 Researchers at Tel Aviv University have developed a novel nano-vaccine for melanoma, the most aggressive [...]
Modern light microscopic techniques provide extremely detailed insights into organs, but the terabytes of data they produce are usually nearly impossible to process. New software, developed by a team led by MDC scientist Dr. [...]
It has long been known that gold can be used to do things that philosophers have never even dreamed of. The Institute of Nuclear Physics of the Polish Academy of Sciences in Cracow has [...]
“We’ll have nanobots that… connect our neocortex to a synthetic neocortex in the cloud. Our thinking will be a…. biological and non-biological hybrid.” Ray Kurzweil, TED 2014 UPDATE - August 6 2019 Since [...]
DARPA has awarded funding to six organizations to support the Next-Generation Nonsurgical Neurotechnology (N3) program, first announced in March 2018. Battelle Memorial Institute, Carnegie Mellon University, Johns Hopkins University Applied Physics Laboratory, Palo Alto [...]
Source: Bold Business. Follow them on twitter. Though you may not realize it, more than 40,000 computer-brain interfaces have already been employed in healthcare today. Thus, to say computer-brain interfaces are something new would [...]
It is hard to imagine just how small one nanometer—one-billionth of a meter—really is. Ten hydrogen atoms in a row are one nanometer long. For perspective, consider that a sheet of paper is 75,000 [...]