WebZine
2018. 04
What's New
AI Cardiologist Aces Its First Medical Exam
A neural network outperforms human cardiologists in a task involving heart scans
By Eliza Strickland
Rima Arnaout wants to be clear: The AI she created to analyze heart scans, which easily outperformed human experts on its task, is not ready to replace cardiologists.
It was a limited task, she notes, just the first step in what a cardiologist does when evaluating an echocardiogram (the image produced by bouncing sound waves off the heart). “The best technique is still inside the head of the trained echocardiographer,” she says.
But with experimental artificial intelligence systems making such rapid progress in the medical realm, particularly on tasks involving medical images, Arnaout does see the potential for big changes in her profession. And when her 10-year-old cousin expressed the desire to be a radiologist when she grows up, Arnaout had some clear advice: “I told her that she should learn to code,” she says with a laugh.
Arnaout, an assistant professor and practicing cardiologist at UC San Francisco, is keeping up with the times through her research in computational medicine; she published this new study in the journal Digital Medicine.
In the study, Arnaout and her colleagues used deep learning, specifically something called a convolutional neural network, to train an AI system that can classify echocardiograms according to the type of view shown.
This classification is a cardiologist’s first step when examining an image of the heart. Because the heart is such a complex structure—it’s an asymmetrical organ with four chambers, four valves, and blood constantly flowing in and out through several vessels—echocardiographers take videos from many different positions. When the doctors are ready to analyze those videos, they first have to figure out which view they’re looking at and which anatomical features they can see.
Ultrasound-Powered Nerve Implant Works Deep in Body
An implant that goes in without surgery could help make “electroceuticals” a reality
By Samuel K. Moore
Posted 3 Apr 2018 | 19:00 GMT
Engineers at Stanford University have built a new kind of millimeter-scale nerve-stimulating implant that beats all others of its size at a crucial parameter: how deep inside the body it can operate. The 6.5-millimeter-long programmable implant can receive both power and data via ultrasound through more than 10.5 centimeters of tissue. That’s deep enough for most any application, say its inventors. And because of its versatility and small size—with some modification it could be injected through a needle rather than requiring real surgery—they envision that it will greatly expand the number of conditions treated with electrical stimulation of the body’s nerves.
So far, most of those treatments have focused on stimulating spinal nerves for controlling pain and the vagus nerve for epilepsy and depression. However, researchers have been working on expanding the role of such “electroceutical” treatments to include ending postpartum bleeding, alleviating rheumatoid arthritis, and restoring bladder control, among many others.
Because implants today require surgery, “implantable devices are seen as a last resort solution,” says Stanford University assistant professor electrical engineering Amin Arbabian. “If you have a disease with any other solution you’ll probably opt for that.” But a nerve stimulator that can be implanted with minimally invasive surgery or simply be injected would allow nerve stimulation treatments to reach 100-fold more patients, he argues.
The Stanford implant consists of: a piezoelectric receiver that converts ultrasound applied from outside the body to electricity, a capacitor for storing that electricity, two stimulating electrodes, an LED, and a custom chip to control it all. Those components are all inside a biocompatible package about the size of a fat grain of rice or a rather slim tic-tac.
