Telemedicine, as a field, can be a little hit or miss. Sometimes there are eye-popping concepts that, upon closer examination, have the whiff of vaporware about them. Other times there are sound and important uses of telemedicine that, while great, aren’t especially interesting or innovative from a technological standpoint (take teledermatology, for instance, which often simply involves emailing photos).
A new project from the École Polytechnique Fédérale de Lausanne, however, is important, has the “wow” factor, and is poised to make it to market soon. It’s an ultrasound machine that has been altered to make it usable at a distance.
Imagine this scenario: you’re a first-year resident, working a nightshift at a rural hospital, when a patient comes in exhibiting urgent neurological symptoms. You know you need to use an ultrasound to take a sonogram—but you simply lack the expertise to make a confident diagnosis. You need a specialist’s help—but he’s many miles away, in another hospital.
Here’s where EPFL’s device, developed by a team at the Signal Processing Laboratory led by Jean-Philippe Thiran, comes in. In order for the remote specialist to make an accurate diagnosis, it’s not enough to simply stream over images from the ultrasound. “If you take a normal ultrasound probe, and an operator places it over a body,” says Thiran in this video explaining the project, “you really have to know where it is to understand the images that are displayed on the screen.”
Seeing the ultrasound images without knowing the placement of the transducer is insufficient; knowing the placement without seeing the images is also insufficient. Though much of telemedicine is about making compromises with circumstances, here’s an instance in which that just won’t do.
So Thiran’s team outfitted a transducer with a motion detector (“the size of a cherry,” in the words of Cécila Carron’s colorfully precise report on the topic), as well as an optical feedback system made of a pair of infrared cameras which films the transducer as you, the sweating first-year resident, move it along the patient. The remote specialist is simultaneously fed images from the ultrasound as well as, crucially, information about the exact position of the transducer (it’s represented on a 3-D model via software the specialist will need to have at hand). In real time, the specialist can use her mouse to guide the resident to place the transducer here, then there, then there—much as the specialist might do were she actually on site.
And it’s not vaporware! Far from it: Carron reports that it has been tested both at the Lausanne University Hospital and another hospital in Besançon. A partner startup in the latter city, a company named Covalia, is working to integrate the device into a telediagnosis platform it had been developing, which means the new device could see its way to market in just a matter of months.
DeepMind’s cofounder: Generative AI is just a phase. What’s next is interactive AI.
“This is a profound moment in the history of technology,” says Mustafa Suleyman.
What to know about this autumn’s covid vaccines
New variants will pose a challenge, but early signs suggest the shots will still boost antibody responses.
Human-plus-AI solutions mitigate security threats
With the right human oversight, emerging technologies like artificial intelligence can help keep business and customer data secure
Next slide, please: A brief history of the corporate presentation
From million-dollar slide shows to Steve Jobs’s introduction of the iPhone, a bit of show business never hurt plain old business.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.