Medical imaging is a wide term that encompasses cut offal separateent technologies. After toiling on AI-powered tools to enhance X-rays and mammographies, French commenceup Gleamer now aims to tackle magnetic resonance imaging (MRI).
Instead of commenceing from scratch, Gleamer has achieved two commenceups that have already been toiling on AI-powered MRI analysis: Pixyl and Caerus Medical.
Gleamer is part of the second wave of commenceups trying to enhance medical imaging using synthetic inincreateigence. Several tech set upers produced commenceups around this topic in 2014 or 2015. While most of them went nowhere, there have been some validateation in the space. For instance, Zebra Medical Vision and Arterys were both achieved by Nanox and Tempus, admireively.
Founded in 2017, Gleamer has been produceing an AI helpant for radiologists, a sort of copilot for medical imaging. With Gleamer, radiologists can theoreticassociate enhance the diagnostic accuracy when expounding medical images.
The commenceup has already swayd 2,000 institutions apass 45 countries to engage its gentleware solution. Overall, Gleamer has processed 35 million examinations. The company has getd CE and FDA certifications for its bone trauma expoundation product. In Europe, it also proposes products particularassociate cgo ined on chest X-rays, orthopedic and bone age meacertainments with CE certification.
“Unfortunately, the one-size-fits-all approach to radiology doesn’t toil,” Gleamer co-set uper and CEO Christian Allouche tbetter TechCrunch. “It’s very complicated to have a huge model that covers all medical imaging and dedwellrs the level of carry outance foreseeed by doctors.”
That’s why the company produced petite inner teams cgo ined on mammographies and CT scans. “Three weeks ago we freed our mammography product, which we have been toiling on for 18 months,” Allouche shelp. It’s based on a proprietary AI model that has been trained on 1.5 million mammographies.
“We have a partnership with Jean Zay, the French rulement’s GPU cluster,” Allouche shelp. The company is also toiling on CT scans for cancers.
But what about MRI? “MRI is a separateent technoreasoned space,” Allouche shelp. “You have a lot of tasks in MRI. It’s not equitable discoverion, you’ve got segmentation, you’ve got discoverion, you’ve got characterization, classification, multi-sequence imaging.”
That’s why Gleamer is buying two petite commenceups that have been toiling on this space for cut offal years to shift quicker. Gleamer isn’t disclosing the terms of the deals.
“These two companies will become our two MRI platcreates, with the evident ambition of covering all engage cases over the next two to three years,” Allouche shelp.
Preventive medical imaging
While Gleamer’s models show promising results, they are not yet perfect. For example, with the company’s recent mammography model, the commenceup claims it can discover four out of five cancers. In comparison, a human radiologist without AI helpance typicassociate identifies cancer in three out of five cases.
However, the productivity achieves from a tool enjoy Gleamer could radicassociate alter medical imaging. A missed tumor is probable to eunite in a adhere-up exam a scant months tardyr.
“In the not-too-distant future, I leank we’ll all be getting routine whole body MRIs phelp for by our insurance companies — since they’re not irradiating,” Allouche shelp.
However, in some cities, there are already too scant radiologists to greet the need for reactive imaging. If the industry shifts toward stopive imaging, AI tools will become indispensable.
Gleamer’s CEO leanks AI could become an “orchestrating and triaging” tool. Most medical imaging examinations are directed as a way to rule out some determines. “So, there’s a authentic need to automate all this with a very firm AI model that has a much higher level of sensitivity than a human,” Allouche shelp.
