Medical imaging refers to a variety of specialized technologies. Following their development of AI-enhanced tools for X-rays and mammograms, the French startup Gleamer is now setting its sights on improving magnetic resonance imaging (MRI).
Rather than starting from the ground up, Gleamer has opted to acquire two firms focused on AI-driven MRI analysis: Pixyl and Caerus Medical.
Gleamer is part of a new wave of startups that aim to revolutionize medical imaging through artificial intelligence. Many tech entrepreneurs ventured into this field in 2014 and 2015, but while many efforts fell short, the landscape has seen some consolidation. Notably, companies like Zebra Medical Vision and Arterys were acquired by Nanox and Tempus, respectively.
Founded in 2017, Gleamer has been developing an AI assistant tailored for radiologists, essentially acting as a copilot in medical imaging. This tool is designed to enhance the accuracy of diagnoses derived from medical images.
The startup has successfully engaged 2,000 institutions in 45 countries to adopt its software solution, processing a total of 35 million examinations. Gleamer has also achieved CE and FDA certifications for its bone trauma interpretation solution, and in Europe, it provides additional CE certified products focused on chest X-rays and orthopedic evaluations.
“The concept of a universal solution in radiology is ineffective,” stated Gleamer co-founder and CEO Christian Allouche in an interview with TechCrunch. “Creating a broad model that encompasses all facets of medical imaging while meeting doctors’ expectations is exceedingly challenging.”
To address this, the company has formed specialized internal teams dedicated to mammography and CT scans. “Recently, we launched our mammography product after 18 months of development,” Allouche shared. This product utilizes a proprietary AI model trained on a dataset of 1.5 million mammograms.
“We have established a partnership with Jean Zay, the GPU cluster initiative by the French government,” Allouche noted, further mentioning the company’s focus on developing AI solutions for cancer-related CT scans.
As for MRI, Allouche elaborated, “MRI technology involves various intricate tasks such as detection, segmentation, characterization, classification, and handling multi-sequence imaging.”
This complexity is the reason Gleamer is acquiring two smaller companies that have been working in this domain for years, allowing for a quicker advancement. The specifics of the acquisition deals remain undisclosed.
“These two firms will serve as our foundational MRI platforms, with a clear goal of addressing all possible applications over the next two to three years,” Allouche stated.
Preventive Medical Imaging
While the outcomes from Gleamer’s models are promising, they are still not flawless. For instance, the newly launched mammography model reportedly detects four out of five cancers, compared to a human radiologist who usually identifies three out of five cases without AI support.
Nonetheless, solutions like Gleamer have the potential to significantly transform medical imaging practices. A cancer that goes undetected may show up in subsequent examinations a few months later.
“In the near future, I envision routine whole-body MRIs being covered by our insurance providers, as they don’t expose patients to radiation,” Allouche predicts.
However, in certain urban areas, the number of radiologists is insufficient to handle the current demand for reactive imaging. Should the focus shift towards preventive imaging, the importance of AI tools will become paramount.
Allouche believes that AI could evolve into a tool for “orchestrating and triaging” medical imaging. A majority of imaging examinations are conducted to exclude specific diagnoses. “This creates a pressing need for automation aided by a robust AI model that demonstrates significantly higher sensitivity than a human radiologist,” he concluded.
Compiled by Techarena.au.
Fanpage: TechArena.au
Watch more about AI – Artificial Intelligence
