If you happen to’ve ever had a PET scan, you realize it’s an ordeal. The scans assist docs detect most cancers and monitor its unfold, however the course of itself is a logistical nightmare for sufferers.
It begins with fasting for 4 to 6 hours earlier than coming into the hospital — and good luck to you in case you reside rurally and your native hospital doesn’t have a PET scanner. Once you get to the hospital, you’re injected with radioactive materials, after which you will need to wait an hour whereas it washes via your physique. Subsequent, you enter the PET scanner and have to try to lie nonetheless for half-hour whereas radiologists purchase the picture. After that, it’s important to maintain bodily away from the aged, younger folks, and pregnant ladies for as much as 12 hours since you’re actually semi-radioactive.
One other bottleneck? PET scanners are concentrated in main cities as a result of their radioactive tracers have to be produced in close by cyclotrons — compact nuclear machines — and used inside hours, limiting entry in rural and regional hospitals.
However what in case you may use AI to transform CT scans, that are far more accessible and inexpensive, into PET scans? That’s the pitch of RADiCAIT, an Oxford spinout that got here out of stealth this month with $1.7 million in pre-seed financing. The Boston-based startup, which is a High 20 finalist in Startup Battlefield at TechCrunch Disrupt 2025, has simply opened a $5 million increase to advance its scientific trials.
“What we actually do is we took probably the most constrained, advanced, and expensive medical imaging resolution in radiology, and we supplanted it with what’s the most accessible, easy and inexpensive, which is CT,” Sean Walsh, RADiCAIT’s CEO, advised TechCrunch.
RADiCAIT’s secret sauce is its foundational mannequin — a generative deep neural community invented in 2021 on the College of Oxford by a group led by the startup’s co-founder and chief medical info officer, Regent Lee.
The mannequin learns by evaluating CT and PET scans, mapping them, and selecting out patterns in how they relate to one another. Sina Shahandeh, RADiCAIT’s chief technologist, describes it as connecting “distinct bodily phenomena” by translating anatomical construction into physiological perform. Then the mannequin is directed to pay further consideration to particular options or facets of the scans, like sure varieties of tissue or abnormalities. This targeted studying is repeated many occasions with many various examples, so the mannequin can establish which patterns are clinically vital.
Techcrunch occasion
San Francisco
|
October 27-29, 2025
The ultimate picture that goes to docs for overview is created by combining a number of fashions working collectively. Shahandeh compares the method to Google DeepMind’s AlphaFold, the AI that revolutionized protein construction prediction: Each techniques be taught to translate one kind of organic info into one other.
Walsh claims the group at RADiCAIT can mathematically show that their artificial or generated PET photos are statistically much like actual chemical PET scans.
“That’s what our trials present,” he stated, “that the identical high quality of determination has been made when the physician, radiologist, or oncologist is given a chemical PET or [our AI-generated PET].”
RADiCAIT doesn’t promise to exchange the necessity for PET scans in particular therapeutic settings, like radioligand remedy, which kills most cancers cells. However for diagnostic, staging, and monitoring functions, RADiCAIT’s know-how may make PET scans out of date.
“As a result of it’s such a constrained system, there’s not sufficient provide to satisfy demand for diagnostics and theragnostics,” Walsh stated, referring to a medical method that mixes diagnostic imaging (i.e., PET scans) with focused remedy to deal with ailments (i.e., most cancers). “So what we’re seeking to do is absorb that demand on the diagnostic aspect. PET scanners themselves ought to decide up the slack on the theragnostic aspect.”
RADiCAIT has already begun scientific pilots particularly for lung most cancers testing with main well being techniques like Mass Normal Brigham and UCSF Well being. The startup is now pursuing an FDA scientific trial — a costlier and concerned course of that’s driving RADiCAIT’s $5 million seed spherical. As soon as that’s permitted, the subsequent step will probably be to do business pilots and display the business viability of the product. RADiCAIT additionally needs to run the identical course of — scientific pilots, scientific trials, business pilots — for colorectal and lymphoma use circumstances.
Shahandeh stated RADiCAIT’s method to utilizing AI to yield legitimate insights with out the burdens of adverse and costly checks is “broadly relevant.”
“We’re exploring extensions throughout radiology,” Shahandeh added. “Count on to see comparable improvements linking domains from supplies science to biology, chemistry, and physics wherever nature’s hidden relationships will be realized.”
If you wish to hear extra about RADiCAIT be part of us at Disrupt, October 27 to 29 in San Francisco. Be taught extra right here.
Keep forward of the curve with NextBusiness 24. Discover extra tales, subscribe to our publication, and be part of our rising neighborhood at nextbusiness24.com
