Glimpse Boosts CT Scanning Speed 10-30x to Catch Costly Defects

LG paid $1.9 billion for a battery defect that CT scanning could have caught. Glimpse, a startup with more than 100 customers including Anker, Lucid and the U.S. Navy, says its software can make that kind of inspection fast enough to actually use.

The recall that sidelined every Chevy Bolt made between 2017 and 2022 traces back to improperly installed parts inside battery cells at an LG factory. Virtually every major manufacturer faces the same risk: Volkswagen, Stellantis, Hyundai and Toyota have all suffered EV recalls.

"The majority of those major quality issues could have been caught with CT scanning. And the reason why they weren't is because it's way too slow to do any kind of statistical sampling," Eric Moch, co-founder and CEO of Glimpse, told TechCrunch.

How fast is the new system?

Glimpse boosts throughput on manufacturers' existing CT scanners, letting battery makers inspect cells 10 to 30 times faster, Moch said. Scanning capacity rises from a handful of cells per day to tens of thousands.

A "super scanner" the company is developing with partners could complete a scan in a second or two, he added.

To wring speed out of traditionally slow machines, Glimpse wrote its own image processing pipeline, built around deep learning algorithms. The pipeline compresses and cleans up scans, and much of the initial processing runs on edge computers deployed at the customer's site.

"It does all of the heavy lifting before sending the output to the cloud," Moch said. The result, the company claims: clear images that load in a web browser within seconds.

"You don't have to wait minutes or even sometimes hours for that data to load," he said.

What does the new Explore product do?

Glimpse is expanding beyond batteries. The company exclusively told TechCrunch it is launching Explore, a product that lets customers in aerospace, automotive, electronics and medical devices run its image processing software on CT scanners in their own labs and development environments.

Alongside scanned images, Glimpse's dashboard displays part measurements customers specify. For batteries, it might measure the distance between layers in a cell. When measurements deviate from the norm, the software flags and highlights them in the images.

"They can see with their own eyes the defects that they care about," Moch said. The deep learning algorithms also incorporate customer input and retrain themselves over time.

Who pays for this?

Glimpse currently generates revenue in the "mid seven-figure" range, Moch said. Its customers include both buyers and sellers of batteries.

For companies without their own CT scanners, Glimpse accepts shipped parts and scans them on its own machine in the Boston area. A second Scan On Demand center is opening in the San Francisco Bay Area.

"We expect this scanning service to actually be a bigger market. You can spend a couple hundred bucks or a few thousand dollars on Glimpse, and you don't have to buy a very expensive piece of equipment," Moch said. "And one day, when it makes sense for you, you buy the scanner and then you run our software on top of it."

That pay-as-you-go path gives Glimpse a low-friction entry into quality-control budgets — and a natural upgrade funnel toward software subscriptions as scanning demand grows.