Short and dated, newest first. A note is a fact with a date, not an article. There is a feed.
Three short videos show CellCount at work: a count from one photo of a hemocytometer, a count on a phone held to the eyepiece, and full image mode for a frame where the whole grid does not fit. They are on the Products page, under See it in use.
Vitr, the company behind CellCount, is part of Microsoft for Startups. Its partner badge now sits with our other supporters on the home page and the Company page, as it does on cellcount.ai.
The live demo on cellcount.ai now opens on the total count, live and dead cells together, with clumps counted separately and never in the cell count. A switch on the result reads Total count and + Viability, so a reader can add the trypan blue live and dead split in one tap, and switch back. The demo still counts two corner squares of a real sample in the browser, with no account.
The hemocytometer guide on cellcount.ai now draws the chamber: one counting area of the improved Neubauer ruling, square by square, with a key giving the volume over each square and its multiplier, and a figure of a cover glass seated until Newton’s rings appear. New sections say how a hemocytometer works and how to clean one, and the counting app page draws what one image holds under each protocol choice.
cellcount.ai/faq has a new answer, in English and in Norwegian, to the question of whether CellCount has an API. It says yes, and sets out what a lab sends from its own systems, a JPEG, PNG or TIFF image, and what comes back: live and dead counts, aggregates and viability, plus every detection. It adds that the counts cover the whole image, so they are not a concentration, because the counting region and the dilution are applied in the app. The answer links the API documentation.
The ViTR wordmark from our designer now heads this site, in the navy and cyan it was drawn in and with the typeface of our printed material. The company, the product and the legal entity, Lowkey Vision AS, are unchanged.
cellcount.ai now has a hemocytometer calculator at /hemocytometer-calculator, open to anyone with no account. Enter the clear and the blue cells you counted, how many squares and the dilution, and it gives live and total cells per mL, viability, the cells in the suspension and the volume to seed, with the arithmetic shown. The page also sets out the dilution factor as a multiplier and how many cells to count.
The three figures on cellcount.ai/about that show how far manual counts spread now carry numbered references, each one a link to the published study by DOI, printed on the page rather than hidden behind a hover. The chart footnote is scoped to the first two figures, which are bead studies, and a line under the figures says the third is cells, counted by two blinded experts. The figures themselves are unchanged.
CellCount is now CellCount by Vitr. The product, the team and the legal entity, Lowkey Vision AS, are unchanged; the company has a name of its own, and this site is its home. A Vitr mark is on its way from a designer and will replace the wordmark here when it lands.
The CellCount site moved from lowkey-vision.com to cellcount.ai, and the old address redirects. Every public page there is now readable without JavaScript, the validation page carries its sources, and a FAQ answers the questions labs ask before they try it.
The contact page on cellcount.ai now shows the founders, and a call is booked in four questions. Most labs start with a call and a demo on their own samples; from there we set up the capture path, a shared counting protocol and an export routine, on site or remote.
Sixteen images straight from a leading automated cell counter, counted by CellCount, which had never seen an image from that instrument. Concordance on cell concentration was 0.91, and the live-or-dead call agreed on 95% of the 6,765 cells both readers found. The plots, the method and the sources are on the validation page.