Forscher haben einen neuen KI-Algorithmus entwickelt, um die Erkennung einiger weniger Krebszellen unter Millionen normaler Blutzellen in etwa 10 Minuten zu automatisieren
Researchers Invent New AI Tool to Automate Detection of Cancer in Blood Samples
4 Kommentare
>Oberai explains, “Machines do not need to curate information in the same way humans do.”
>
>RED works differently than existing computational tools for liquid biopsies that require a human to be in the loop. In fact, instead of looking for specific, known features of a cancer cell and grouping the millions of cells down into smaller groups, RED does not even need to know what the “needle” it is searching for looks like.
>
>According to Oberai, who is the corresponding author on the paper, RED uses AI to identify unusual patterns and ranks everything by rarity – the most unusual findings rise to the top.
>
>Like that Sesame Street game, the algorithm points out “that one of these things is not like the others.” Or as Kuhn says, the algorithm can look at millions of cells and “separate outliers from non-outliers.”
[Unsupervised detection of rare events in liquid biopsy assays | npj Precision Oncology](https://www.nature.com/articles/s41698-025-01015-3)
i kinda wish researchers would open source their work so people can learn from it or contribute to it.
if we had a public manhattan project for cancer we would have cured all of this decades ago.
An interesting and productive use case scenario for AI.
I work in the same field, but on slightly different problem statements. Don’t be fooled by the headlines. For most cancer types, the sensitivity and specificity of detection isn’t enough to warrant diagnostic use in the broader population