Loading…
Spatial proteomics prediction from routine H&E slides, generating 21-channel virtual multiplex immunofluorescence maps of the tumor microenvironment.
Distilled whole-slide pathology foundation model pairing a 22M-parameter ViT-S tile encoder with a LongNet slide encoder for cohort-scale analysis.
Ataraxis AI / NYU Grossman School of Medicine / New York University / Karmanos Cancer Institute / Cancer Center Baselland / The Catholic University of Korea / University of Chicago / Memorial Sloan Kettering Cancer Center / University of Aberdeen / University Hospital Basel / Cancer Research Malaysia / Omica.bio / Vilnius University / Providence / UPMC Hillman Cancer Center / Northwell Health / Yale University / Meta AI
Released October 28, 2024
Breast cancer recurrence risk read from an H&E slide and six routine clinical variables, using a frozen pan-cancer pathology encoder.