INSIGHT AI

Source-linked text edition ·

Genome-anchored foundation model embeddings improve molecular prediction from histology images

The written, source-linked counterpart to this video.

Spoken scripts · Report and scripts (PDF)

Published edition1 story

Genome-anchored foundation model embeddings improve molecular prediction from histology images

Here we introduce PathLUPI, which uses transcriptomic privileged information during training to extract genome-anchored histological embeddings, enabling effective molecular prediction using only WSIs at inference.

Through extensive evaluation across 49 molecular oncology tasks using 11,361 cases from 20 cohorts, PathLUPI demonstrates superior performance compared to conventional methods trained solely on WSIs.

Source evidence for Genome-anchored foundation model embeddings improve molecular prediction from histology images
Source-linked proof · original source

Video edition · Markdown edition

Source ledger