Transcriptomics-guided Slide Representation Learning in Computational Pathology

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jaume, Guillaume, Oldenburg, Lukas, Vaidya, Anurag, Chen, Richard J., Williamson, Drew F. K., Peeters, Thomas, Song, Andrew H., Mahmood, Faisal
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910452881031168
author Jaume, Guillaume
Oldenburg, Lukas
Vaidya, Anurag
Chen, Richard J.
Williamson, Drew F. K.
Peeters, Thomas
Song, Andrew H.
Mahmood, Faisal
author_facet Jaume, Guillaume
Oldenburg, Lukas
Vaidya, Anurag
Chen, Richard J.
Williamson, Drew F. K.
Peeters, Thomas
Song, Andrew H.
Mahmood, Faisal
contents Self-supervised learning (SSL) has been successful in building patch embeddings of small histology images (e.g., 224x224 pixels), but scaling these models to learn slide embeddings from the entirety of giga-pixel whole-slide images (WSIs) remains challenging. Here, we leverage complementary information from gene expression profiles to guide slide representation learning using multimodal pre-training. Expression profiles constitute highly detailed molecular descriptions of a tissue that we hypothesize offer a strong task-agnostic training signal for learning slide embeddings. Our slide and expression (S+E) pre-training strategy, called Tangle, employs modality-specific encoders, the outputs of which are aligned via contrastive learning. Tangle was pre-trained on samples from three different organs: liver (n=6,597 S+E pairs), breast (n=1,020), and lung (n=1,012) from two different species (Homo sapiens and Rattus norvegicus). Across three independent test datasets consisting of 1,265 breast WSIs, 1,946 lung WSIs, and 4,584 liver WSIs, Tangle shows significantly better few-shot performance compared to supervised and SSL baselines. When assessed using prototype-based classification and slide retrieval, Tangle also shows a substantial performance improvement over all baselines. Code available at https://github.com/mahmoodlab/TANGLE.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11618
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transcriptomics-guided Slide Representation Learning in Computational Pathology
Jaume, Guillaume
Oldenburg, Lukas
Vaidya, Anurag
Chen, Richard J.
Williamson, Drew F. K.
Peeters, Thomas
Song, Andrew H.
Mahmood, Faisal
Computer Vision and Pattern Recognition
Artificial Intelligence
Self-supervised learning (SSL) has been successful in building patch embeddings of small histology images (e.g., 224x224 pixels), but scaling these models to learn slide embeddings from the entirety of giga-pixel whole-slide images (WSIs) remains challenging. Here, we leverage complementary information from gene expression profiles to guide slide representation learning using multimodal pre-training. Expression profiles constitute highly detailed molecular descriptions of a tissue that we hypothesize offer a strong task-agnostic training signal for learning slide embeddings. Our slide and expression (S+E) pre-training strategy, called Tangle, employs modality-specific encoders, the outputs of which are aligned via contrastive learning. Tangle was pre-trained on samples from three different organs: liver (n=6,597 S+E pairs), breast (n=1,020), and lung (n=1,012) from two different species (Homo sapiens and Rattus norvegicus). Across three independent test datasets consisting of 1,265 breast WSIs, 1,946 lung WSIs, and 4,584 liver WSIs, Tangle shows significantly better few-shot performance compared to supervised and SSL baselines. When assessed using prototype-based classification and slide retrieval, Tangle also shows a substantial performance improvement over all baselines. Code available at https://github.com/mahmoodlab/TANGLE.
title Transcriptomics-guided Slide Representation Learning in Computational Pathology
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2405.11618