Integrating spatial gene expression and breast tumour morphology via deep learning
(2020) In Nature Biomedical Engineering 4(8). p.827-834- Abstract
Spatial transcriptomics allows for the measurement of RNA abundance at a high spatial resolution, making it possible to systematically link the morphology of cellular neighbourhoods and spatially localized gene expression. Here, we report the development of a deep learning algorithm for the prediction of local gene expression from haematoxylin-and-eosin-stained histopathology images using a new dataset of 30,612 spatially resolved gene expression data matched to histopathology images from 23 patients with breast cancer. We identified over 100 genes, including known breast cancer biomarkers of intratumoral heterogeneity and the co-localization of tumour growth and immune activation, the expression of which can be predicted from the... (More)
Spatial transcriptomics allows for the measurement of RNA abundance at a high spatial resolution, making it possible to systematically link the morphology of cellular neighbourhoods and spatially localized gene expression. Here, we report the development of a deep learning algorithm for the prediction of local gene expression from haematoxylin-and-eosin-stained histopathology images using a new dataset of 30,612 spatially resolved gene expression data matched to histopathology images from 23 patients with breast cancer. We identified over 100 genes, including known breast cancer biomarkers of intratumoral heterogeneity and the co-localization of tumour growth and immune activation, the expression of which can be predicted from the histopathology images at a resolution of 100 µm. We also show that the algorithm generalizes well to The Cancer Genome Atlas and to other breast cancer gene expression datasets without the need for re-training. Predicting the spatially resolved transcriptome of a tissue directly from tissue images may enable image-based screening for molecular biomarkers with spatial variation.
(Less)
- author
- He, Bryan ; Bergenstråhle, Ludvig ; Stenbeck, Linnea ; Abid, Abubakar ; Andersson, Alma ; Borg, Åke LU ; Maaskola, Jonas ; Lundeberg, Joakim and Zou, James
- organization
- publishing date
- 2020-08
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Nature Biomedical Engineering
- volume
- 4
- issue
- 8
- pages
- 8 pages
- publisher
- Nature Publishing Group
- external identifiers
-
- scopus:85086705289
- pmid:32572199
- ISSN
- 2157-846X
- DOI
- 10.1038/s41551-020-0578-x
- language
- English
- LU publication?
- yes
- id
- 0d6feb09-f08b-4a43-85d4-b7b53de754c7
- date added to LUP
- 2020-07-13 14:41:48
- date last changed
- 2024-06-27 21:15:20
@article{0d6feb09-f08b-4a43-85d4-b7b53de754c7,
abstract = {{<p>Spatial transcriptomics allows for the measurement of RNA abundance at a high spatial resolution, making it possible to systematically link the morphology of cellular neighbourhoods and spatially localized gene expression. Here, we report the development of a deep learning algorithm for the prediction of local gene expression from haematoxylin-and-eosin-stained histopathology images using a new dataset of 30,612 spatially resolved gene expression data matched to histopathology images from 23 patients with breast cancer. We identified over 100 genes, including known breast cancer biomarkers of intratumoral heterogeneity and the co-localization of tumour growth and immune activation, the expression of which can be predicted from the histopathology images at a resolution of 100 µm. We also show that the algorithm generalizes well to The Cancer Genome Atlas and to other breast cancer gene expression datasets without the need for re-training. Predicting the spatially resolved transcriptome of a tissue directly from tissue images may enable image-based screening for molecular biomarkers with spatial variation.</p>}},
author = {{He, Bryan and Bergenstråhle, Ludvig and Stenbeck, Linnea and Abid, Abubakar and Andersson, Alma and Borg, Åke and Maaskola, Jonas and Lundeberg, Joakim and Zou, James}},
issn = {{2157-846X}},
language = {{eng}},
number = {{8}},
pages = {{827--834}},
publisher = {{Nature Publishing Group}},
series = {{Nature Biomedical Engineering}},
title = {{Integrating spatial gene expression and breast tumour morphology via deep learning}},
url = {{http://dx.doi.org/10.1038/s41551-020-0578-x}},
doi = {{10.1038/s41551-020-0578-x}},
volume = {{4}},
year = {{2020}},
}