Spatial transcriptomics inferred from pathology whole-slide images links tumor heterogeneity to survival in breast and lung cancer
Open accessPublished version of a preprint
Abstract
Digital analysis of pathology whole-slide images is fast becoming a game changer in cancer diagnosis and treatment. Specifically, deep learning methods have shown great potential to support pathology analysis, with recent studies identifying molecular traits that were not previously recognized in pathology H&E whole-slide images. Simultaneous to these developments, it is becoming increasingly evident that tumor heterogeneity is an important determinant of cancer prognosis and susceptibility to treatment, and should therefore play a role in the evolving practices of matching treatment protocols to patients. State of the art diagnostic procedures, however, do not provide automated methods for characterizing and/or quantifying tumor heterogeneity, certainly not in a spatial context. Further, existing methods for analyzing pathology whole-slide images from bulk measurements require many training samples and complex pipelines. Our work addresses these two challenges. First, we train deep learning models to spatially resolve bulk mRNA and miRNA expression levels on pathology whole-slide images (WSIs). Our models reach up to 0.95 AUC on held-out test sets from two cancer cohorts using a simple training pipeline and a small number of training samples. Using the inferred gene expression levels, we further develop a method to spatially characterize tumor heterogeneity. Specifically, we produce tumor molecular cartographies and heterogeneity maps of WSIs and formulate a heterogeneity index (HTI) that quantifies the level of heterogeneity within these maps. Applying our methods to breast and lung cancer slides, we show a significant statistical link between heterogeneity and survival. Our methods potentially open a new and accessible approach to investigating tumor heterogeneity and other spatial molecular properties and their link to clinical characteristics, including treatment susceptibility and survival.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Histology-enhanced contrastive learning can impute transcriptomic profiles by explicitly learning morphology-molecular correspondences in a shared space, reducing reliance on expensive spatial transcriptomics assays while preserving biologically meaningful variation.
“Closely related approaches shift from direct regression toward alignment objectives, using histology-enhanced contrastive learning to impute transcriptomic profiles by explicitly learning morphology–molecular correspondences in a shared space, thereby reducing reliance on expensive spatial transcriptomics assays while preserving biologically meaningful variation (14).”
From The role of multimodality in clinical disease diagnosis: advances, challenges, and opportunities (2026) · cites this paper as [14]
Split into 2 atoms — 0 confirmed, 1 partially supported, 1 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 74 · Cited by 155
Research works printed but not linked: 1
- [31]Bhandari, V. et al. The inter and intra-tumoural heterogeneity of subclonal reconstruction. bioRxiv 418780 (2019).
- Authors
- Levy-Jurgenson, A., Tekpli, X., Kristensen, V. N., & Yakhini, Z.
- Affiliations
- Technion – Israel Institute of Technology (IL)
- Oslo University Hospital (NO)
- Corresponding author
- Levy-Jurgenson, Alona
- Venue
- Scientific Reports
- Published
- 2020-11-02
- Volume
- 10
- Issue
- 1
- Pages
- 18802-18802
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC7606448
- OpenAlex
- W3096881394
- Cited by
- 155
- References
- 74
- Citations by year
- 2026: 16 · 2025: 21 · 2024: 31 · 2023: 44 · 2022: 28 · 2021: 15
- FWCI
- 8.54
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- NORA - Norwegian Open Research Archives (submittedVersion, cc-by)
- Funders
- European Commission (HORIZON2020, 847912)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- spatial transcriptomics, tumor heterogeneity, whole slide images, breast cancer, lung cancer, deep learning, spatial gene expression, microRNA expression, heterogeneity index, survival, prognosis
- MeSH terms
- Deep Learning, Breast Neoplasms, Female, Humans, Image Processing, Computer-Assisted, Lung Neoplasms, RNA, Messenger, Gene Expression, Survival Rate, Genetic Heterogeneity, MicroRNAs
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
