ArticleNature communications2021
The impact of site-specific digital histology signatures on deep learning model accuracy and bias.
Article in Nature communications, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 162 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
162 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Deep learning applications in visual data for benign and malignant hematologic conditions: a systematic review and visual glossary.Haematologica · 2023Pooled it
- Serial H&E Pathology Reveals Progression-Associated Nuclear Size Drift as a Longitudinal Digital Readout of Bladder Cancer Evolution.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Mitigating Domain Shift and Dataset Bias in Deep Learning Models for Cancer Diagnostics.Journal of imaging informatics in medicine · 2026Review
- Current quality challenges in H&E preparation: The critical foundation for increased use of digital pathology and AI emergence.Virchows Archiv : an international journal of pathology · 2026Article
- AI Cautionary Guide: Pitfalls and Strategies for the Use of Machine Learning in Medical Research.Clinical pharmacology and therapeutics · 2026Review
- Counterfactual Diffusion Models Provide Interpretable Explanations of Artificial Intelligence Models in Pathology.Cancer research · 2026Article
- Foundation model-powered deep learning of endometrial histology for predicting the cumulative live birth of an in vitro fertilization cycle.PLOS digital health · 2026Article
- Artificial intelligence for detection, grading, and prognostication in prostate cancer pathology: A scoping review.Histology and histopathology · 2026Article
- The Missing Millions: Building Cancer Pathology Artificial Intelligence for Safety Net Populations.Mayo Clinic proceedings. Digital health · 2026Review
- Artificial intelligence in oncology: linking biological discovery to clinical utility.Molecular cancer · 2026Review
- Applications of Artificial Intelligence in Cancer Diagnosis and Treatment.Cancer medicine · 2026Review
- A protocol for evaluating robustness to H&E staining variation in computational pathology models.Journal of pathology informatics · 2026Article
- Benchmarking Open-Source Pathology Foundation Models for Breast Cancer Biomarker Prediction from H&E Whole-Slide Images.Cancers · 2026Article
- Human genetics across levels of biological organization.Nature reviews. Genetics · 2026Review
- Harnessing data science to control non-communicable diseases in Africa: a systematic review and gap analysis.Communications medicine · 2026Article
- Towards robust foundation models for digital pathology.Nature communications · 2026Article
- AI-assisted histomorphological stratification of endometrial cancer: real-world validation of foundation models for molecular subtyping.NPJ precision oncology · 2026Article
- Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation.Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 2026Article
- Strategies for mitigating artificial intelligence bias in healthcare: a systematic review.JAMIA open · 2026Review
- A novel prognostic model based on MVIRGs identifies ANGPT2 as a key target driving the malignant progression of HCC.Biological procedures online · 2026Article
102 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
13 authors.
Funding
Abstract
The Cancer Genome Atlas (TCGA) is one of the largest biorepositories of digital histology. Deep learning (DL) models have been trained on TCGA to predict numerous features directly from histology, including survival, gene expression patterns, and driver mutations. However, we demonstrate that these features vary substantially across tissue submitting sites in TCGA for over 3,000 patients with six cancer subtypes. Additionally, we show that histologic image differences between submitting sites can easily be identified with DL. Site detection remains possible despite commonly used color normalization and augmentation methods, and we quantify the image characteristics constituting this site-specific digital histology signature. We demonstrate that these site-specific signatures lead to biased accuracy for prediction of features including survival, genomic mutations, and tumor stage. Furthermore, ethnicity can also be inferred from site-specific signatures, which must be accounted for to ensure equitable application of DL. These site-specific signatures can lead to overoptimistic estimates of model performance, and we propose a quadratic programming method that abrogates this bias by ensuring models are not trained and validated on samples from the same site.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.