Background Technical factors can bias H&E digital slides potentially compromising computational histopathology studies. Here, we hypothesised that sample quality and sampling variation can introduce even greater and undocumented technical fallacy. Methods Using The Cancer Genome Atlas (TCGA) clear-cell renal cell carcinoma (ccRCC) as a model disease, we annotated ~78,000 image tiles and trained deep learning models to detect histological textures and lymphocyte infiltration at the tumour core and its surrounding margin and correlated these with clinical, immunological, genomic, and transcriptomic profiles. Results The models reached 95% validation accuracy for classifying textures and 95% for lymphocyte infiltration enabling reliable profiling of ccRCC samples. We validated the lymphocyte-per-texture distributions in the Helsinki dataset (n = 64). Texture analysis indicated constitutive sampling bias by TCGA clinical centres and technically suboptimal samples. We demonstrate how computational texture mapping (CTM) can abrogate these issues by normalising textural variance. CTM-harmonised histopathological architecture resonated with both expected associations and novel molecular fingerprints. For instance, tumour fibrosis associated with histological grade, epithelial-to-mesenchymal transition, low mutation burden and metastasis. Conclusions This study highlights texture-based standardisation to resolve technical bias in computational histopathology and understand the molecular basis of tissue architecture. All code, data and models are released as a community resource.
Evaluating tissue architecture from routine hematoxylin and eosin-stained (H&E) slides is prone to subjectivity and sampling bias. Here, we extensively annotated ~40,000 images of five tissue texture types and ~25,000 images of lymphocyte quantity to train deep learning models. We defined histopathological patterns in over 400 clear-cell renal cell carcinoma H&E-stained slides of The Cancer Genome Atlas (TCGA) and resolved sampling and staining differences by harmonizing textural composition. By integrating multi-omic and imaging data, we profiled their clinical, immunological, genomic, and transcriptomic phenotypes. Histological grade, stage, adaptive immunity, the epithelial-to-mesenchymal transition signature and lower mutation burden were more common in stroma-rich samples. Histological proximity between the malignant and normal renal tissues was associated with poor survival, cellular proliferation, tumor heterogeneity, and wild-type PBRM1. This study highlights textural characterization to standardize sampling differences, quantify lymphocyte infiltration and discover novel histopathological associations both in the intratumoral and peritumoral regions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.