Article

Nuclear Morphology Tracks Molecular Class Unevenly Across Four Cancers

2026-08-20

Abstract excerpt

<title>Abstract</title> <p>Computational pathology can quantify nuclear morphology from routine haematoxylin and eosin (H&E) whole-slide images, raising the prospect of inferring molecular class from tissue alone. The untested question is when this works, since some molecular distinctions are morphologically encoded and others are not. Using the open-access tier of The Cancer Genome Atlas (TCGA), we assembled dia...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 42bc0361-98a7-5ae9-bf89-5b69859a360e
DOI: 10.21203/rs.3.rs-10623310/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Nuclear Morphology Tracks Molecular Class Unevenly Across Four CancersDOI 10.21203/rs.3.rs-10623310/v1Read

Morphological Landscape Mapping Decodes Pathological Heterogeneity and Proteomic Programs in HCCSemantic proximity Read

Deep-learning quantified cell-type-specific nuclear morphology predicts genomic instability and prognosis in multiple cancer typesSemantic proximity Read

Nuclear Irregularity as a Universal Diagnostic Tool in Solid TumorsSemantic proximity Read

Integrated morphologic analysis for the identification and characterization of disease subtypesSemantic proximity Read

MorphoITH: a framework for deconvolving intra-tumor heterogeneity using tissue morphology.Semantic proximity Read

Association of nuclear morphometric and texture features derived from routine hematoxylin and eosin slides with molecular alterations in IDH-wildtype diffuse gliomasSemantic proximity Read

Clinical Significance and Molecular Annotation of Cellular Morphometric Subtypes in Lower Grade Gliomas discovered by Machine Learning: a retrospective multicentric studySemantic proximity Read

SHEST: Single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell type prediction and spatial transcriptomics reconstructionSemantic proximity Read

Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unannotated pathology slides.Semantic proximity Read

Morpho-FM: spatial molecular reconstruction from routine H&E histology using transcriptomic foundation-model priorsSemantic proximity Read

Buyer Beware: confounding factors and biases abound when predicting omics-based biomarkers from histological imagesSemantic proximity Read

AI powered quantification of nuclear morphology in cancers enables prediction of genome instability and prognosisSemantic proximity Read