EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Integrating Morphology and Molecular Biology: Artificial Intelligence-Driven Molecular Prediction in Pathology with a Focus on Cytology

Diana Montezuma, Fernando C Schmitt

Acta Cytologica · 04.06.2026 · 1-9

DOI: 10.1159/000552799 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Acta Cytologica, online erschienen am 04.06.2026. Verfasst von Diana Montezuma und 1 weiteren Autor:innen. Beteiligte Einrichtung: Research and Development Unit, IMP Diagnostics, Porto, Portugal. Die Arbeit nennt 45 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background: Recent computational pathology research proposes using artificial intelligence (AI) to infer molecular features from routine haematoxylin-eosin images, aiming to reduce the cost and time associated with biomarker analysis. Summary: Herein, we explore advancements in predicting genetic mutations, molecular subtypes, microsatellite instability, tumour mutational burden, and spatial proteomics from histological and, specifically, cytological specimens. Despite some promising predictive performances, recent evidence also suggests that current models may rely on confounding clinicopathological features or “shortcut learning” rather than true biological signals, raising important questions about their consistency when applied to broader and more diverse patient cohorts. In cytology, the field is at an earlier stage, and although AI-based molecular triage is an appealing concept, further research is needed to determine whether the predictive performance observed in histology can be replicated in cytological specimens. Key Messages: AI-based prediction of molecular features from histology shows promise but remains insufficient to replace established molecular testing. Current models may be influenced by shortcut learning and therefore require validation across broader cohorts. In cytology, AI-driven molecular prediction is still preliminary and warrants substantial further investigation.

Schlagwörter

Stichwörter der Autor:innen

Artificial intelligenceComputational pathologyCytologyCytology informaticsMolecular pathology

Autor:innen und Institutionen

  • Research and Development Unit, IMP Diagnostics, Porto, Portugal.
  • Cancer Biology and Epigenetics Group, IPO Porto Research Center (CI-IPO Porto), Portuguese Oncology Institute of Porto (IPO Porto), Porto, Portugal.
  • RISE-Associate Laboratory (Health Research Network), Porto, Portugal.
  • Porto Comprehensive Cancer Centre Raquel Seruca (Porto.CCC), Porto, Portugal.
  • RISE-Associate Laboratory (Health Research Network), Porto, Portugal, fschmitt@ipatimup.pt.
  • RISE-Health, Department of Pathology, Faculty of Medicine of University of Porto, Porto, Portugal, fschmitt@ipatimup.pt.

Zitieren

APA

Montezuma, D., & Schmitt, F. C. (2026). Integrating Morphology and Molecular Biology: Artificial Intelligence-Driven Molecular Prediction in Pathology with a Focus on Cytology. Acta Cytologica, 1-9. https://doi.org/10.1159/000552799

Vancouver

Montezuma D, Schmitt FC. Integrating Morphology and Molecular Biology: Artificial Intelligence-Driven Molecular Prediction in Pathology with a Focus on Cytology. Acta Cytologica. 2026:1-9. doi:10.1159/000552799

BibTeX
@article{Montezuma2026,
  author = {Montezuma, Diana and Schmitt, Fernando C},
  title = {Integrating Morphology and Molecular Biology: Artificial Intelligence-Driven Molecular Prediction in Pathology with a Focus on Cytology},
  journal = {Acta Cytologica},
  year = {2026},
  pages = {1--9},
  doi = {10.1159/000552799}
}
Kostenlos starten →