Deep learning in cancer pathology: a new generation of clinical biomarkers

Clinical workflows in oncology rely on predictive and prognostic molecular biomarkers. However, the growing number of these complex biomarkers tends to increase the cost and time for decision-making in routine daily oncology practice; furthermore, biomarkers often require tumour tissue on top of rou...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:British journal of cancer Jg. 124; H. 4; S. 686 - 696
Hauptverfasser: Echle, Amelie, Rindtorff, Niklas Timon, Brinker, Titus Josef, Luedde, Tom, Pearson, Alexander Thomas, Kather, Jakob Nikolas
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 16.02.2021
Nature Publishing Group
Schlagworte:
631/67/1059/602
631/67/1857
639/705/1042
692/4028/67/2321
Artificial intelligence
Biomarkers
Biomarkers, Tumor - analysis
Biomedical and Life Sciences
Biomedicine
Cancer
Cancer Research
Clinical decision making
Decision Making
Deep Learning
Drug Resistance
Epidemiology
Histology
Humans
Image processing
Image Processing, Computer-Assisted - methods
Molecular Medicine
Neoplasms - pathology
Neoplasms - therapy
Oncology
Predictions
Prognosis
Review
Review Article
Tumors
ISSN:0007-0920, 1532-1827, 1532-1827
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Clinical workflows in oncology rely on predictive and prognostic molecular biomarkers. However, the growing number of these complex biomarkers tends to increase the cost and time for decision-making in routine daily oncology practice; furthermore, biomarkers often require tumour tissue on top of routine diagnostic material. Nevertheless, routinely available tumour tissue contains an abundance of clinically relevant information that is currently not fully exploited. Advances in deep learning (DL), an artificial intelligence (AI) technology, have enabled the extraction of previously hidden information directly from routine histology images of cancer, providing potentially clinically useful information. Here, we outline emerging concepts of how DL can extract biomarkers directly from histology images and summarise studies of basic and advanced image analysis for cancer histology. Basic image analysis tasks include detection, grading and subtyping of tumour tissue in histology images; they are aimed at automating pathology workflows and consequently do not immediately translate into clinical decisions. Exceeding such basic approaches, DL has also been used for advanced image analysis tasks, which have the potential of directly affecting clinical decision-making processes. These advanced approaches include inference of molecular features, prediction of survival and end-to-end prediction of therapy response. Predictions made by such DL systems could simplify and enrich clinical decision-making, but require rigorous external validation in clinical settings.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Review-3
content type line 23
ISSN:0007-0920
1532-1827
1532-1827
DOI:10.1038/s41416-020-01122-x