Deep learning for fully-automated nuclear pleomorphism scoring in breast cancer.

Autor: Mercan C; Radboud University Medical Center, Department of Pathology, Nijmegen, The Netherlands., Balkenhol M; Radboud University Medical Center, Department of Pathology, Nijmegen, The Netherlands., Salgado R; GZA-ZNA Hospitals, Department of Pathology, Antwerp, Belgium.; Peter Mac Callum Cancer Centre, Division of Research, Melbourne, Australia., Sherman M; Mayo Clinic, Department of Laboratory Medicine and Pathology, Rochester, MN, USA., Vielh P; Medipath & American Hospital of Paris, Paris, France., Vreuls W; Canisius Wilhelmina Ziekenhuis, Nijmegen, The Netherlands., Polónia A; University of Porto, Institute of Molecular Pathology and Immunology Department of Pathology, Ipatimup Diagnostics, Porto, Portugal., Horlings HM; The Netherlands Cancer Institute, Department of Molecular Pathology, Amsterdam, The Netherlands., Weichert W; Technical University Munich, Institute of Pathology, Munich, Germany., Carter JM; Department of Laboratory Medicine and Pathology, University of Alberta, Edmonton, Canada., Bult P; Radboud University Medical Center, Department of Pathology, Nijmegen, The Netherlands., Christgen M; Hannover Medical School, Institute of Pathology, Hannover, Germany., Denkert C; Philipps University of Marburg, Institute of Pathology, Marburg, Germany., van de Vijver K; Ghent University Hospital and Cancer Research Institute Ghent, Department of Pathology, Ghent, Belgium., Bokhorst JM; Radboud University Medical Center, Department of Pathology, Nijmegen, The Netherlands., van der Laak J; Radboud University Medical Center, Department of Pathology, Nijmegen, The Netherlands.; Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden., Ciompi F; Radboud University Medical Center, Department of Pathology, Nijmegen, The Netherlands. francesco.ciompi@radboudumc.nl.
Jazyk: angličtina
Zdroj: NPJ breast cancer [NPJ Breast Cancer] 2022 Nov 08; Vol. 8 (1), pp. 120. Date of Electronic Publication: 2022 Nov 08.
DOI: 10.1038/s41523-022-00488-w
Abstrakt: To guide the choice of treatment, every new breast cancer is assessed for aggressiveness (i.e., graded) by an experienced histopathologist. Typically, this tumor grade consists of three components, one of which is the nuclear pleomorphism score (the extent of abnormalities in the overall appearance of tumor nuclei). The degree of nuclear pleomorphism is subjectively classified from 1 to 3, where a score of 1 most closely resembles epithelial cells of normal breast epithelium and 3 shows the greatest abnormalities. Establishing numerical criteria for grading nuclear pleomorphism is challenging, and inter-observer agreement is poor. Therefore, we studied the use of deep learning to develop fully automated nuclear pleomorphism scoring in breast cancer. The reference standard used for training the algorithm consisted of the collective knowledge of an international panel of 10 pathologists on a curated set of regions of interest covering the entire spectrum of tumor morphology in breast cancer. To fully exploit the information provided by the pathologists, a first-of-its-kind deep regression model was trained to yield a continuous scoring rather than limiting the pleomorphism scoring to the standard three-tiered system. Our approach preserves the continuum of nuclear pleomorphism without necessitating a large data set with explicit annotations of tumor nuclei. Once translated to the traditional system, our approach achieves top pathologist-level performance in multiple experiments on regions of interest and whole-slide images, compared to a panel of 10 and 4 pathologists, respectively.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz: