Enhanced Prognostication of Early Breast Cancer Outcomes Using Deep Learning on Merged Multistain and Multicolor-Depth Tumor Histopathology
Microscopy and Microanalysis · 2025
DOI: 10.1093/mam/ozaf044 ↗Kurz gefasst
Fachartikel in der Zeitschrift Microscopy and Microanalysis, 2025. Verfasst von Yifei Lin und 7 weiteren Autor:innen. Beteiligte Einrichtung: Electrical & Computer Engineering Department, Faculty of Engineering, University of Alberta, 116 Street, Edmonton, Canada T6G 1H9. Hauptthemen laut MEDLINE: Breast Neoplasms, Deep Learning, Image Processing, Computer-Assisted. Die Arbeit nennt 50 Literaturangaben. Gefördert von: MINISTRY OF SCIENCE, TECHNOLOGICAL DEVELOPMENT AND INNOVATION.
Abstract (Originalsprache)
Accurate breast cancer prognosis helps clinicians in selecting optimal treatments, potentially improving patient survival. We tested whether combining deep learning with tumor histopathology images could reliably predict cancer spread. Advantages of this study include the use of deep learning, which often outperforms traditional methods, and the analysis of tumor histopathology images that offer higher resolution than MRI or CT. We also optimized tumor immunostaining by separately staining slides with AE1/AE3 pan-cytokeratin and hematoxylin and eosin (H&E), and evaluated different image color-depth representations (color, grayscale, and binary) for their prognostic utility. The results indicate that grayscale images outperformed both color and binary formats. Grayscale pan-CK-stained images achieved 94.4% accuracy [area under the curve (AUC) = 0.982], while grayscale H&E-stained images reached 85.7% accuracy (AUC = 0.992) on the test set. Notably, training the ResNet-50 model with experimentally augmented data comprising six distinct datasets differing in staining type and color depth, totaling 2,646 images, further enhanced performance, to 100% accuracy (AUC of 1.0). Importantly, our pipeline ensured no contamination between the development and test sets. Deep learning applied to tumor histopathology images of early-stage breast cancer patients using two stains and varying color depths achieved exceptional prognostic accuracy and robust generalization.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Electrical & Computer Engineering Department, Faculty of Engineering, University of Alberta, 116 Street, Edmonton, Canada T6G 1H9.
- Department of Experimental Oncology, Institute of Oncology and Radiology of Serbia, Pasterova 14, Belgrade 11000, Serbia.
- Department of Basic and Environmental Science, Instituto Tecnológico de Santo Domingo (INTEC), Avenida de Los Próceres #49, Los Jardines del Norte, Santo Domingo 10602, Dominican Republic.
ORCID-Profile: Jelena Milovanović, Nataša Todorović Raković, Marko Radulovic
Förderung
- MINISTRY OF SCIENCE, TECHNOLOGICAL DEVELOPMENT AND INNOVATION
Zitieren
APA
Lin, Y., Li, X., Milovanović, J., Todorović Raković, N., Vranes, V., Vujasinović, T., Kanjer, K., & Radulovic, M. (2025). Enhanced Prognostication of Early Breast Cancer Outcomes Using Deep Learning on Merged Multistain and Multicolor-Depth Tumor Histopathology. Microscopy and Microanalysis. https://doi.org/10.1093/mam/ozaf044
Vancouver
Lin Y, Li X, Milovanović J, Todorović Raković N, Vranes V, Vujasinović T, et al. Enhanced Prognostication of Early Breast Cancer Outcomes Using Deep Learning on Merged Multistain and Multicolor-Depth Tumor Histopathology. Microscopy and Microanalysis. 2025. doi:10.1093/mam/ozaf044
BibTeX
@article{Lin2025,
author = {Lin, Yifei and Li, Xingyu and Milovanović, Jelena and Todorović Raković, Nataša and Vranes, Velicko and Vujasinović, Tijana and Kanjer, Ksenija and Radulovic, Marko},
title = {Enhanced Prognostication of Early Breast Cancer Outcomes Using Deep Learning on Merged Multistain and Multicolor-Depth Tumor Histopathology},
journal = {Microscopy and Microanalysis},
year = {2025},
doi = {10.1093/mam/ozaf044}
}
EUVIMED