Deep-Learning-Based Approach in Cancer-Region Assessment from HER2-SISH Breast Histopathology Whole Slide Images
Cancers · 11.11.2024 · 16 (22) · 3794
DOI: 10.3390/cancers16223794 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancers, online erschienen am 11.11.2024. Verfasst von Zaka Ur Rehman und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FRGS, TMR&D Research Grant, Ministry of Higher Education (MOHE) Malaysia under the Fundamental Research Grant Scheme.
Abstract (Originalsprache)
Fluorescence in situ hybridization (FISH) is widely regarded as the gold standard for evaluating human epidermal growth factor receptor 2 (HER2) status in breast cancer; however, it poses challenges such as the need for specialized training and issues related to signal degradation from dye quenching. Silver-enhanced in situ hybridization (SISH) serves as an automated alternative, employing permanent staining suitable for bright-field microscopy. Determining HER2 status involves distinguishing between “Amplified” and “Non-Amplified” regions by assessing HER2 and centromere 17 (CEN17) signals in SISH-stained slides. This study is the first to leverage deep learning for classifying Normal, Amplified, and Non-Amplified regions within HER2-SISH whole slide images (WSIs), which are notably more complex to analyze compared to hematoxylin and eosin (H&E)-stained slides. Our proposed approach consists of a two-stage process: first, we evaluate deep-learning models on annotated image regions, and then we apply the most effective model to WSIs for regional identification and localization. Subsequently, pseudo-color maps representing each class are overlaid, and the WSIs are reconstructed with these mapped regions. Using a private dataset of HER2-SISH breast cancer slides digitized at 40× magnification, we achieved a patch-level classification accuracy of 99.9% and a generalization accuracy of 78.8% by applying transfer learning with a Vision Transformer (ViT) model. The robustness of the model was further evaluated through k-fold cross-validation, yielding an average performance accuracy of 98%, with metrics reported alongside 95% confidence intervals to ensure statistical reliability. This method shows significant promise for clinical applications, particularly in assessing HER2 expression status in HER2-SISH histopathology images. It provides an automated solution that can aid pathologists in efficiently identifying HER2-amplified regions, thus enhancing diagnostic outcomes for breast cancer treatment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Engineering, Multimedia University, Cyberjaya 63100, Malaysia.
- Institute for Research, Development and Innovation, IMU University, Bukit Jalil, Kuala Lumpur 57000, Malaysia.
- Faculty of Engineering and Technology, Multimedia University, Bukit Beruang, Melaka 75450, Malaysia.
- Department of Pathology, University Malaya-Medical Center, Kuala Lumpur 50603, Malaysia.
ORCID-Profile: Mohammad Faizal Ahmad Fauzi, Wan Siti Halimatul Munirah Wan Ahmad, Fazly Salleh Abas, Seow-Fan Chiew, Lai-Meng Looi
Förderung
- FRGS
- TMR&D Research Grant
- Ministry of Higher Education (MOHE) Malaysia under the Fundamental Research Grant Scheme
- TM R&D Research Grant, Malaysia
Zitieren
APA
Rehman, Z. U., Ahmad Fauzi, M. F., Wan Ahmad, W. S. H. M., Abas, F. S., Cheah, P. L., Chiew, S. F., & Looi, L. M. (2024). Deep-Learning-Based Approach in Cancer-Region Assessment from HER2-SISH Breast Histopathology Whole Slide Images. Cancers, 16(22), 3794. https://doi.org/10.3390/cancers16223794
Vancouver
Rehman ZU, Ahmad Fauzi MF, Wan Ahmad WSHM, Abas FS, Cheah PL, Chiew SF, et al. Deep-Learning-Based Approach in Cancer-Region Assessment from HER2-SISH Breast Histopathology Whole Slide Images. Cancers. 2024;16(22):3794. doi:10.3390/cancers16223794
BibTeX
@article{Rehman2024,
author = {Rehman, Zaka Ur and Ahmad Fauzi, Mohammad Faizal and Wan Ahmad, Wan Siti Halimatul Munirah and Abas, Fazly Salleh and Cheah, Phaik-Leng and Chiew, Seow-Fan and Looi, Lai-Meng},
title = {Deep-Learning-Based Approach in Cancer-Region Assessment from HER2-SISH Breast Histopathology Whole Slide Images},
journal = {Cancers},
year = {2024},
volume = {16},
number = {22},
pages = {3794},
doi = {10.3390/cancers16223794}
}
EUVIMED