Rehman, Zaka Ur and Fauzi, Mohammad Faizal Ahmad and Ahmad, Wan Siti Halimatul Munirah Wan and Abas, Fazly Salleh and Cheah, Phaik-Leng and Chiew, Seow-Fan and Looi, Lai-Meng (2024) Deep-Learning-Based Approach in Cancer-Region Assessment from HER2-SISH Breast Histopathology Whole Slide Images. Cancers, 16 (22). p. 3794. ISSN 2072-6694, DOI https://doi.org/10.3390/cancers16223794.
Full text not available from this repository.Abstract
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 40x 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.
| Item Type: | Article |
|---|---|
| Funders: | Ministry of Higher Education (MOHE) Malaysia under the Fundamental Research Grant Scheme, TM R&D Research Grant, Malaysia (RDTC/231104) ; (FRGS/1/2020/ICT02/MMU/02/10) |
| Uncontrolled Keywords: | deep learning; digital pathology; human epidermal growth factor receptor 2 (HER2); silver-enhanced in situ hybridization (SISH) |
| Subjects: | R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer) |
| Divisions: | Universiti Malaya Medical Centre (UMMC) |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 19 Feb 2025 01:27 |
| Last Modified: | 19 Feb 2025 01:27 |
| URI: | http://eprints.um.edu.my/id/eprint/47374 |
Actions (login required)
 |
View Item |
