Annotation-efficient deep learning for breast cancer whole-slide image classification using tumour infiltrating lymphocytes and slide-level labels
- Author(s)
- Perera, R; Savas, P; Senanayake, D; Salgado, R; Joensuu, H; O’Toole, S; Li, J; Loi, S; Halgamuge, S;
- Details
- Publication Year 2024-07-25,Volume 3,Issue #1,Page 104
- Journal Title
- Communications Engineering
- Publication Type
- Research article
- Abstract
- Tumour-Infiltrating Lymphocytes (TILs) are pivotal in the immune response against cancer cells. Existing deep learning methods for TIL analysis in whole-slide images (WSIs) demand extensive patch-level annotations, often requiring labour-intensive specialist input. To address this, we propose a framework named annotation-efficient segmentation and attention-based classifier (ANSAC). ANSAC requires only slide-level labels to classify WSIs as having high vs. low TIL scores, with the binary classes divided by an expert-defined threshold. ANSAC automatically segments tumour and stroma regions relevant to TIL assessment, eliminating extensive manual annotations. Furthermore, it uses an attention model to generate a map that highlights the most pertinent regions for classification. Evaluating ANSAC on four breast cancer datasets, we demonstrate substantial improvements over three baseline methods in identifying TIL-relevant regions, with up to 8% classification improvement on a held-out test dataset. Additionally, we propose a pre-processing modification to a well-known method, enhancing its performance up to 6%.
- Publisher
- Springer Nature
- Department(s)
- Laboratory Research; Medical Oncology
- Publisher's Version
- https://doi.org/10.1038/s44172-024-00246-9
- Open Access at Publisher's Site
https://doi.org/10.1038/s44172-024-00246-9- Terms of Use/Rights Notice
- Refer to copyright notice on published article.
Creation Date: 2025-05-01 08:11:40
Last Modified: 2025-05-01 08:12:28