A means of assessing deep learning-based detection of ICOS protein expression in colon cancer.

Sarker, Md Mostafa Kamal; Makhlouf, Yasmine; Craig, Stephanie G.; Humphries, Matthew P.; Loughrey, Maurice; James, Jacqueline A.; Salto-Tellez, Manuel; O�Reilly, Paul; Maxwell, Perry

Abstract

Biomarkers identify patient response to therapy. The potential immune‐checkpoint bi-omarker, Inducible T‐cell COStimulator (ICOS), expressed on regulating T‐cell activation and involved in adaptive immune responses, is of great interest. We have previously shown that open-source software for digital pathology image analysis can be used to detect and quantify ICOS using cell detection algorithms based on traditional image processing techniques. Currently, artificial intelligence (AI) based on deep learning methods is significantly impacting the domain of digital pa-thology, including the quantification of biomarkers. In this study, we propose a general AI‐based workflow for applying deep learning to the problem of cell segmentation/detection in IHC slides as a basis for quantifying nuclear staining biomarkers, such as ICOS. It consists of two main parts: a simplified but robust annotation process, and cell segmentation/detection models. This results in an optimised annotation process with a new user‐friendly tool that can interact with1 other open‐source software and assists pathologists and scientists in creating and exporting data for deep learning. We present a set of architectures for cell‐based segmentation/detection to quantify and analyse the trade‐offs between them, proving to be more accurate and less time consuming than traditional methods. This approach can identify the best tool to deliver the prognostic significance of ICOS protein expression.

Citation

SARKER, M.M.K., MAKHLOUF, Y., CRAIG, S.G., HUMPHRIES, M.P., LOUGHREY, M., JAMES, J.A., SALTO-TELLEZ, M., O'REILLY, P. and MAXWELL, P. 2021. A means of assessing deep learning-based detection of ICOS protein expression in colon cancer. Cancers [online], 13(15): machine learning techniques in cancer, article 3825. Available from: https://doi.org/10.3390/cancers13153825

• Journal Article Type: Article
• Acceptance Date: Jul 23, 2021
• Online Publication Date: Jul 29, 2021
• Publication Date: Aug 1, 2021
• Deposit Date: Dec 2, 2021
• Publicly Available Date: Dec 9, 2021
• Journal: Cancers
• Electronic ISSN: 2072-6694
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 13
• Issue: 15
• Article Number: 3825
• Pages: 3825
• DOI: https://doi.org/10.3390/cancers13153825
• Keywords: Colorectal cancer; Immunohistochemistry; Biomarkers; ICOS; Artificial intelligence; Deep learning
• Public URL: https://rgu-repository.worktribe.com/output/1538614
• Additional Information: Supplementary material for this output can be found at https://www.mdpi.com/article/10.3390/cancers13153825/s1.