Digital pathology

Programme session type(s): Workshop

Chair: Karin Oien, University of Glasgow, UK
Speaker: Manuel Salto-Tellez, Queen's University Belfast, UK
Speaker: Nasir Rajpoot, University of Warwick, UK
Speaker: Yinyin Yuan, The Institute of Cancer Research, UK


Room: Dochart

This session will include:
– RCPath Guidelines for Digital Pathology
– Deep Learning for Pathology
– Deciphering the Tumour Ecosystem Using Machine Learning for Pathology
– Digital Pathology and Cancer Immunology Testing

Computational Pathology: Challenges and Opportunities
Speaker: Nasir Rajpoot
Affiliation: University of Warwick


The visual cortex of human brain is an incredibly powerful computing machine, fantastic at recognising people and objects and building an understanding of the natural world around us. However, it is not ideally suited for objectively measuring what we see and recognising complex spatial patterns hidden in plain sight cannot. Computational Pathology is an emerging discipline concerned with the study of computer algorithms and AI for understanding disease from the analysis of digitised histology images. I will show some snippets of computational pathology research in my group to demonstrate the value of analytics of information-rich whole-slide images (the so-called Big Cancer Image Data) for cancer diagnosis and prognosis. I will conclude with some of the main challenges facing digital pathology research.

Digital Pathology & Artificial Intelligence, the Third Revolution in Pathology
Speaker: Manuel Salto-Tellez
Affiliation: Queen’s University Belfast


After immunohistochemistry (IHC) [1] [2] and the molecular diagnostic revolution [3, 4], Digital Pathology (DP) and Artificial Intelligence (AI) represent an incipient “third revolution” in pathology. DP/AI have the potential to make the complex and fragmented pathway of routine pathological tissue interrogation a more seamless endeavour at, at least, 3 levels, namely a) the analysis of H&E for diagnostic purposes; b) the scoring of tissue hybridization-based biomarkers for therapeutic decision-making; and c) the annotation of H&E samples ahead of nucleic acid extraction. This lecture will discuss in detail our contributions to the application of DP in this areas and, in particular a) the application of QuPath, developed in our laboratory, to the analysis of known biomarkers [5]; b) the analysis of markers of adaptive immunity and cancer immunotherapy [6]; and c) the development and utilization of DP and AI to annotate and characterize the H&E of samples ahead of genomic testing [6]. References1. John Wiley & Sons, Incorporated, ISBN-10 0470032200 & ISBN-13 97804700322062. J Clin Pathol. 2013 Jan;66(1):58-613. Br J Cancer. 2017 Nov 21;117(11):1581-1582. 4. J Clin Pathol. 2018 Apr;71(4):285-290.5. Lab Invest. 2018 Jan;98(1):15-26. 6. Sci Rep. 2017 Dec 4;7(1):16878.