Delivering high-quality, quantitative data from digital pathology images is one of OracleBio’s core values. Tools such as Visiopharm enable us to achieve this by building robust, AI-powered image analysis workflows.

In this masterclass, we explore the QC strategies used to ensure accuracy and reproducibility in the following case studies:

• The creation of a pathologist-validated and scalable image analysis workflow for a retrospective clinical study involving over 2,200 IHC-stained colorectal polyp whole slide images.
• The use of Deep Learning apps to segment morphologically distinct cell subpopulations and the Phenoplex workflow to streamline the thresholding process for spatial phenotyping in multiplex IF-stained pre-clinical tissue.

Karen McClymont
With a PhD in Biochemistry and her active involvement and support in the analysis of some of OracleBio’s most complex studies, Karen plays a key role leading OracleBio’s image analysis projects and overseeing the team’s continued development. 

Gabriel Reines March
With a PhD in Biomedical Image Processing and a background in Electrical Engineering, Gabriel is the OracleBio R&D team lead. He oversees and manages the group’s project pipeline and ensures that the company stays at the bleeding edge of the industry. 

Gabriel also manages OracleBio’s involvement in the INCISE project – a collaborative effort between industry, academia and the UK’s National Health Service.

Prostate cancer remains a significant health challenge globally, with metastatic castration-resistant prostate cancer (mCRPC) marking a critical juncture in patient care. The complex interactions between tumour and immune cells within the tumour microenvironment are pivotal for disease progression and therapeutic outcomes. In this presentation, I share our experience with using hyperplex immunofluorescence (IF) analysis with Visiopharm software to explore these interactions. I describe our approach to tissue segmentation, the determination of positivity in IF images, and the phenotyping of various cell populations. Moreover, I will discuss our observations on the spatial distribution of immune cells within the tumour microenvironment and its implications for prognosis. This work highlights the utility of hyperplex IF analysis in deepening our understanding of the immune landscape in mCRPC, offering new perspectives on prognosis and potential therapeutic avenues.

Dr. Gurel is a computational pathologist specialising in urogenital pathology with extensive experience in computerized image analysis, deep learning, molecular pathology, and cancer research. He is currently working as a clinician scientist/pathologist with the De Bono team at the Institute of Cancer Research, London.

Join us for an insightful seminar on the Hyperion XTi™ Imaging System and its pivotal role in advancing spatial biology. This emerging field is transforming our understanding of tissue organization in health and disease, with implications for predicting immune and therapeutic responses, improving drug development strategies, and potentially preventing or curing diseases. 

While conventional microscopy techniques use fluorescence to visualize protein or RNA targets in tissue samples, they face challenges due to spectral overlap and tissue autofluorescence. The Hyperion™ XTi overcomes these limitations by utilizing Imaging Mass Cytometry™ (IMC™), a fluorescence-free approach enabling detection of 40+ targets. 

IMC has expanded its capabilities with new whole slide imaging modes, which include Preview Mode, Cell Mode and Tissue Mode. These modes facilitate rapid and detailed analysis, supporting automated, continuous imaging of more than 40 large tissue samples (400 mm²) weekly. This significantly accelerates researchers' ability to gain insights from complex biological samples. 

Phenoplex™ software from Visiopharm® complements this hardware by offering a comprehensive workflow for data analysis, including automated ROI selection, phenotyping and spatial analyses of IMC images. This seminar will demonstrate how the multi-modal features of Hyperion XTi, combined with advanced analysis tools from Visiopharm, are revolutionizing our approach to spatial biology and opening new avenues for biological assessment. 

James holds a PhD in medical biophysics from the University of Toronto, specializing in advanced fluorescence microscopy techniques, cell biology and cell signaling mechanisms. At Standard BioTools, he currently works within product management and collaborates with R&D teams to leverage the multi-plex capabilities of the Hyperion XTi Imaging System. His goal is to drive innovation in spatial biology, enhancing our understanding of complex cellular interactions and tissue architecture in both health and disease. 

Multiplex methods for the detection of protein expression generate extremely data-rich images of intact tissue sections. These images are invaluable for the quantification and analysis of complex biology and have huge potential for biomarker development. However, their interpretation presents a considerable data analysis challenge which limits their utility, especially in clinical workflows.

The key task from these images is often cellular phenotyping - e.g. the identification of immunophenotypes, or the separation cells with compartment-specific protein expression from others. Most current automated methods depend upon a cellular segmentation step to support this, and segmentation has become an area of intensive research in AI (Artificial Intelligence), but the task is very difficult and no universally accepted method has been identified.

Therefore, methods of cellular phenotyping which operate without the need for segmentation would be very valuable. To meet this challenge, we have developed an AI cellular phenotyping method which does not require segmentation at all.

We use the U-Net backbone within the Visiopharm deep learning module to train our algorithm using expert human annotations of entire cellular regions. Crucially, we need only train for a single example of each compartmental stain (nuclear/cytoplasmic/membranous), and the algorithm then assigns class identities to cells without the need for segmentation of nuclei cytoplasm or membranes, using regional information in a manner analogous to a human expert, who may not need to be confident about cellular boundaries to accurately phenotype a cell.

The method is comparable in accuracy to segmentation-based methods, is highly transferrable, and represents a highly novel approach to quantitative image analysis with the potential to radically alter the way that we analyse these data-rich images.

Rachel Pennie MSc is a translational histologist in the deep phenotyping advanced technology facility within the Le Quesne Lab at the CRUK Scotland Institute. She is an expert in the development and application of Visiopharm deep learning methods to multiplex and high plex histopathological images.