DEEP LEARNING blog

Understanding spatial biology to unravel personalized medicine: Multiplex Immunofluorescence IHC combined to Deep Learning is leading the way

By Charlotte Plestant, Louis Jeay, Suliman Bouizaguen, David Guet - 26 Jul 2021

Delivering the right treatment to the right patient, and at the right time. This motto has become the driving force in drug development, placing solutions empowering personalized medicine as a top priority in the Pathology field. The scientific community is striving to answer the technological needs required by such a challenge. Multiplex fluorescence IHC (immunohistochemistry) is a revolutionary method offering powerful possibilities in simultaneous analysis of multiple biomarkers on whole tissue sections. In this post, we describe why understanding spatial biology, the study of tissues in their 2D and 3D context, is the next big step the field has to take and how Deep Learning will assist in unraveling personalized medicine.

Exploring the tumor microenvironment is crucial for a successful personalized medicine

 

The small success rate of drug candidates, especially in oncology, has outdated the concept of “one fits all” treatments. Immunotherapy has indeed significantly improved survival in different cancer types, yet its efficacy remains limited to small subpopulations. Every patient is different and has a unique genetic make up: we are now in the era of personalized medicine

An efficient personalized medicine strongly relies on understanding the tumor microenvironment (TME). TME is defined by the interplay between individual cells in the tumor, immune cells, blood vessels, fibroblasts and the extracellular matrix. Investigation of the TME has revealed that the type, the density, the localisation and organisation of immune cells - 

 

 

 

 

 

defined as the immune contexture - within solid tumors could help predict treatment response and clinical outcome [1,2]. 

Establishing the cellular profile of this environment and the cell spatial distribution is crucial in deciphering the immune contexture. The diversity in cell populations and states is translated in the expression of a large panel of biomarkers. For example, PD-L1 is the most known biomarker that has received FDA approval for its use as a companion and complementary diagnostic for two checkpoint inhibitors, pembrolizumab and nivolumab [3,4].

Integrating immune contexture with clinical outcome will help to discover new prognostic and predictive biomarkers.

TME elucidation with Multiplex Fluorescence Immunohistochemistry

 

Multiplex fluorescence IHC (mf IHC) allows the simultaneous analysis of a large number of biomarkers while preserving the spatial distribution information.

Indeed, unlike methods such as flow cytometry, staining is performed on intact FFPE (Formalin Fixed Paraffin Embedded) tissues. After staining and scanning, the generated multiplexed images contain precious information such as tissue morphology, cell morphology and cell phenotypes.

Their analyses offers a visual translation of the molecular cellular processes taking place.

High dimensional mf IHC image, tonsil section [5].

Albeit extremely informative, the process is time consuming and can be prone to errors. For example, lowly expressed proteins can generate weak signal, which will be difficult to detect above the background. Many artifacts, resulting from events such as necrosis or fibrosis, can also hamper signal detection and analysis. Moreover, the technologies allowing the generation of the images, going from tissue sampling to staining and acquisition, are not globally standardized. This means the images used for the analyses are technology-dependent, adding another variable to this

complex equation. This means the images used for the analyses are technology-dependent, adding another variable to this complex equation.

Considering the amount of biomarkers that can be studied simultaneously, it is mandatory to bring performant image analysis tools capable of highlighting crucial information, flooded within the haystack of data. All these challenges cannot be faced with regular analysis tools and cannot only rely on the capability of the human eye to accurately interpret these high dimensional data.

Deep Learning at the service of multiplexed image analysis

 

It has been decades that Artificial Intelligence (AI)-automated image analysis has allowed objective quantification of images. By mimicking human behaviour, it allows better and faster data extraction from images. AI technology, such as Machine Learning, requires training the algorithms by extracting handcrafted features, which are fairly complex to define.

Deep Learning (DL) is another category of AI technology, which can aid in overcoming this problem: it is an end-to-end trainable system that includes feature extraction. The direct benefits are to save time and overcome the complexity of defining the right features to train the algorithms. This AI-technology allows the discovery of meaningful features, while combining a better robustness to signal heterogeneity, whether it is intensity or morphology-dependent. 

In the context of multiplexed image analysis, the goals are to retrieve complex information such as single cell interaction, distal analysis, expression of biomarkers or cell infiltration within the tumor.  

WORKFLOW FOR MULTIPLEXED IMAGE ANALYSIS

How can Deep Learning technology provide such data? After defining every cell location within the tissue, most frequently through DAPI staining, the positivity for each biomarker is assessed. Some cells can co-express several biomarkers and reveal certain phenotypes of interest.  

Deep Learning algorithms developed at Keen Eye rely on convolutional neural networks, which achieve state-of-the-art results in most image classification tasks. Thus, the algorithms simultaneously learn the 

specific biomarker intensity and shape to identify positive cells.

Indeed, shape is important to distinguish noisy signals from true positive cells but also enables finding low intensity positive cells, which are just above the background and exhibit the right shape.

Deep Learning algorithms give access to high level accuracy for every biomarker, which is mandatory to prevent exponential multiplication of errors during quantification steps, as phenotypes combine several biomarkers.  

The benefits of Deep Learning technology are numerous: reliable tissue segmentation, accurate biomarker quantification, cell population profiling and morphological discovery. 

Examples of spatial biology analysis outcomes. A. Tumour infiltration analysis of CD68+ cells (tumor pink, stroma blue). B. Resolution of spatial localization of biomarkers: tSNE plots for individual biomarkers, cytokeratin and PD-L1. C. Analysis of the probability of biomarkers expression with a phenograph.

Find out how Keen Eye can be your driving force for success:

References:

 

  1. Galon J, Costes A, Sanchez-Cabo F, Kirilovsky A, Mlecnik B, Lagorce-Pagès C, Tosolini M, Camus M, Berger A, Wind P, Zinzindohoué F, Bruneval P, Cugnenc PH, Trajanoski Z, Fridman WH, Pagès F. Type, density, and location of immune cells within human colorectal tumors predict clinical outcome. Science. 2006 Sep 29;313(5795):1960-4. doi: 10.1126/science.1129139. PMID: 17008531.
  2. Fridman WH, Pagès F, Sautès-Fridman C, Galon J. The immune contexture in human tumours: impact on clinical outcome. Nat Rev Cancer. 2012 Mar 15;12(4):298-306. doi: 10.1038/nrc3245. PMID: 22419253.
  3. Roach C, Zhang N, Corigliano E, Jansson M, Toland G, Ponto G, Dolled-Filhart M, Emancipator K, Stanforth D, Kulangara K. Development of a Companion Diagnostic PD-L1 Immunohistochemistry Assay for Pembrolizumab Therapy in Non-Small-cell Lung Cancer. Appl Immunohistochem Mol Morphol. 2016 Jul;24(6):392-7. doi: 10.1097/PAI.0000000000000408. PMID: 27333219; PMCID: PMC495795.
  4. Scheerens H, Malong A, Bassett K, Boyd Z, Gupta V, Harris J, Mesick C, Simnett S, Stevens H, Gilbert H, Risser P, Kalamegham R, Jordan J, Engel J, Chen S, Essioux L, Williams JA. Current Status of Companion and Complementary Diagnostics: Strategic Considerations for Development and Launch. Clin Transl Sci. 2017 Mar;10(2):84-92. doi: 10.1111/cts.12455. Epub 2017 Feb 27. PMID: 28121072; PMCID: PMC535596. 
  5. Du Z, Lin JR, Rashid R, Maliga Z, Wang S, Aster JC, Izar B, Sorger PK, Santagata S. Qualifying antibodies for image-based immune profiling and multiplexed tissue imaging. Nat Protoc. 2019 Oct;14(10):2900-2930. doi: 10.1038/s41596-019-0206-y. Epub 2019 Sep 18. PMID: 31534232; PMCID: PMC6959005.

Authors:

Charlotte Plestant - Scientific Content Manager

Louis Jeay - Data Scientist

Suliman Bouizaguen - Data Scientist

David Guet - Product Application Specialist