Characterization of the location and phenotype of cells in the tumor microenvironment (TME) is important to inform the development and monitoring of anti-cancer therapeutic interventions, especially immunotherapies designed to stimulate the immune system to have an anti-cancer effect. Multiplex immunofluorescence (mIF) imaging is being increasingly employed to simultaneously label multiple cell types and subtypes in the tumor microenvironment, but interpretation of these images to gain a robust understanding of tumor and immune cell interactions remains a complicated and challenging process. The rich phenotypic information contained in mIF images has to be taken into account with the spatial topology of the cells in order to be able to distil potential predictive indicators of patient response to therapies as well as prognostic indicators of outcome. While contemporary computational methods allow pathologists to view aggregated phenotypical information and cell interactions on a limited, generally one-to-one basis, these methods have been largely descriptive and geared toward addressing hypotheses as opposed to holistically leveraging the spatial and phenotypic data into a single predictive model. Additional methods are needed to provide a fuller picture of the spatial structure of the TME as captured in mIF images. In this work, we propose a novel pipeline that uses graphs generated from image analysis results and user-defined distance criteria to represent the tumor cellular microstructure. This graph-based approach complements existing mIF analysis techniques by providing information on the spatial, phenotypic, and morphological features of cells in the context of their neighborhood. These graphs subsequently enable characterization of protein expression in detail, description of interactions between individual cells or cell types and their neighbors, interactive tissue querying, and exploration of the cell-level biodiversity. The graph approach not only allows pathologists to efficiently interrogate data contained in mIF images in a hypothesis-driven manner, but importantly also supports more holistic data-driven approaches which, by leveraging state of the art graph convolutional neural networks to obtain numerical embeddings representing each graph and its nodes, enable additional downstream activities such as cell similarity search, and the development of predictive models for patient outcomes and response to therapies.
Citation Format: Jason Hipp, Christopher Innocenti, Zhenning Zhang, Jake Cohen-Setton, Balaji Selvaraj, Michalis Frangos, Carlos Pedrinaci, Michael Surace, Laura Dillon, Khan Baykaner. Leveraging graphs to do novel hypothesis and data-driven research using multiplex immunofluorescence images [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PR-05.