PathAI to Present on AI Models Supporting Advances in Oncology Research at Society for Immunotherapy of Cancer Annual Meeting

Last year at SITC, PathAI presented data highlighting their machine learning (ML) model that was developed to identify and quantify CD8+ T cells in digitized whole slide images of melanoma patients. PathAI has since expanded upon that research and will share data demonstrating how their newly developed ML-based models quantify CD8+ lymphocytes and CD8 topology classifiers across seven cancer types: NSCLC, urothelial carcinoma, head and neck squamous cell carcinoma, gastric cancer, colorectal cancer, pancreatic cancer, and hepatocellular carcinoma.

“Concordance analysis of AI-powered CD8 quantification and automated CD8 topology with manual histopathological assessment across seven solid tumor types” shows that PathAI’s ML model-predicted CD8+ cell counts are highly correlated with pathologist-generated counts across these tumor types. This poster also highlights PathAI’s ability to characterize the topology of CD8 expression across the tumor to predict immune-inflamed, excluded and desert immunophenotypes in these seven cancer types. This work demonstrates the power of PathAI’s digital pathology models for automated quantitation of the CD8+ lymphocytes and immunophenotyping in clinical samples, confirming the potential for this approach in immuno-oncology.

“Our latest results support and further extend our research in immuno-oncology for multiple disease areas,” said Dr. Mike Montalto, Chief Scientific Officer at PathAI. “This is another big step forward in innovating and improving pathology research, future drug development, and, ultimately, patient outcomes.”

Additionally, PathAI has developed a new deep-learning-based method for the analysis of whole slide image multiplex immunofluorescence (mIF) data in NSCLC. As the importance of spatial relationships between cells increases in immuno-oncology, “Identification of clinically relevant spatial phenotypes in large-scale multiplex immunofluorescence data via unsupervised graph learning in non-small cell lung cancer” aims to show how a deep-learning approach to mIF analysis can capture spatial phenotypes in NSCLC. The graph neural network (GNN) approach used in this study revealed distinct spatial phenotypes that can describe the organization of distinct cell types, such as cancer and immune cells. The relative amounts of these phenotypes in a cancer specimen are related to the immunogenicity and antigenicity of the cancer, as well as patient outcome. This new approach has potential to identify patterns in the spatial relationship between cells in NSCLC tissue.

The full list of PathAI’s poster presentations highlighting their biomarker and tumor microenvironment research products is listed below. More information on each research abstract can be found here.

Title: Characteristics of the tumor microenvironment in IDH1-mutated cholangiocarcinoma patients from ClarIDHy trial
Poster Hours: November 11, 2022, from 9:00 AM – 8:30 PM ET
Abstract: #552
Collaborator: Servier Pharmaceuticals

Title: Identification of clinically relevant spatial tissue phenotypes in large-scale multiplex immunofluorescence data via unsupervised graph learning in non-small cell lung cancer
Poster Hours: November 10, 2022, from 9:00 AM – 9:00 PM ET
Abstract: #1277
Collaborator: Bristol Myers Squibb

Title: A multi-tumor machine learning model to identify tertiary lymphoid structures in histopathological H&E images as a potential clinical biomarker
Poster Hours: November 10, 2022, from 9:00 AM – 9:00 PM ET
Abstract: #1291
Collaborator: Bristol Myers Squibb

Title: Concordance analysis of AI-powered CD8 quantification and automated CD8 topology with manual histopathological assessment across seven solid tumor types
Poster Hours: November 11, 2022, from 9:00 AM – 8:30 PM ET
Abstract: #1282
Collaborator: Bristol Myers Squibb

Title: Artificial intelligence (AI)-powered immune phenotyping of advanced or metastatic urothelial carcinoma (aUC) clinical trial samples from hematoxylin and eosin (H&E)-stained whole slide images (WSI)
Poster Hours: November 11, 2022, from 9:00 AM – 8:30 PM ET
Abstract: #554
Collaborators: Merck KGaA, Darmstadt, Germany, and Pfizer

About PathAI 

PathAI is a leading provider of AI-powered research tools and services for pathology. PathAI’s platform promises substantial improvements to the accuracy of diagnosis and the efficacy of treatment of diseases like cancer, leveraging modern approaches in machine and deep learning. Based in Boston, PathAI works with leading life sciences companies and researchers to advance precision medicine. To learn more, visit pathai.com.