PathAI Announces Research Presentations at the 2024 AACR Annual Meeting The seven research presentations underscore the advantages of leveraging AI-powered pathology tools to enhance biomarker development and precision medicine strategies
Boston, MA
|
April 03, 2024 10:00 AM Eastern Daylight Time
PathAI, Inc., a leading AI-powered precision pathology company, today announced it will present research from its portfolio of oncology products at the AACR Annual Meeting on April 7-10, 2024, in San Diego, CA. The research demonstrates how machine learning models developed to characterize the tumor microenvironment (TME) from routine hematoxylin and eosin (H&E)-stained whole slide images (WSIs) can be used to advance biomarker development and precision medicine strategies.
The presentations include new research leveraging PathAI’s pan-tumor foundation models and its commercially available product, PathExplore1, to identify key histologic features associated with molecular signatures and patient response to therapy. Highlights:
- Researchers deployed PathExplore on HNSCC and NSCLC samples to characterize the cell and tissue composition of the tumor microenvironment, as well as compute immune phenotypes directly from H&E WSI. (Poster #905)
- Researchers from Incendia Therapeutics developed a continuous scoring method for Discoidin Domain Receptor 1 (DDR1), which revealed widespread immune exclusion in tumors based on the spatial distribution of lymphocytes, CD8+ T cells, and CD45+ immune cells from H&E and mIF images. DDR1 is highly expressed in epithelial cancers and has been implicated in tumor growth, invasion, and lack of response to therapy. The immune exclusion score correlates with DDR1 mRNA and protein expression. The study provides additional insight into the role of DDR1 in human cancers and may be useful in selecting indications and stratifying patients for DDR1-targeted therapies. (Poster #2916)
- Using unsupervised learning driven by PathExplore’s features and a novel collagen fiber detection imaging technology, researchers discovered three distinct phenotypes of cancer associated stroma (CAS) that had distinct patterns of association with survival and gene expression signatures. Two of them were enriched in collagen fiber density as well as in density of fibroblasts, while the third phenotype had the highest density of immune cells, providing a categorization of different types of CAS-tumor interaction that may be useful for patient stratification. (Poster #4912)
- Using AI-powered models from PathAI, Foundation Medicine researchers investigated digital pathology TME features of immunotherapy outcomes among NSCLC patients within a real-world dataset from the Flatiron Health-Foundation Medicine Clinico-Genomic Database. These results indicate that the composition of the TME assessed via digital pathology may have utility in identifying NSCLC patients who will respond to first-line immune checkpoint inhibitors beyond the established immunotherapy biomarkers. (Poster #4969)
- In collaboration with EMD Serono, AI-powered TME models from PathAI were used to analyze H&E WSI of NSCLC from a randomized Phase 3 trial directly comparing two immunotherapies. Researchers compared cell abundance features with gene expression data from the same samples and found that immune and stromal cell abundance features were associated with expression of genes in relevant cellular pathways, confirming the biological relevance of our cellular features. In analyzing the features alongside the clinical data from the retrospective study, researchers identified candidate prognostic immunotherapy biomarkers. (Poster #6179)
- Researchers from Incendia Therapeutics illustrated that morphologic features derived from H&E images using PathExplore can be effective predictors of CD8-defined immune exclusion, providing an option for patient stratification by immune phenotype using widely available H&E images. The features and direction of association align with prior knowledge of the mechanism or manifestations of immune exclusion or infiltration in the TME, including the relative density of lymphocytes in tumor and stroma. (Poster #7392)
- PathAI’s pan-tumor foundation models were used to identify tissue regions and cell types on H&E WSI to quantify tumor purity across multiple tumor types. Model-derived tumor purity estimates were compared to three orthogonal molecular methods of purity and found to correlate across disease indications. These results provide evidence of how AI can improve the efficiency of molecular testing and enhance precision diagnostic strategies. (Poster #7402)
Follow PathAI on LinkedIn and X for more updates from #AACR24 and visit us in person at booth #1549.
1PathExplore is For Research Use Only. Not for use in diagnostic procedures.
About PathAI
PathAI is the only AI-focused technology company to provide comprehensive precision pathology solutions from wet lab services to algorithm deployment for clinical trials and laboratory use. Rigorously trained and validated with data from more than 15 million annotations, its AI-powered models can be leveraged to optimize the analysis of pathology samples to improve efficiency and accuracy of pathology interpretation, as well as to better gauge therapeutic efficacy and accelerate drug development for complex diseases.
PathAI, which is headquartered in Boston, MA, and operates a CAP/CLIA-certified laboratory in Memphis, TN, is proud to have a team of 600+ innovative thinkers from around the globe. For more information, please visit www.pathai.com.
Contact Details
SVM Public Relations and Marketing Communications
Maggie Naples
+1 401-490-9700
Company Website
