PathAI, a leader in AI-powered precision pathology, is preparing to present its latest research at the AACR Annual Meeting from April 7-10, 2024, in San Diego, CA. The company's innovative machine learning models, designed to analyze the tumor microenvironment (TME) from routine hematoxylin and eosin (H&E)-stained whole slide images (WSIs), are set to revolutionize biomarker development and precision medicine approaches.
Among the highlights is PathAI's PathExplore product, which has been applied to head and neck squamous cell carcinoma (HNSCC) and non-small cell lung cancer (NSCLC) samples. This tool characterizes the cell and tissue composition of the TME and computes immune phenotypes directly from H&E WSI, showcasing its potential in cancer research (Poster #905).
In a collaborative effort with Incendia Therapeutics, PathAI has developed a continuous scoring method for Discoidin Domain Receptor 1 (DDR1). This method uncovers widespread immune exclusion in tumors by analyzing the spatial distribution of immune cells from H&E and multiplex immunofluorescence (mIF) images. Such findings could significantly impact patient stratification for DDR1-targeted therapies (Poster #2916).
Another groundbreaking study facilitated by PathExplore identified three distinct cancer-associated stroma (CAS) phenotypes. These phenotypes, associated with survival and gene expression signatures, could enhance patient stratification by understanding CAS-tumor interactions (Poster #4912).
Foundation Medicine researchers utilized PathAI's AI models to explore digital pathology TME features related to immunotherapy outcomes in NSCLC patients. This research suggests that TME composition could help identify responders to immune checkpoint inhibitors, beyond current biomarkers (Poster #4969).
Collaborating with EMD Serono, PathAI analyzed H&E WSI of NSCLC from a Phase 3 trial, identifying potential prognostic immunotherapy biomarkers. This study links immune and stromal cell abundance features with gene expression and clinical data, offering new avenues for treatment strategies (Poster #6179).
Incendia Therapeutics further demonstrated that PathExplore's morphologic features from H&E images can predict CD8-defined immune exclusion. This capability allows for patient stratification by immune phenotype using widely available H&E images (Poster #7392).
Lastly, PathAI's pan-tumor foundation models were used to quantify tumor purity across various tumor types by identifying tissue regions and cell types on H&E WSI. The correlation of these estimates with molecular methods underscores AI's role in enhancing molecular testing and diagnostic precision (Poster #7402).
For those interested in learning more about PathAI's contributions to cancer research and precision medicine, additional information can be found by visiting their LinkedIn and X profiles.
