PathAI Research Shows Power of Artificial Intelligence to Predict Biomarkers from H&E Images

Leader in AI-powered pathology to present two abstracts at 2022 World Conference on Lung Cancer highlighting clinically relevant predictions from H&E slides

BOSTON — August 4, 2022 — PathAI, a global leader in AI-powered pathology, today announced it will present two research abstracts at this year’s IASLC 2022 World Conference on Lung Cancer hosted by the International Association for the Study of Lung Cancer in Vienna, Austria. The abstracts detail the unique capabilities of AI-powered models from PathAI to provide clinically relevant predictions from hematoxylin and eosin stain (H&E) images in a human interpretable fashion. Particularly, the demonstrated deep learning-based prediction of cMet status from H&E images show a highly sensitive predictor of cMet overexpression from H&E that can enable more efficient patient selection for clinical trial enrollment and in the future, clinical care.

Deep-Learning–Based Prediction of c-MET Status From Digitized H&E-Stained Non-small Cell Lung Cancer Tissue Samples, highlights the utility of AI-powered prediction of cMET overexpression from H&E whole slide images of non-small cell lung cancer (NSCLC) patient samples. This study leveraged PathAI’s unique approach of extracting human interpretable features (HIFs) quantifying the tumor microenvironment (TME) of NSCLC H&E images of patients. HIFs extracted from the TME demonstrated the ability to build a highly sensitive predictor of cMET overexpression directly from H&E samples, paving the way for a more efficient patient selection approach using AI-based prediction of cMet status.

“There is a wealth of spatial information in the tumor microenvironment that can be unlocked using AI-powered analyses such as these,” said Dr. Mike Montalto, Chief Scientific Officer at PathAI. “Molecular phenotypes such as cMET overexpression can leave signatures in the tissue morphology that can be leveraged to more efficiently identify the right patient for clinical trials, accelerating drug development to get patients the life-saving therapies they need.”

The World Conference on Lung Cancer runs August 6-9, 2022. PathAI’s abstract details are listed below:

Title: Deep-Learning–Based Prediction of c-MET Status From Digitized H&E-Stained Non-small Cell Lung Cancer Tissue Samples
Session Date and Time: August 8, 2022, 5:15pm-7:15pm CEST (UTC+2:00)
Session: P2.07 – Tumor Biology and Biomarkers – Tumour Biology & Preclinical Studies

Title: Digital Pathology Uncovers Multi-Omic Hallmarks of Lung Cancer in Histopathology Images
Session Date and Time: August 8, 2022, 5:15pm-7:15pm CEST (UTC+2:00)
Session: P2.15 – Tumor Biology and Biomarkers – Tumour Biology & Preclinical Studies