바이오스펙테이터

by Sungmin Kim

Collaboration to harness Lunit SCOPE Genotype Predictor for rapid and convenient prediction of non-small cell lung cancer driver mutations

AstraZeneca has started utilizing AI tools to identify patients with mutations in EGFR-mutated non-small cell lung cancer, a key focus area for its anticancer drug portfolio.

Lunit 18th announced a strategic collaboration with AstraZeneca, a leading pharmaceutical company, to develop AI-powered digital pathology solutions.

The solution in focus is Lunit SCOPE Genotype Predictor, an AI-powered tool capable of analyzing H&E slide images to predict the likelihood of the tumor harboring NSCLC driver mutations, such as Epidermal Growth Factor Receptor (EGFR) mutations.

Identifying patients with mutations in genes such as EGFR is crucial in determining the most appropriate therapies for patients with certain types of cancer, such as NSCLC. Genomic testing in NSCLC is resource intensive and time consuming, and is too often bypassed because of the urgency to begin treatment. By leveraging Lunit SCOPE Genotype Predictor, the collaboration aims to develop a rapid and cost-effective AI screening tool for predicting NSCLC driver mutations directly from H&E-stained tissue samples. The results from this risk assessment tool would be available before molecular test results, thus allowing practitioners to prioritize testing of patient tumor samples that have a high likelihood for harboring EGFR mutations.

“This collaboration with Lunit underscores our commitment to advancing precision medicine in oncology,” said Kristina Rodnikova, Head of Global Oncology Diagnostics, Oncology Business Unit at AstraZeneca. “Tools like this will help to address unmet needs by optimizing diagnostic workflows for NSCLC patients and, ultimately, improve their outcomes.”

“We are excited to partner with AstraZeneca, a leader in oncology therapeutics, to develop and evaluate this groundbreaking technology,” said Brandon Suh, CEO of Lunit. “The integration of Lunit SCOPE Genotype Predictor as a screening test into pathology workflows promises to improve the opportunity for patients to benefit from appropriate targeted therapy, ultimately improving patient outcomes and streamlining the treatment planning process.”

Together, AstraZeneca and Lunit hope to further develop this screening tool and, following validation, explore its deployment in real-world settings to assess risk of lung driver mutations, and inform further molecular testing.

Lunit SCOPE Genotype Predictor utilizes advanced deep learning algorithms to analyze H&E slide images and predict the likelihood of presence of druggable genomic alterations, such as the presence of EGFR and other genomic alterations which, when confirmed, could inform treatment decision making. This novel approach can inform treatment teams about which molecular tests and results could be most important to prioritize before starting therapy, making it a valuable tool for both pathologists and oncologists.

As part of this collaboration, Lunit and AstraZeneca will also explore additional future molecular biomarker predictions based on H&E slide analysis, enabling their future development and extensive validation. The ultimate goal is to render these AI-powered solutions accessible to laboratories and healthcare institutions worldwide. By empowering healthcare practitioners with state-of-the-art computational pathology tools, actionable insights can be derived to help prioritize confirmatory molecular testing and select the optimal treatments for patients with cancer.