South Korea-based AI-powered cancer diagnostics company Lunit has partnered with British pharmaceutical company AstraZeneca to develop AI-powered digital pathology solutions.
The collaboration will focus on Lunit SCOPE Genotype Predictor, an AI-powered solution for analysing H&E slide images to predict tumours harbouring mutations that drive NSCLC.
It leverages advanced deep learning algorithms to analyse and predict the presence of druggable genomic alterations, which could inform treatment decisions when confirmed.
By identifying patients with mutations in genes, such as Epidermal Growth Factor Receptor (EGFR) mutations, the solution will help determine the most appropriate therapies.
AstraZeneca oncology business unit global oncology diagnostics head Kristina Rodnikova said: “This collaboration with Lunit underscores our commitment to advancing precision medicine in oncology.
“Tools like this will help to address unmet needs by optimising diagnostic workflows for NSCLC patients and, ultimately, improve their outcomes.”
According to Lunit, genomic testing in NSCLC is resource-intensive and time-consuming and is too often bypassed because of the urgency to begin treatment.
The collaboration will develop a rapid and cost-effective AI screening tool for predicting NSCLC driver mutations directly from H&E-stained tissue samples.
Lunit SCOPE Genotype Predictor is a risk assessment tool that would provide results before molecular test results, allowing practitioners to prioritise patients with EGFR mutations.
AstraZeneca and Lunit would further develop the tool and explore its deployment in real-world settings to evaluate the risk of lung mutations and inform further molecular testing.
Furthermore, the companies will also explore additional molecular biomarker predictions based on H&E slide analysis, enabling future development and validation.
Lunit CEO Brandon Suh said: “We are excited to partner with AstraZeneca, a leader in oncology therapeutics, to develop and evaluate this groundbreaking technology.
“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.”
