AI-powered model predicts EGFR mutations from H&E-stained slides, demonstrating robust performance across diverse clinical settings and helping overcome barriers to molecular testing in NSCLC
SEOUL, South Korea, April 2, 2025 -- Lunit (KRX:328130.KQ), a leading provider of AI-powered solutions for cancer diagnostics and therapeutics, will present a deep learning study on Epidermal Growth Factor Receptor (EGFR) mutation prediction in patients with non-small cell lung cancer (NSCLC) at the upcoming American Association for Cancer Research (AACR) Annual Meeting 2025, held from April 25 to 30 in Chicago, Illinois. The study, which highlights the development and validation of the Lunit SCOPE Genotype Predictor, an AI-powered deep learning model capable of predicting EGFR mutations directly from hematoxylin and eosin (H&E)-stained tissue samples in NSCLC patients, will be presented in collaboration with AstraZeneca (LSE/STO/Nasdaq: AZN).
EGFR mutation testing plays a crucial role in determining the best course of treatment for patients with NSCLC, yet many patients remain untested due to logistical and resource constraints, despite guideline recommendations. Existing AI models designed to predict mutations from pathology images have faced limitations in real-world clinical applications due to limited training data and lack of validation. Lunit and AstraZeneca’s collaborative study leveraged the largest and most diverse training dataset to date, consisting of more than 12,000 pathology slides (>4,500 EGFR-mutated and >7,500 wild-type) from NSCLC patients across multiple countries, including the US, China, and South Korea, to further develop and validate Lunit’s model.
In brief
Lunit says it will present a collaborative study with AstraZeneca on predicting EGFR mutations in people with non-small cell lung cancer (NSCLC) at the AACR Annual Meeting 2025 in Chicago. The research developed and validated Lunit SCOPE Genotype Predictor, which analyzes H&E-stained tissue slides. The study used more than 12,000 pathology slides from patients in several countries, including the United States, China and South Korea. Lunit reports that model performance was consistent across specimen types, mutation subtypes, scanners and scan magnifications. The company says the approach could help clinicians prioritize molecular testing where access is constrained. The release does not provide a numerical performance result. Lunit CEO Brandon Suh is quoted discussing the study’s potential role in precision oncology.
Key takeaways
- Lunit and AstraZeneca collaborated on a study of AI-based EGFR mutation prediction in NSCLC.
- The model analyzes H&E-stained tissue samples and was developed and validated using more than 12,000 pathology slides.
- Lunit says model performance was consistent across several clinical and technical variables.
- The study is scheduled for presentation at the AACR Annual Meeting 2025 in Chicago.
The AI model’s performance remained consistent across key clinical variables including specimen types, EGFR mutation subtypes, slide scanners, and scan magnifications, reinforcing its potential for real-world deployment in diverse clinical environments.
The collaboration focuses on the development of the Lunit SCOPE Genotype Predictor, an AI-driven tool designed to rapidly and cost-effectively predict NSCLC driver mutations from H&E-stained tissue samples.
“This study is a testament to the real-world potential of AI in precision oncology,” said Brandon Suh, CEO of Lunit. “By leveraging Lunit AI, we have demonstrated that routine pathology slides can serve as a powerful tool to predict EGFR mutations with high accuracy. This could help clinicians prioritize molecular testing for NSCLC patients, ensuring that patients receive targeted therapy without unnecessary delays. We are excited to showcase this breakthrough at AACR 2025, reinforcing our commitment to advancing AI-driven precision oncology in collaboration with AstraZeneca.”
Join Us at AACR 2025
Visit Lunit at AACR 2025 Booth #2843 to learn more about this study and how AI is advancing precision oncology and improving patient outcomes.
About Lunit
Founded in 2013, Lunit (KRX:328130.KQ) is a medical AI company on a mission to conquer cancer. Lunit harnesses AI-powered medical image analytics and biomarker analysis to ensure accurate diagnosis and optimal treatment for each cancer patient. The FDA-cleared Lunit INSIGHT suite for cancer screening serves over 4,800 hospitals and medical institutions across 55+ countries. Lunit clinical studies have been published in top journals, including the Journal of Clinical Oncology and the Lancet Digital Health, and presented at global conferences such as the ASCO and RSNA. Headquartered in Seoul, South Korea, with a network of offices worldwide, Lunit leads the global fight against cancer. Discover more at lunit.io.
If you detect any issues, problems, or errors in this press release content, kindly contact [email protected] to notify us (it is important to note that this email is the authorized channel for such matters, sending multiple emails to multiple addresses does not necessarily help expedite your request). We will respond and rectify the situation in the next 8 hours.
Questions around this news
What did the study presented at AACR 2025 examine?
The study examined a deep-learning model designed to predict EGFR mutations in non-small cell lung cancer (NSCLC) using routine hematoxylin and eosin-stained pathology slides. The release says the model was developed and validated using slides from patients in multiple countries, and that its performance was consistent across specimen types, mutation subtypes, scanners, and scan magnifications.
How could AI-based EGFR prediction support molecular testing for NSCLC?
The release says logistical and resource constraints leave some patients untested despite guideline recommendations. The model is intended to help clinicians prioritize molecular testing by identifying patients whose tissue slides suggest an EGFR mutation. The release describes this as support for prioritizing testing, not as a replacement for molecular testing or a confirmed mutation diagnosis.
What is an EGFR mutation, and why can it matter in NSCLC?
EGFR is a gene that provides instructions for a protein involved in cell growth and signaling. Some changes in this gene can affect how cancer cells behave and may help guide treatment choices in NSCLC. Molecular testing can identify these changes, giving clinicians information to consider alongside other clinical findings.
What are hematoxylin and eosin-stained pathology slides?
Hematoxylin and eosin, often abbreviated H&E, are dyes used to color thin tissue samples for examination under a microscope. The stains help make cell structures and tissue patterns visible to pathologists. Digital images of these slides can also be analyzed with computational methods, including machine-learning systems.
Earlier from Lunit
- Lunit Secures Multi-Year Contract with UAE's Largest Healthcare Network to Power National AI Breast Cancer Screening Program
- World’s First Large-Scale, Multicenter Prospective Study in Single-Reading Mammography Confirms Lunit AI Boosts Cancer Detection
- Lunit Expands Partnership with Saudi Arabia’s Largest Medical Group to Deploy AI Chest X-Ray Solution
- Real-World Validation: Lunit AI Proven Successful in 1-Year Breast Cancer Screening Deployment
- Lunit Inks Partnership with Salud Digna to Advance AI in Medical Imaging
