Lunit to Present AI Study on EGFR Mutation Prediction in NSCLC at AACR 2025 in Collaboration with AstraZeneca
Lunit (KRX:328130.KQ) and AstraZeneca (AZN) will present a collaborative AI study at AACR 2025, showcasing the Lunit SCOPE Genotype Predictor. This deep learning model predicts EGFR mutations in non-small cell lung cancer (NSCLC) patients using H&E-stained tissue samples.
The study utilized the largest diverse training dataset to date, comprising over 12,000 pathology slides (>4,500 EGFR-mutated and >7,500 wild-type) from NSCLC patients across the US, China, and South Korea. The AI model demonstrated consistent performance across various clinical variables, including specimen types, EGFR mutation subtypes, slide scanners, and scan magnifications.
The technology aims to address current limitations in molecular testing accessibility for NSCLC patients, offering a rapid and cost-effective solution for predicting driver mutations. The presentation will take place at the AACR Annual Meeting from April 25-30, 2025, in Chicago.
Lunit (KRX:328130.KQ) e AstraZeneca (AZN) presenteranno uno studio collaborativo sull'IA all'AACR 2025, mostrando il Lunit SCOPE Genotype Predictor. Questo modello di deep learning prevede le mutazioni EGFR nei pazienti con carcinoma polmonare non a piccole cellule (NSCLC) utilizzando campioni di tessuto colorati con H&E.
Lo studio ha utilizzato il più grande dataset di addestramento diversificato mai realizzato, composto da oltre 12.000 diapositive patologiche (>4.500 con mutazioni EGFR e >7.500 di tipo selvatico) provenienti da pazienti NSCLC negli Stati Uniti, in Cina e in Corea del Sud. Il modello di IA ha dimostrato prestazioni costanti attraverso varie variabili cliniche, inclusi i tipi di campione, i sottotipi di mutazione EGFR, gli scanner di diapositive e le ingrandimenti di scansione.
La tecnologia mira a affrontare le attuali limitazioni nell'accessibilità ai test molecolari per i pazienti NSCLC, offrendo una soluzione rapida ed economica per prevedere le mutazioni driver. La presentazione avrà luogo durante l'AACR Annual Meeting dal 25 al 30 aprile 2025 a Chicago.
Lunit (KRX:328130.KQ) y AstraZeneca (AZN) presentarán un estudio colaborativo de IA en el AACR 2025, mostrando el Lunit SCOPE Genotype Predictor. Este modelo de aprendizaje profundo predice mutaciones de EGFR en pacientes con cáncer de pulmón no microcítico (NSCLC) utilizando muestras de tejido teñidas con H&E.
El estudio utilizó el conjunto de datos de entrenamiento más diverso hasta la fecha, que comprende más de 12,000 diapositivas de patología (>4,500 mutadas por EGFR y >7,500 tipo salvaje) de pacientes con NSCLC en EE. UU., China y Corea del Sur. El modelo de IA demostró un rendimiento consistente en diversas variables clínicas, incluidos tipos de muestras, subtipos de mutación de EGFR, escáneres de diapositivas y aumentos de escaneo.
La tecnología tiene como objetivo abordar las limitaciones actuales en la accesibilidad a las pruebas moleculares para pacientes con NSCLC, ofreciendo una solución rápida y rentable para predecir mutaciones conductoras. La presentación tendrá lugar en la Reunión Anual de AACR del 25 al 30 de abril de 2025 en Chicago.
루닛 (KRX:328130.KQ)와 아스트라제네카 (AZN)는 AACR 2025에서 협력 AI 연구를 발표하며, 루닛 SCOPE 유전자 예측기를 선보일 예정입니다. 이 딥러닝 모델은 H&E 염색된 조직 샘플을 사용하여 비소세포 폐암(NSCLC) 환자의 EGFR 변이를 예측합니다.
이번 연구는 미국, 중국, 한국의 NSCLC 환자들로부터 수집된 12,000개 이상의 병리 슬라이드(>4,500 EGFR 변이 및 >7,500 야생형)를 포함한 가장 다양한 훈련 데이터셋을 활용했습니다. AI 모델은 샘플 유형, EGFR 변이 하위 유형, 슬라이드 스캐너 및 스캔 배율 등 다양한 임상 변수에서 일관된 성능을 보여주었습니다.
이 기술은 NSCLC 환자를 위한 분자 검사 접근성의 현재 한계를 해결하는 것을 목표로 하며, 드라이버 변이를 예측하기 위한 빠르고 비용 효율적인 솔루션을 제공합니다. 발표는 2025년 4월 25일부터 30일까지 시카고에서 열리는 AACR 연례 회의에서 이루어질 예정입니다.
Lunit (KRX:328130.KQ) et AstraZeneca (AZN) présenteront une étude collaborative sur l'IA lors de l'AACR 2025, mettant en avant le Lunit SCOPE Genotype Predictor. Ce modèle d'apprentissage profond prédit les mutations EGFR chez les patients atteints de cancer du poumon non à petites cellules (NSCLC) en utilisant des échantillons de tissu teintés à l'H&E.
L'étude a utilisé le plus grand ensemble de données d'entraînement diversifié à ce jour, comprenant plus de 12 000 lames de pathologie (>4 500 avec mutations EGFR et >7 500 de type sauvage) provenant de patients NSCLC aux États-Unis, en Chine et en Corée du Sud. Le modèle d'IA a montré des performances cohérentes à travers diverses variables cliniques, y compris les types d'échantillons, les sous-types de mutations EGFR, les scanners de lames et les grossissements de numérisation.
La technologie vise à résoudre les limitations actuelles de l'accessibilité aux tests moléculaires pour les patients NSCLC, offrant une solution rapide et économique pour prédire les mutations conductrices. La présentation aura lieu lors de la réunion annuelle de l'AACR du 25 au 30 avril 2025 à Chicago.
Lunit (KRX:328130.KQ) und AstraZeneca (AZN) werden auf dem AACR 2025 eine gemeinsame KI-Studie präsentieren, die den Lunit SCOPE Genotype Predictor vorstellt. Dieses Deep-Learning-Modell sagt EGFR-Mutationen bei Patienten mit nicht-kleinzelligem Lungenkrebs (NSCLC) anhand von H&E-färbten Gewebeproben voraus.
Die Studie nutzte den bisher größten vielfältigen Trainingsdatensatz, der über 12.000 pathologische Folien (>4.500 EGFR-mutiert und >7.500 Wildtyp) von NSCLC-Patienten aus den USA, China und Südkorea umfasst. Das KI-Modell zeigte in verschiedenen klinischen Variablen, einschließlich Probenarten, EGFR-Mutationsuntertypen, Folien-Scannern und Scan-Vergrößerungen, eine konsistente Leistung.
Die Technologie zielt darauf ab, die aktuellen Einschränkungen bei der Zugänglichkeit von molekularen Tests für NSCLC-Patienten zu überwinden und bietet eine schnelle und kostengünstige Lösung zur Vorhersage von Treibermutationen. Die Präsentation findet während des AACR-Jahrestreffens vom 25. bis 30. April 2025 in Chicago statt.
- Partnership with major pharmaceutical company AstraZeneca enhances market credibility
- AI technology addresses significant market need in NSCLC molecular testing
- Large-scale validation using 12,000+ pathology slides demonstrates robust performance
- Cost-effective solution potential for healthcare providers
- Technology still pending regulatory approvals for clinical use
- Commercial success depends on healthcare provider adoption
Insights
AstraZeneca's collaboration with Lunit represents a strategic but early-stage investment in AI-powered precision medicine capabilities for lung cancer treatment. The development of the Lunit SCOPE Genotype Predictor addresses a critical bottleneck in NSCLC treatment pathways, where many patients miss opportunities for targeted therapy due to insufficient molecular testing.
The significance lies in the potential to expand the addressable patient population for AstraZeneca's EGFR-targeted therapies like Tagrisso, which remains one of their key revenue drivers in oncology. By potentially identifying EGFR mutations from routine H&E slides, this AI tool could help prioritize patients for confirmatory molecular testing, particularly in regions with testing infrastructure.
What distinguishes this initiative is the scale and diversity of validation - with over 12,000 pathology slides from multiple countries. This suggests the technology may be robust enough for varied clinical settings, potentially expanding AstraZeneca's precision medicine reach globally.
However, investors should note this remains a research-stage collaboration with no disclosed regulatory timeline, commercialization strategy, or specific accuracy metrics. This technology would likely complement, not replace, conventional molecular testing, positioning it as a longer-term strategic asset rather than a near-term revenue driver for AstraZeneca.
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
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,
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 through AI. 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 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
View original content to download multimedia:https://www.prnewswire.com/news-releases/lunit-to-present-ai-study-on-egfr-mutation-prediction-in-nsclc-at-aacr-2025-in-collaboration-with-astrazeneca-302411752.html
SOURCE Lunit
FAQ
What is the purpose of Lunit and AstraZeneca's (AZN) AI collaboration for NSCLC patients?
How many pathology slides were used to train the Lunit SCOPE Genotype Predictor?
When and where will Lunit present their EGFR mutation prediction study with AstraZeneca (AZN)?
What clinical variables was the AI model tested across for NSCLC patients?
