– Lunit presentations at ASCO 2024 to highlight advances including AI-based ultra-low HER2 detection and ICI response prediction models for NSCLC, demonstrating the impact of the Lunit SCOPE suite on precision oncology
Seoul, South Korea, May 24, 2024 /PRNewswire/ — Lunit (KRX: 328130.KQ), a leading provider of AI-based solutions for cancer diagnosis and therapy, today announced the presentation of seven studies at the meeting 2024 Annual Meeting of the American Society of Clinical Oncology (ASCO) ChicagoSince May 31 to June 4. Lunit will present detailed results from several innovative studies, including the identification of ultra-low HER2 expression in breast cancer using AI-based quantification, and a learning-based model deep integrating chest CT and histopathological analysis to predict immunotherapy response in non-small cell cells. lung cancer (NSCLC).
Visit Lunit at booth IH22 to discover how the Lunit SCOPE suite is revolutionizing oncology research and clinical practice.
In a poster presentation, Lunit’s AI-powered HER2 analyzer, Lunit SCOPE HER2, demonstrated its ability to identify ultra-low HER2 expression and differentiate it from true HER2-negative cases in patients with breast cancer using continuous subcellular quantification from HER2 immunohistochemistry (IHC) images. .
According to results presented at ASCO 2022, HER2-targeted antibody-drug conjugates (ADCs) can effectively target tumor cells even in low-HER2 breast cancers. This highlights the importance of accurately identifying HER2-low and HER2 ultra-low expression in breast cancer, particularly for patients previously classified as HER2-negative. In response, Lunit developed an AI-based whole slide image (WSI) analyzer for IHC-stained slides to differentiate between true HER2 negative and ultra-low HER2 cases. The AI model evaluated more than 67 million tumor cells and 119 million non-tumor cells from 401 WSIs, identifying a significant proportion of ultra-low HER2 cases among the HER2 score 0 cases evaluated by pathologists. This AI-based analysis could expand and refine treatment options for patients benefiting from HER2-targeted therapies, as demonstrated by the 23.6% of cases with a HER2 score of 0 identified as ultra-low HER2 by the IA and the 51.9% of cases with a HER2 score of 1+ classified. as low HER2 by AI, comparable to the 52.3% objective response rate to a HER2-targeted ADC observed in another clinical trial.
In another study, Lunit developed and validated an AI model that analyzes patients’ chest CT images alone and in combination with pathology images to predict immune checkpoint inhibitor (ICI) response in patients suffering from NSCLC. Lunit’s deep learning-based chest CT prediction model, developed using data from 1,876 NSCLC patients treated with ICI, predicted treatment response based on pre-treatment chest CT scans, as well as PD-L1 status and immune phenotype. The model demonstrated significant predictive power as an independent biomarker. Patients predicted as responders by the AI model showed significantly longer median time to next treatment (TTNT; 7 months vs. 2.5 months) and longer overall survival (OS; 16.5 months vs. 7 .6 months) compared to patients predicted to be non-responders. . Combining the AI CT model with histopathological biomarkers such as PD-L1 expression and tumor-infiltrating lymphocytes (TIL) further improved prediction accuracy, highlighting the complementary strengths of imaging and pathology data to improve the predictive models of the response HERE.
A collaborative study with Stanford University The School of Medicine examined the association of immune phenotypes with outcomes after immunotherapy in metastatic melanoma, highlighting the heterogeneity of immune phenotypes across melanoma subtypes.
Another study with Northwestern University used AI-based analysis of tertiary lymphoid structures (TLS) in H&E whole-slide images to predict response to immunotherapy in NSCLC patients. This demonstrated the potential of AI in identifying biomarkers predictive of survival outcomes.
“At ASCO 2024, Lunit is proud to present seven groundbreaking studies that illustrate our pioneering role in AI-driven precision oncology,” said Brandon Suh, CEO of Lunit. “From HER2 quantification to predictive models of immunotherapy response, our work is transforming oncology by making cancer treatment not only personalized but also predictive, ensuring the best possible outcomes for patients around the world.
In addition to the above studies, Lunit will present three other studies at this year’s ASCO, demonstrating the diverse capabilities of the Lunit SCOPE suite. Studies include comprehensive histopathomic prediction models for early breast cancer and hypothetical generation of test and control groups for treatment selection in high TPS NSCLC.
Visit Lunit at booth IH22 to discover how the Lunit SCOPE suite is revolutionizing oncology research and clinical practice.
Presentations at ASCO 2024 featuring Lunit SCOPE include:
- “Ultra-low HER2 identification based on artificial intelligence (AI)-based subcellular HER2 quantification from HER2 immunohistochemistry images“ (11:15 a.m., Billboard #93)
- “Deep learning-based chest CT model to predict treatment response to immune checkpoint inhibitors in non-small cell lung cancer, independent and additive to histopathological biomarkers“ (8536, notice board no. 400)
- “Artificial intelligence (AI)-based whole-slide image (WSI) analysis to predict recurrence of hormone receptor-positive (HR+) early breast cancer (EBC)“ (571, notice board no. 163)
- “Immune Phenotype Profiling Based on Anatomical Origin of Melanoma and Impact on Clinical Outcomes of Immune Checkpoint Inhibitor Treatment“ (9569, notice board no. 353)
- “Artificial Intelligence (AI)-Based H&E Image Analysis (WSI) of Tertiary Lymphoid Structure (TLS) to Predict Response to Immunotherapy in Non-Small Cell Lung Cancer (NSCLC)“ (3135, notice board no. 280)
- “Updated Safety, Efficacy, Pharmacokinetics, and Biomarkers from the Phase 1 Study of IMC-002, a Novel Anti-CD47 Monoclonal Antibody, in Patients With Advanced Solid Tumors“ (2642, notice board no. 121)
- “Relationship Between Immune Phenotype and Chemo-IO Versus IO Only Treatment Selection in High TPS NSCLC Using Hypothetical Test and Control Group Generation Based on Survival Data Extracted from Phase III Trials“ (e13569)
About Lunit
Founded in 2013, Lunit is a medical AI company with a mission to beat cancer. We leverage AI-based medical image analysis and AI biomarkers to ensure accurate diagnosis and optimal treatment for every cancer patient. Our FDA-approved Lunit INSIGHT suite for cancer screening serves more than 3,000 hospitals and medical facilities in more than 40 countries.
Our clinical findings are featured in leading journals including the Journal of Clinical Oncology and Lancet Digital Health, and presented at global conferences such as ASCO and RSNA.
In 2024, Lunit acquired Volpara Health Technologies, paving the way for unparalleled synergy and precision, particularly in breast health and screening technologies.
Based at Seoul, South Korea, with a global network of offices, Lunit is a leader in medical AI innovation. Find out more about lunit.io.
SOURCE Lunit
