# Lunit Highlights AI-Powered Pathology Insights Across Cancer Types at ESMO 2026 - Link: https://www.thailand-business-news.com/pr-news/lunit-highlights-ai-powered-pathology-insights-across-cancer-types-at-esmo-2026 - Published: 2026-10-20T20:00:00+07:00 - Author: PR Newswire | | _Five studies to be presented, with key research examining AI-based biomarker assessment and tumor microenvironment analysis in breast, lung and pancreatic cancers_ SEOUL, South Korea, Oct. 20, 2026 /PRNewswire/ — Lunit (KRX: 328130), a leading provider of AI for cancer diagnostics and precision oncology, today announced that five studies involving its AI-powered pathology platform, Lunit SCOPE, will be presented at the European Society for Medical Oncology (ESMO) Congress 2026, taking place October 23–27 in Madrid, Spain. [⌊Lunit to Present Five Studies at ESMO 2026⌉⌊Lunit to Present Five Studies at ESMO 2026⌉[ Lunit to Present Five Studies at ESMO 2026 The studies highlight how AI-powered quantitative pathology analysis can help researchers examine cancer biomarkers and tumor tissue characteristics across different cancer types. By generating detailed measurements from pathology images, Lunit SCOPE supports research into the biological and clinical significance of tumor features. Among the five studies, three highlight applications of AI-powered pathology in breast, lung, and pancreatic cancer research. The first study is part of the AIforHER project, led by France’s Institut de Cancérologie de l’Ouest (ICO). The project aims to develop and evaluate AI-powered solutions for more precise HER2 assessment in breast cancer. Accurate HER2 classification has become increasingly important as HER2-targeted therapies expand to patients with lower levels of HER2 expression, including HER2-ultralow breast cancer. As part of the initiative, multiple AI solutions were evaluated under standardized conditions to assess their ability to classify HER2 expression levels. Lunit will present findings from Study A, the initial comparative evaluation, in a poster presentation at ESMO 2026. Following this evaluation, Lunit was selected as one of only two companies to advance to Study B and is currently participating in the follow-up study, which is evaluating the solution in a real-world clinical setting. The research explores the potential of AI-assisted HER2 assessment to support the identification of patients who may be eligible for HER2-targeted therapies, particularly in cases where subtle differences in HER2 expression are difficult to distinguish. In a large-scale Japanese study involving 993 patients with surgically resected non-small cell lung cancer (NSCLC), researchers compared PD-L1 tumor proportion scores (TPS) assessed independently by a pathologist and Lunit SCOPE PD-L1. The overall concordance rate was 73% (κ=0.58), with the lowest concordance observed in tumors classified as PD-L1 negative (TPS <1%) by the pathologist. Of the 211 tumors scored as TPS <1% by the pathologist but TPS ≥1% by AI, 204 (97%) were classified as having low PD-L1 expression (TPS 1–10%) by AI. The findings highlight differences between manual and AI-based PD-L1 assessment, particularly at low expression levels, while providing insights into areas that warrant further clinical investigation. In another study involving 181 patients with pancreatic ductal adenocarcinoma (PDAC), researchers used Lunit SCOPE IO to quantify tumor-stroma ratios and endothelial cell proportions in pathology images, examining their associations with KRAS mutation status and survival outcomes. While higher tumor-stroma ratios were associated with worse progression-free survival overall (HR=1.89, p=0.046), the opposite association was observed in patients with KRAS G12D-mutated tumors (HR=0.50, p=0.047). Higher endothelial cell proportions were also associated with favorable survival outcomes in tumors with lower stromal content, but not in those with higher stromal content. These findings highlight how the prognostic significance of tumor tissue characteristics can vary depending on molecular subtype and tissue context, suggesting the potential of AI-powered quantitative pathology to uncover complex relationships between tumor biology and patient outcomes. Together, these studies demonstrate how AI-powered quantitative pathology can support research across different cancer types, from examining biomarker assessment differences to investigating the relationship between tumor tissue characteristics and clinical outcomes. "AI is helping researchers uncover new insights from pathology images across different cancer types," said Brandon Suh, CEO of Lunit. "These studies reflect the diverse ways Lunit SCOPE can support cancer research. We will continue to support researchers and expand collaborations that advance our understanding of cancer biology and precision oncology."  _*Lunit SCOPE products are for research use only. Not for use in diagnostic procedures or decisions._ **Research Presentations at ESMO 2026:** 1. Poster Presentation [#287P / Oct. 25, 12:00–12:45 PM]: [Comparative evaluation of 7 artificial intelligence (AI) tools for HER2-low and ultralow scoring in breast cancer (BC)](https://cslide.ctimeetingtech.com/esmo2026/attendee/confcal_1/presentation/list?q=287P&c=pnr) 2. Poster Presentation [#313P / Oct. 25, 12:00–12:45 PM]: [A large-scale concordance comparing digital and manual PD-L1 scoring using surgical specimens of non-small cell lung cancer in the LC-SCRUM-Advantage/MRD study](https://cslide.ctimeetingtech.com/esmo2026/attendee/confcal_1/presentation/list?q=313p&c=pnr) 3. Poster Presentation [#322P / Oct. 25, 12:00–12:45 PM]: [AI-driven stromal profiling in PDAC: Context-dependent endothelial cell prognosis and KRAS subtype-specific paradoxes](https://cslide.ctimeetingtech.com/esmo2026/attendee/confcal_1/presentation/list?q=322P) 4. Poster Presentation [#346P / Oct. 25, 12:00–12:45 PM]: [Tertiary lymphoid structures (TLS) add prognostic value beyond tumor-infiltrating lymphocyte (TIL) density in patients treated with immune checkpoint inhibitor (ICI)-based therapies: A multi-institutional pan-cancer analysis](https://cslide.ctimeetingtech.com/esmo2026/attendee/confcal_1/presentation/list?q=346P) 5. Poster Presentation [#3810P / Oct. 26, 12:00–12:45 PM]: [Artificial intelligence-based endothelial cell profiling reveals a prognostic signature in the tumor microenvironment of small-cell lung cancer](https://cslide.ctimeetingtech.com/esmo2026/attendee/confcal_1/presentation/list?q=3810P) **About** **Lunit** Founded in 2013, Lunit (KRX: 328130) is a global leader on a mission to conquer cancer through AI. Our clinically validated solutions span medical imaging, breast health, and biomarker analysis, empowering earlier detection, smarter treatment decisions, and more precise outcomes across the cancer care continuum. Lunit offers a comprehensive suite spanning risk prediction and early detection to precision oncology. Our FDA-cleared Lunit INSIGHT Breast Suite and breast health solutions support cancer screening in thousands of medical institutions worldwide, while the Lunit SCOPE platform is used in research partnership with global pharma and laboratory leaders for biomarker research, and companion diagnostic development. Trusted by over 10,000 sites in more than 65 countries, Lunit combines deep medical expertise with continuously evolving datasets to deliver measurable impact for patients, clinicians, and researchers alike. Headquartered in Seoul with global offices, Lunit is driving the worldwide fight against cancer. Learn more at [lunit.io](https://www.lunit.io/en/). --- | This article was produced by Cision PR Newswire, our trusted news partner. The views expressed and the content presented here are solely those of the author and may not fully reflect the opinions of Thailand Business News. | --- **Read the original article :** [Lunit Highlights AI-Powered Pathology Insights Across Cancer Types at ESMO 2026 ](http://www.prnasia.com/story/archive/5076420_CN76420_0?rand=184833)