{"id":2304,"date":"2025-10-13T00:00:29","date_gmt":"2025-10-13T00:00:29","guid":{"rendered":"https:\/\/www.lunit.io\/en\/?post_type=media-hub&p=2304"},"modified":"2026-04-18T10:17:01","modified_gmt":"2026-04-18T01:17:01","slug":"lunit-ai-predicts-immunotherapy-outcome-in-colorectal-kidney-and-lung-cancer-at-esmo-2025","status":"publish","type":"media-hub","link":"https:\/\/www.lunit.io\/en\/media-hub\/lunit-ai-predicts-immunotherapy-outcome-in-colorectal-kidney-and-lung-cancer-at-esmo-2025\/","title":{"rendered":"Lunit AI Predicts Immunotherapy Outcome in Colorectal, Kidney, and Lung Cancer at ESMO 2025"},"content":{"rendered":"

AI-powered histopathology demonstrates predictive value for immunotherapy outcomes in pMMR mCRC, advanced ccRCC, and NSCLC with data featured in both oral and poster presentations<\/em><\/strong><\/p>\n

SEOUL, South Korea, October 13, 2025<\/strong>\u00a0\u2014 Lunit (KRX:328130.KQ), a leading provider of AI for cancer diagnostics and therapeutics, today announced the presentation of three studies at the European Society for Medical Oncology (ESMO) Congress 2025, taking place October 17\u201321 in Berlin, Germany. All three studies highlight how Lunit\u2019s AI pathology solution, Lunit SCOPE IO\u00ae, can identify biomarkers that predict response to immune checkpoint inhibitors (ICIs), offering new potential to guide more effective and personalized cancer treatment.<\/p>\n

Among these, the first study, selected for oral presentation, was conducted in collaboration with Chiara Cremolini, MD, PhD, Professor of Medical Oncology at the University of Pisa, Italy. Researchers applied Lunit SCOPE IO to pre-treatment H&E slides from patients with proficient mismatch repair (pMMR) metastatic colorectal cancer (mCRC) enrolled in the AtezoTRIBE and AVETRIC trials. The AI quantified multiple cell types within the tumor microenvironment, generating a biomarker that stratified patients into \u201cbiomarker-high\u201d and \u201cbiomarker-low\u201d groups.<\/p>\n

In the AtezoTRIBE trial, biomarker-high patients treated with atezolizumab plus FOLFOXIRI\/bevacizumab showed significantly improved progression-free survival (PFS) and overall survival (OS) compared to biomarker-low patients, while no such benefit was observed in the control arm. Validation in the AVETRIC cohort confirmed improved survival outcomes for biomarker-high patients receiving ICI-based therapy, with better PFS and OS compared to biomarker-low patients. These results suggest that an AI-derived tumor microenvironment biomarker could help identify patients with pMMR mCRC who are most likely to benefit from immunotherapy combinations\u2014an urgent unmet need in this population.<\/p>\n

A collaborative study with Yonsei University College of Medicine, Korea, evaluated whether AI-defined immune phenotypes (IP) could predict outcomes in patients with advanced clear cell renal cell carcinoma (ccRCC) treated with either nivolumab plus ipilimumab (NIVO+IPI) or sunitinib (SUN). Using Lunit SCOPE IO, tumors were classified as inflamed or non-inflamed, based on the density and spatial distribution of tumor-infiltrating lymphocytes.<\/p>\n

Patients with inflamed tumors treated with NIVO+IPI demonstrated significantly longer PFS, OS, and higher response rates (60.5% vs. 23.2%) compared to those with non-inflamed tumors. No such benefit was observed in the SUN arm. Findings were validated in an independent ccRCC cohort and aligned with inflamed gene expression signatures from The Cancer Genome Atlas, supporting AI-based immune phenotyping as a promising biomarker to guide treatment selection between immunotherapy combinations and targeted therapies in first-line treatment for ccRCC.<\/p>\n

The third study, conducted in collaboration with the National Cancer Center Hospital East (NCCHE) Japan, further validated the predictive power of Lunit SCOPE IO for ICI treatment response in non-small cell lung cancer (NSCLC) patients. In this multicenter prospective study, tumors classified as inflamed showed significantly better responses and longer survival with ICI therapy compared to non-inflamed tumors, a difference not observed among patients treated with cytotoxic chemotherapy. This result strengthens the evidence supporting Lunit SCOPE IO as a predictive biomarker for immunotherapy benefit in NSCLC.<\/p>\n

\u201cAt ESMO 2025, we are demonstrating how AI can unlock predictive biomarkers directly from routine pathology slides,\u201d said Brandon Suh, CEO of Lunit. \u201cThese findings show the potential of Lunit SCOPE IO to help identify patients who will truly benefit from immunotherapy\u2014whether in colorectal or kidney cancer\u2014and to guide treatment strategies that can make cancer care more precise and effective.\u201d<\/p>\n

Lunit\u2019s Featured Presentations at ESMO 2025<\/strong><\/p>\n