 |
AI-powered whole-slide analysis provides insights into treatment response beyond conventional HER2 classification
SEOUL, South Korea, Oct. 14, 2026 /PRNewswire/ — Lunit (KRX: 328130), a leading provider of AI for cancer diagnostics and precision oncology, today announced findings from a study published in Nature Medicine, in which its AI-powered pathology platform, Lunit SCOPE, identified an association between quantitative HER2 expression and treatment response in patients with HER2-positive advanced biliary tract cancer (BTC).
The study, led by researchers at Yonsei University College of Medicine, evaluated a four-drug combination as a potential first-line treatment for HER2-positive advanced BTC. Lunit researchers contributed as co-authors, conducting exploratory biomarker analyses using Lunit SCOPE to investigate how HER2 expression and tumor immune characteristics were associated with clinical outcomes.
BTC is an aggressive cancer with limited treatment options and poor prognosis. HER2 overexpression or amplification occurs in approximately 15% of BTC cases, but identifying patients who may derive greater benefit from HER2-targeted therapies remains an important clinical challenge.
The multicenter phase 1b/2 HERBOT trial enrolled 40 patients across 12 sites in South Korea to evaluate trastuzumab, a HER2-targeted therapy, combined with nivolumab, an immune checkpoint inhibitor, and gemcitabine and cisplatin chemotherapy. The regimen achieved an objective response rate (ORR) of 55% and a median progression-free survival (PFS) of 10.6 months, supporting further investigation of HER2-targeted therapy in the first-line setting.
Lunit SCOPE HER2 analyzed whole-slide pathology images to detect and classify individual tumor cells according to HER2 staining intensity, enabling quantitative measurement of the proportion of strongly HER2-expressing (HER2 3+) tumor cells across the analyzed tissue. Lunit SCOPE IO separately assessed the tumor immune microenvironment, classifying tumors into immune-inflamed, immune-excluded, and immune-desert phenotypes.
In the exploratory AI analysis, patients whose tumors contained at least 10% HER2 3+ cells had a significantly higher objective response rate of 80%, compared with 40% among those below the threshold (P=0.0138). A higher proportion of HER2 3+ tumor cells was also significantly associated with greater tumor shrinkage.
Conventional HER2 classification did not show a statistically significant difference in objective response rates between HER2 IHC 3+ and IHC 2+/ISH-positive groups. AI-powered whole-slide analysis, however, identified an association between quantitative HER2 3+ tumor cell proportions and treatment response, suggesting that this approach may provide additional information beyond conventional HER2 classification. Additionally, immune phenotype classification was also associated with the treatment response.
“AI-powered whole-slide analysis identified differences in quantitative HER2 expression associated with treatment response, providing insights beyond conventional HER2 classification,” said Professor Choong-kun Lee of Yonsei University College of Medicine, who led the study. “While further validation in larger patient populations is needed, these findings highlight the potential of AI-based tissue analysis to support future research into treatment response.”
“This study highlights how AI-powered pathology can help us look beyond conventional biomarker classifications to better understand differences in treatment response,” said Brandon Suh, CEO of Lunit. “We will continue to advance Lunit SCOPE to support more precise biomarker research and contribute to the development of personalized treatment strategies.”
* Lunit SCOPE products are for research use only. Not for use in diagnostic procedures or decisions.
###
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.
ข่าวที่เกี่ยวข้อง
- Wizstar Enables Scalable E-Commerce Video Production with AI-Powered Workflows
- Tesollo Expects Cumulative Robotic Hand and Gripper Sales to Surpass 1,000 Units in 2026
- Neurophet Honored with Two Awards at the BioSpectrum Asia Excellence Awards 2026
- xFusion at OCP 2026: When Cooling, Power, and Interconnect Converge for the Agentic Era
