A new study has demonstrated the value of Lunit’s AI-powered pathology tools in improving human epidermal growth factor receptor 2 (HER2) biomarker evaluation in metastatic colorectal cancer (mCRC) patients undergoing HER2-targeted therapy.
The South Korean AI company’s SCOPE HER2 AI model was applied to assess HER2 status and tumour microenvironment (TME) variables among 30 patients involved in the Phase II TRIUMPH trial. The data was published in the Journal of Clinical Oncology Precision Oncology, with the TRIUMPH trial conducted in collaboration with Japan's National Cancer Center Hospital East (NCCHE).
Lunit’s model demonstrated 86.7% accuracy compared to pathologist assessments for HER2 immunohistochemistry (IHC) and achieved a 100% accuracy in identifying HER2 IHC in 3+ cases (HER2-positive tumours).
According to Lunit, patients identified by the AI model as having a high proportion of HER2 IHC 3+ tumour cells exhibited better clinical outcomes than those identified through traditional HER2 evaluation methods. The objective response rate (ORR) with Lunit’s model was 42.1% versus 26.7%, progression-free survival (PFS) 4.4 months versus 1.4 months, and overall survival (OS) 16.5 months versus 4.1 months.
Lunit SCOPE IO was used in the study to perform detailed tumour microenvironment (TME) profiling, including lymphocyte and macrophage densities. Among AI-H3-high patients, those with low stromal TME density (TME-low) achieved the most favourable outcomes, with 57.1% ORR; 5.6-month PFS; and 26-month OS.
HER-2-targeted therapy uses monoclonal antibodies (mAb) or tyrosine kinase inhibitors to stop the growth of HER2-positive cancer cells.
Lunit CEO Brandon Suh commented: “The findings from this study demonstrate how Lunit’s AI-powered solutions, Lunit SCOPE HER2 and Lunit SCOPE IO, can provide clinicians with actionable insights to refine treatment strategies.
“Our continued collaboration with NCCHE showcases the transformative potential of AI in precision oncology.”
"The ability to more precisely stratify patients will lead to more personalised treatment options, improving outcomes for patients with HER2-positive metastatic colorectal cancer,” added NCCHE deputy director Dr Takayuki Yoshino and principal investigator of the research.
Used to predict immunotherapy treatment outcomes in rare tumours, Lunit’s SCOPE IO system was found to cut the risk of disease progression or death by as much as 51%.
