AI-Powered Pathology Solutions Accurately Predict Outcomes for HER2-Targeted Therapy in Metastatic CRC

The study, published in the Journal of Clinical Oncology, demonstrates how Lunit’s (Seoul, South Korea) advanced AI pathology solutions, Lunit SCOPE HER2 and Lunit SCOPE IO, can significantly improve the evaluation of the HER2 biomarker and predict clinical outcomes in patients with metastatic colorectal cancer (mCRC) undergoing HER2-targeted therapies. This study presented results from the TRIUMPH phase II clinical trial, which involved 30 patients with HER2-positive mCRC treated with a dual HER2-targeted therapy regimen that included Trastuzumab and Pertuzumab. Lunit's AI technology was used to assess both HER2 status and various TME factors, with notable findings. Lunit SCOPE HER2 achieved an impressive 86.7% accuracy when compared to pathologist evaluations of HER2 immunohistochemistry (IHC), and it reached 100% accuracy in identifying HER2 IHC 3+ cases.

The AI model identified patients with a high proportion of HER2 IHC 3+ staining tumor cells (AI-H3-high, >50%), who showed better clinical outcomes than those identified using conventional HER2 assessment methods. The study also utilized Lunit SCOPE IO for detailed TME profiling, analyzing lymphocyte, macrophage, and fibroblast densities. Among AI-H3-high patients, those with low stromal TME density (TME-low) experienced the most favorable outcomes. These results underscore the potential of AI-driven pathology tools to revolutionize precision oncology. By providing a more accurate and detailed analysis of HER2 status and TME characteristics, Lunit’s solutions offer a better method for patient stratification and predicting responses to HER2-targeted therapies that are currently available or under development. This capability may lead to more personalized treatment plans, ultimately improving outcomes for mCRC patients and potentially for other cancers with HER2 amplification.

"This study underscores the potential of AI technology to redefine how we evaluate biomarkers and predict treatment responses," said Dr. Takayuki Yoshino, principal investigator of the research. "The ability to more precisely stratify patients will lead to more personalized treatment options, improving outcomes for patients with HER2-positive metastatic colorectal cancer."

"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," added Brandon Suh, CEO of Lunit.

Related Links:
Lunit