The study finds the solution achieved 83.5% overall concordance rate with expert interpretations.
A new study published in Laboratory Investigation evaluating an AI-powered pathology solution, Lunit Scope HER2, found high concordance with pathologist assessments in HER2 immunohistochemistry interpretation for advanced biliary tract cancer.
The retrospective study examined Lunit Scopre HER2’s consistency compared to pathologists using light microscopy and digital pathology. Conducted by investigators at CHA Bundang Medical Center and CHA Ilsan Medical Center in South Korea with Lunit researchers, the analysis included 309 HER2-stained whole-slide images from 291 advanced biliary tract cancer patients treated between 2019 and 2022.
Three board-certified pathologists independently evaluated HER2 expression, with their assessments compared against AI-based scoring using Lunit Scope HER2. Complete agreement among pathologists was observed in 62.1% of light microscopy assessments and 63.4% of digital pathology assessments, reflecting inherent variability in HER2 interpretation.
Against this background, Lunit Scope HER2 achieved an overall concordance rate of 83.5% with pathologist-defined ground truth, indicating close alignment with expert-reviewed interpretations.
Addressing Interpretation Challenges
The findings highlight recognized challenges of HER2 interpretation in biliary tract cancer, particularly in cases with low or borderline expression where variability among pathologists was more pronounced. Biliary tract cancer is a rare and aggressive cancer where accurate biomarker evaluation is critical for identifying patients who may benefit from HER2-targeted therapies.
“Accurate and consistent biomarker assessment is critical as precision oncology continues to expand into more complex and less common cancers,” says Brandon Suh, CEO of Lunit, in a release. “This study shows that AI-powered pathology can closely align with expert pathologists in HER2 interpretation for biliary tract cancer, an area where variability has been a longstanding challenge.”
The study suggests AI-based analysis may help support more consistent interpretation when integrated into digital pathology workflows, according to the researchers.
Clinical Implications
The research addresses a key challenge in precision oncology where consistent biomarker assessment is essential for treatment decisions. HER2 testing variability has been a recognized issue in biliary tract cancer, making standardized interpretation tools potentially valuable for clinical practice.
“We believe AI can play a meaningful role in supporting more standardized and reproducible decision-making as new targeted therapies emerge,” says Suh in a release.
ID 161334722 © Andrei Dodonov | Dreamstime.com
