Lunit SCOPE IO assesses a patient's cancer tissue slide image by analyzing the distribution of tumor-infiltrating lymphocytes (TILs)—one of the representative immunocytes that fight cancer cells. Based on the spatial distribution of TILs and cancer cells in the tumor microenvironment, Lunit SCOPE IO identifies the sample as one of three immune phenotypes: inflamed, immune-excluded, or immune-desert.

One of the studies to be presented investigates the correlation between AI-powered immune phenotype and real-world outcomes in liver cancer.

Anti-PD-(L)1 monotherapy or combination with bevacizumab or ipilimumab are approved treatment options for hepatocellular carcinoma (HCC; liver cancer). However, not all patients benefit from immunotherapy regimens, raising a need for biomarkers to predict treatment outcomes. Lunit SCOPE IO was used to assess the correlation between the AI solution's immune phenotype and actual outcomes from two separate immunotherapy regimens across 177 HCC patient cases.

Findings showed progression-free survival (PFS) of the nivolumab or nivolumab plus ipilimumab (Niv+/-Ipi) regimen to be significantly longer in patients with high inflamed scores—the proportion of area with a high intra-tumoral TIL infiltration. Thus, results showed that the inflamed score, as evaluated by Lunit SCOPE IO, can be used as a biomarker to predict outcomes of Niv+/-Ipi treatment.

Lunit will also present findings from a study assessing the clinical significance of Lunit SCOPE IO for the prediction of prognosis in stage II-III colon cancer patients treated with surgery and adjuvant chemotherapy.

Across 289 patients included in the study, TIL quantification evaluated by Lunit SCOPE IO showed clinically meaningful correlations with microsatellite instability status, stage of cancer progression, and the occurrence of perineural invasion—factors known to be associated with the prognosis of colon cancer. Furthermore, patients with low TIL quantification were more likely to exhibit recurrence.

"TIL quantification is important in the prediction of prognosis in colon cancer, but assessment usually requires additional tissue processing and interpretational efforts," explained Chan-Young Ock, Chief Medical Officer of Lunit's Oncology Group. "This study shows that AI-powered TIL analysis using only an H&E-stained whole-slide image can provide prognostic information in stage II-III colon cancer patients in a practical manner."

"Our presentations at this year's ASCO GI continue to demonstrate the credibility of Lunit SCOPE IO as a practical biomarker as we expand the range of our research across all cancer types," said Brandon Suh, CEO of Lunit. "We will expand our research and commercial access programs for Lunit SCOPE throughout this year to provide optimized treatment to cancer patients around the world."

Lunit at ASCO GI 2023: Poster Presentations