New findings demonstrate the clinical efficacy of AI-powered tissue analysis as a guide in cancer treatment, according to medical AI provider Lunit. The findings will be presented at the 2022 ASCO Annual Meeting, to be held from June 3 to 7. This year's ASCO meeting will showcase the largest number of studies by Lunit, including seven poster presentations and four online publications.

One of the poster presentations by Lunit elaborates on the validation of the Inflamed Immune Phenotype (IIP) as a practical biomarker to guide immune checkpoint inhibitor (ICI) treatment. The IIP is assessed by Lunit SCOPE IO, Lunit's AI-powered immune phenotype analyzer, from H&E slide images.

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

Findings upon evaluation showed that the Inflamed Immune Phenotype (IIP) may represent a practical, clinically actionable biomarker predictive of favorable ICI treatment outcomes across more than 16 primary cancer types. This study included more than 1,800 samples paired with real-world clinical outcomes data.

"Patient outcomes after ICI treatment were analyzed with specific indicators including objective response rate and progression-free survival. This study is especially noteworthy in that it demonstrates the utility of the AI-assessed IIP as a biomarker across diverse cancer patient populations, including those with PD-L1 negative, MSS/TMB-low tumors, in whom predictive biomarkers are urgently needed," said Chan-Young Ock, Chief Medical Officer at Lunit.

Lunit will also deliver a presentation on Lunit SCOPE PD-L1 TPS, the company's AI-powered PD-L1 tumor proportion score (TPS) analyzer.

"While PD-L1 expression is the standard biomarker for advanced non-small cell lung cancer (NSCLC), manual evaluation of PD-L1 TPS by pathologists has practical limitations including interobserver variation and lengthy time demands," said Kyunghyun Paeng, Chief Product Officer of Lunit. "Through a randomized trial, this study aimed to test the benefit of our AI-based PD-L1 TPS analyzer in assisting pathologists' evaluation in terms of accuracy and evaluation time."