Lunit reported results of a South Korean clinical study showing how its Lunit SCOPE IO tissue analytics software helped predict the prognosis of patients with stage II-III colon cancer who were treated with curative surgery and adjuvant therapy.
Lunit SCOPE IO is a deep learning-based tumor-infiltrating lymphocyte (TIL) analyzer comprised of two complementary learning models developed for cell detection and tissue segmentation. It analyzes the tumor microenvironment based on hematoxylin and eosin analysis, a common laboratory technique used in research to provide a detailed view of tissue architecture, and provides AI-based predictive clinical outcome information.
The retrospective study, published in NPJ Precision Oncology, was conducted by researchers at the Seoul National University Bundang Hospital, the Seoul National University of Medicine, and Lunit. The researchers evaluated the clinical utility of AI-powered spatial TIL analysis for predicting the prognosis of 289 patients with stage II-III colon cancer after undergoing treatment.
Patients with confirmed recurrences showed significantly lower stromal TIL densities compared to those with no recurrence. The study also identified distinct high-, medium-, and low-risk groups. The groups were predictive of recurrence-free survival time and were independently associated with clinical outcomes after adjusting for other clinical factors.
