Nucleai, an AI-powered spatial biology company with a mission to transform drug development and clinical treatment decisions by unlocking the power of pathology data, today announced that it will share new data at the American Society of Clinical Oncology (ASCO) 2022 Annual Meeting in an online publication on an exploratory analysis of a phase 2 study to find new pathology-based predictive biomarkers for DLBCL, the most common type of Non-Hodgkin’s lymphoma. The meeting is taking place from June 3 to June 7 at McCormick Place in Chicago.

Up to 40% of patients with DLBCL, which accounts for 30-40% of cases, have relapsed and/or refractory (R/R) disease, despite recent improvements in response and survival with standard of care treatment. A phase 2 study evaluated the efficacy of naratuximab emtansine, an anti-CD37 ADC, in combination with rituximab, in patients with R/R DLBCL. Deep learning models were used to extract spatial features from digitized slides stained with CD37 and CD20. Their potential as a pathology-based biomarker predictive of response was evaluated.