Predicting response to naratuximab emtansine, an anti-CD37 antibody-drug conjugate (ADC), in combination with rituximab in diffuse Large B Cell Lymphoma (DLBCL), by analyzing the spatial arrangement of CD37 and CD20 positive cells using deep learning

Poster presented at the 34th EORTC-NCI-AACR Symposium, ENA 2022

Anna Pokorska-Bocci¹, Sandrine Micallef¹, Mariola Dymkowska¹, Yuval Gabay², Roman Gluskin², Avi Laniado², Efrat Dicker², Amit Bart², Tomer Dicker², Ifat Rotbein², Albert Achtenberg², Ori Zelichov²

​¹Debiopharm International SA, Lausanne, Switzerland,
²Nucleai, Tel Aviv, Israel

Introduction

DLBCL is the most common type of Non-Hodgkin’s lymphoma, accounting for 30-40% of cases. ​
Despite improvements in survival with standard of care treatment, up to 40% of patients have relapsed and/or refractory (R/R) disease. ​
A Phase 2 Study (NCT02564744) evaluated the efficacy of naratuximab emtansine, an anti-CD37 ADC, in combination with rituximab, in 80 patients with R/R DLBCL. ​
We performed an exploratory, retrospective analysis of the study to find pathology-based biomarkers predictive of response. ​
Deep learning (DL) models were used to extract spatial features from whole slide images (WSI) stained with CD37 and CD20, and their predictive role was evaluated.