PathAI Publications

AI-powered Approaches Accurately Predict t(11;14) Positive Multiple Myeloma from H&E-stained Histologic Sections by Identifying Regions Demonstrating Lymphoplasmacytic Cytology

Written by Admin | Apr 25, 2025 4:00:00 AM

Study Background

Venetoclax, a highly selective oral BCL-2 inhibitor, has demonstrated efficacy in patients with multiple myeloma (MM) harboring a t(11;14)
translocation, which is present in 16-24% of patients

MM cells harboring t(11;14) translocation are known to exhibit a distinct lymphoplasmacytoid morphology, in which plasma cell morphology resembles that of lymphocytes

Fluorescence in situ hybridization (FISH) is the main method to determine t(11;14) status in pathology specimens. However, FISH requires significant quantities of bone marrow tissue or aspirate, requires the use of a separate slide than the routine hematoxylin and eosin (H&E) stain, and is low-throughput

Herein, we 1) describe an artificial intelligence (AI)-based model that accurately predicts t(11;14) status from routine H&E-stained MM whole slide images (WSIs), and 2) demonstrate that the biological signal underlying the model predictions is driven by regions containing the lymphoplasmacytic phenotype of t(11;14) positive MM cells

 

Conference

AACR 2025

Partner

AbbVie

View Poster