Peer-Reviewed Publication
Cancers (Basel)2026;18(12)June 10, 2026Journal Article
Spatial Biomarker Deep Learning Model Predicts Response to PI3K Inhibition in Head and Neck Cancer.
Antoine Desilets1,2, Minh Tri Le2,3, Catalina Moreno2, Justin Lucas4, Alexandre Pellan Cheng2,5, Orit Matcovitch-Natan6, Amit Bart6, Avi Laniado6, Meir Azulay6, Ettai Markovits6, Jennifer Kaplan Kerner6, Amit Gutwillig6, Hadar Yehezkeli6, Lisa F Licitra7, Sunny Lu4, Kevin Dreyer4, Ying Pan4, Nanhai He4, Archie Tse4, Sandrine Faivre8, Denis Soulières1,2
1Hematology-Oncology Service, Department of Medicine, Centre Hospitalier de l'Université de Montréal (CHUM), Montreal, QC H2X 0A9, Canada.
2Cancer Axis, Centre de Recherche du CHUM (CRCHUM), Montreal, QC H2X 0A9, Canada.
3Department of Pathology, Centre Hospitalier de l'Université de Montréal (CHUM), Montreal, QC H2X 0A9, Canada.
4Adlai Nortye, North Brunswick, NJ 08902, USA.
5Department of Systems Engineering, École de Technologie Supérieure, Montreal, QC H3C 1K3, Canada.
6Nucleai, Tel Aviv 6744840, Israel.
7Head and Neck Cancer Medical Oncology 3 Unit, Fondazione IRCCS Istituto Nazionale dei Tumori, Department of Oncology and Hemato-Oncology, University of Milan, 20122 Milan, Italy.
8Hôpital St-Louis, 75010 Paris, France.
Abstract
Background: Buparlisib, combined with paclitaxel, improved survival in BERIL-1 trial patients with recurrent/metastatic head and neck squamous cell carcinoma (R/M HNSCC). However, predictive biomarkers of benefit remain undefined. Objective: To evaluate whether spatial biomarkers extracted from hematoxylin and eosin (H&E) slides using artificial intelligence (AI) can predict overall survival benef…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans