Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Master's Award: Canada Graduate Research Scholarships - Master's program

McGill University

$27,000.00

Artificial Intelligence Powered Pathologic Response Assessment in Non-Small Cell Lung Cancer Neoadjuvant Therapy

FY 2025-26

Summary
Current manual assessment of Major Pathologic Response (MPR) in non-small cell lung cancer is subjective, time-consuming, and difficult to standardize. We propose an AI system to automate this evaluation using H&E whole-slide images. By benchmarking Convolutional Neural Networks against advanced Vision Transformers and self-supervised foundation models, our approach will generate precise, continuous estimates of residual tumor rather than simple binary classifications. This automated framework aims to standardize response assessment, overcoming the limitations of manual pathology to improve prognostic stratification and clinical decision-making.
Program
Master's Award: Canada Graduate Research Scholarships - Master's program
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database

As published

Id
573228
Name
Dai David
Region
Québec
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Artificial Intelligence Powered Pathologic Response Assessment in Non-Small Cell Lung Cancer Neoadjuvant Therapy
Programtype2
Studentship Programs
Orgnameinp2
McGill University
Cihramount2
$27,000
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Research Scholarships - Master's program
Keyworddelim
Artificial Intelligence; Deep Learning; Digital Pathology; Foundation Model; Lung Cancer; Neoadjuvant Therapy; Pathologic Response; Residual Viable Tumor; Vision Transformer; Whole Slide Imaging
Abstract
Current manual assessment of Major Pathologic Response (MPR) in non-small cell lung cancer is subjective, time-consuming, and difficult to standardize. We propose an AI system to automate this evaluation using H&E whole-slide images. By benchmarking Convolutional Neural Networks against advanced Vision Transformers and self-supervised foundation models, our approach will generate precise, continuous estimates of residual tumor rather than simple binary classifications. This automated framework aims to standardize response assessment, overcoming the limitations of manual pathology to improve prognostic stratification and clinical decision-making.
Competitiondate
202512
Approvedterm2
1 yr 0 mth
Pinamesdelim
Dai, David
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $27,000~ $0~