Canada Spends Logo

Explorez notre analyse du budget 2026

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

University of Toronto

$27,000.00

Deep Learning-Driven Morphological Profiling of Esophageal Adenocarcinoma

EF 2025-26

Résumé
Esophageal cancer is a serious malignant cancer and a leading cause of cancer-related death. In the Western world, the most common type is esophageal adenocarcinoma (EAC), and its incidence rate has been increasing in recent years. To diagnose and guide treatment decisions, pathologists must carefully examine tumor tissue under a microscope. The process of identifying and classifying tissue structures is very labor-intensive, relies on specialist expertise, and can be prone to human-errors. Today, new technologies make it possible to convert tissue samples into high-resolution digital images, and advances in deep learning offer an opportunity to analyze these images more efficiently and accurately. This project aims to develop and validate a deep learning model that can predict specific tissue classifications from whole-slide images of tumor samples. The model will identify ten types of tissue structures and assess regression grading, which indicates how well the tissue responded to initial treatment. These structural predictions are helpful because they provide insights on how advanced the tumor is and how it may behave or progress in the future. A key part of this project is close collaboration with pathologists, who will help confirm the accuracy of the model’s predictions and provide feedback to guide improvements. By combining expert knowledge with computational tools, this work has the potential to make EAC diagnosis and prognosis more consistent and efficient, while contributing to the expanding field of digital pathology.
Programme
Master's Award: Canada Graduate Research Scholarships - Master's program
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database

Tel que publié

Id
573302
Name
Wan Ellie
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Deep Learning-Driven Morphological Profiling of Esophageal Adenocarcinoma
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$27,000
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Research Scholarships - Master's program
Keyworddelim
Artificial Intelligence; Cancer Diagnostics; Clinical Impact; Deep Learning; Digital Pathology; Esophageal Adenocarcinoma; Histopathology; Pathomic; Tumor Morphology; Whole Slide Imaging
Abstract
Esophageal cancer is a serious malignant cancer and a leading cause of cancer-related death. In the Western world, the most common type is esophageal adenocarcinoma (EAC), and its incidence rate has been increasing in recent years. To diagnose and guide treatment decisions, pathologists must carefully examine tumor tissue under a microscope. The process of identifying and classifying tissue structures is very labor-intensive, relies on specialist expertise, and can be prone to human-errors. Today, new technologies make it possible to convert tissue samples into high-resolution digital images, and advances in deep learning offer an opportunity to analyze these images more efficiently and accurately. This project aims to develop and validate a deep learning model that can predict specific tissue classifications from whole-slide images of tumor samples. The model will identify ten types of tissue structures and assess regression grading, which indicates how well the tissue responded to initial treatment. These structural predictions are helpful because they provide insights on how advanced the tumor is and how it may behave or progress in the future. A key part of this project is close collaboration with pathologists, who will help confirm the accuracy of the model’s predictions and provide feedback to guide improvements. By combining expert knowledge with computational tools, this work has the potential to make EAC diagnosis and prognosis more consistent and efficient, while contributing to the expanding field of digital pathology.
Competitiondate
202512
Approvedterm2
1 yr 0 mth
Pinamesdelim
Wan, Ellie
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $27,000~ $0~