Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Master's Award: Canada Graduate Scholarships

University of Toronto

$17,500.00

Deep Learning Approaches to Deciphering Intra-Tumoural Heterogeneity for Precision Medicine

EF 2020-21

Résumé
Cancer therapeutics for aggressive cancers such as glioblastoma (GBM) based on traditional models of cancer have failed to yield durable and improved outcomes in clinical trials. One recent explanation for these previous failures is that while we often think of a patient's tumour as being a homogenous mass of identical cancer cells, there are in fact a number of tumour subclones within each cancer tumour that respond differently to our conventional and traditional therapies. This means that existing treatments may not equally target all tumour cells and allow resistant subclones to survive and drive disease recurrence and progression. To address this, this project will aim to harness expertise in Artificial Intelligence (AI) and molecular profiling to explore if AI technology can help automate the detection of biologically distinct tumour subregions and understand the biological significance of these computer defined regions. First, previously trained AI tools and dissection technology will be used to determine if computer defined regions of variability do indeed show unique biological activity that may be driving partial responses to therapy. Secondly, the degree of morphological variation within selected tumours will be examined to determine if AI-defined variation predicts therapeutic response and/or success within our dataset. If successful, this project will help to define areas within cancer tumours that should be distinctly targeted therapeutically. Routine use of this tool will help define and characterize distinct tumour subpopulations, as well as aid in designing personalized drug cocktails to target a larger fraction of the tumours' true biology. Ultimately, this could provide more durable responses for patients.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database

Tel que publié

Id
449770
Name
Dent Anglin
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Deep Learning Approaches to Deciphering Intra-Tumoural Heterogeneity for Precision Medicine
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Brain Tumors; Cancer; Computational Pathology; Deep Learning; Diagnostics; Image Analysis; Machine Learning; Personalized Medicine; Proteomics
Abstract
Cancer therapeutics for aggressive cancers such as glioblastoma (GBM) based on traditional models of cancer have failed to yield durable and improved outcomes in clinical trials. One recent explanation for these previous failures is that while we often think of a patient's tumour as being a homogenous mass of identical cancer cells, there are in fact a number of tumour subclones within each cancer tumour that respond differently to our conventional and traditional therapies. This means that existing treatments may not equally target all tumour cells and allow resistant subclones to survive and drive disease recurrence and progression. To address this, this project will aim to harness expertise in Artificial Intelligence (AI) and molecular profiling to explore if AI technology can help automate the detection of biologically distinct tumour subregions and understand the biological significance of these computer defined regions. First, previously trained AI tools and dissection technology will be used to determine if computer defined regions of variability do indeed show unique biological activity that may be driving partial responses to therapy. Secondly, the degree of morphological variation within selected tumours will be examined to determine if AI-defined variation predicts therapeutic response and/or success within our dataset. If successful, this project will help to define areas within cancer tumours that should be distinctly targeted therapeutically. Routine use of this tool will help define and characterize distinct tumour subpopulations, as well as aid in designing personalized drug cocktails to target a larger fraction of the tumours' true biology. Ultimately, this could provide more durable responses for patients.
Competitiondate
202012
Approvedterm2
1 yr 0 mth
Pinamesdelim
Dent, Anglin
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~