Grant: Master's Award: Canada Graduate Scholarships
University of Calgary
$17,500.00
Using a magnetic-resonance imaging-based radiomics approach to predict molecular genetics of meningiomas
EF 2023-24
Résumé
Meningiomas are the most common primary brain tumors in adults. Although a large percentage are classified as benign, the more aggressive tumors carry a significant morbidity and mortality burden. The routine histopathological diagnosis of meningiomas is falling out of favor with the advent of molecular-based classification schemes. It is important to identify genetic alterations in meningiomas earlier for better patient-specific treatment strategies. However, performing molecular analysis is costly and difficult for resource-challenged centers, even in developed nations. Preoperative tools to identify the aggressiveness of meningiomas can help in surgical planning and post-operative management. Radiomics is a promising tool for this purpose. Magnetic-resonance imaging (MRI) contains a plethora of radiological data that is invisible to the naked eye; however, large amounts of MRI data can be extracted by machine learning. Thousands of features can be identified in a single MRI, which can then be correlated with clinical presentation, histopathological grade, molecular genetics, surgical anatomy, and potential for disease recurrence. We will develop a machine learning model to extract features from MR images of meningioma tumors that can predict genetic alterations. The goal of this project will be to identify imaging predictors of molecular classification of meningiomas. We expect that MRI data can provide adequate feature extraction to predict tumor biology and disease recurrence. This is the first study to interrogate machine learning models in predicting meningioma genomic classification and this will enhance surgical planning and patient-specific treatment paradigms.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database
Tel que publié
Id
506159
Name
Karmur Brij S
Region
Alberta
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Using a magnetic-resonance imaging-based radiomics approach to predict molecular genetics of meningiomas
Programtype2
Studentship Programs
Orgnameinp2
University of Calgary
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Convolutional Neural Networks; Deep Learning; Machine Learning; Meningioma; Molecular Diagnostics; Mri; Radiogenomics; Radiomics
Abstract
Meningiomas are the most common primary brain tumors in adults. Although a large percentage are classified as benign, the more aggressive tumors carry a significant morbidity and mortality burden. The routine histopathological diagnosis of meningiomas is falling out of favor with the advent of molecular-based classification schemes. It is important to identify genetic alterations in meningiomas earlier for better patient-specific treatment strategies. However, performing molecular analysis is costly and difficult for resource-challenged centers, even in developed nations. Preoperative tools to identify the aggressiveness of meningiomas can help in surgical planning and post-operative management. Radiomics is a promising tool for this purpose. Magnetic-resonance imaging (MRI) contains a plethora of radiological data that is invisible to the naked eye; however, large amounts of MRI data can be extracted by machine learning. Thousands of features can be identified in a single MRI, which can then be correlated with clinical presentation, histopathological grade, molecular genetics, surgical anatomy, and potential for disease recurrence. We will develop a machine learning model to extract features from MR images of meningioma tumors that can predict genetic alterations. The goal of this project will be to identify imaging predictors of molecular classification of meningiomas. We expect that MRI data can provide adequate feature extraction to predict tumor biology and disease recurrence. This is the first study to interrogate machine learning models in predicting meningioma genomic classification and this will enhance surgical planning and patient-specific treatment paradigms.
Competitiondate
202312
Approvedterm2
1 yr 0 mth
Pinamesdelim
Karmur, Brij S
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~