Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Master's Award: Canada Graduate Scholarships

University of Ottawa

$17,500.00

Machine learning-based identification of diagnostic biomarkers in prostate cancer with intraductal carcinoma.

EF 2018-19

Résumé
Prostate cancer is the most commonly diagnosed cancer among Canadian men. When diagnosed with prostate cancer, patients are classified in different risk categories for recurrence of the cancer after treatment. This classification guides the type of treatment that the patient will receive after diagnosis. For example, a prostate cancer patient exhibiting a high risk of recurrence will typically receive a more aggressive treatment than one with a lower risk. These individualized treatment options result in a better prognosis of the disease. However, not all known risk factors of recurrence are currently used in prostate cancer recurrence risk stratification. The presence of tumour growth in the ducts of the prostate is one of those factors that increases the risk of recurrence. However, due to their small size, these tumour growths are often missed in tumour biopsies and patients are therefore not treated appropriately. In this project, I propose to use a technology named imaging mass spectrometry that allows the identification of molecules in very small regions of the prostate. The detection of these molecules can then be used to determine the presence of tumour growth in prostate ducts and provide patients with the appropriate treatment. I will also use a computational and statistical approach that will identify the set of molecules that provide the most accurate prediction of the presence of tumour growth in prostate cancer. The discovered molecules will make the diagnosis of prostate cancer more accurate and ensure that the treatment of patients is more tailored to their condition. Ultimately, my project will reduce prostate cancer recurrence and improve its survival rate.
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
406726
Name
Shahryari Fard Soroush
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Machine learning-based identification of diagnostic biomarkers in prostate cancer with intraductal carcinoma.
Programtype2
Studentship Programs
Orgnameinp2
University of Ottawa
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Bioinformatics; Biomarker; Imaging Mass Spectrometry; Intraductal Carcinoma; Machine Learning; Personalized Medicine; Prostate Cancer; Proteomics; Statistics; Supervised Learning
Abstract
Prostate cancer is the most commonly diagnosed cancer among Canadian men. When diagnosed with prostate cancer, patients are classified in different risk categories for recurrence of the cancer after treatment. This classification guides the type of treatment that the patient will receive after diagnosis. For example, a prostate cancer patient exhibiting a high risk of recurrence will typically receive a more aggressive treatment than one with a lower risk. These individualized treatment options result in a better prognosis of the disease. However, not all known risk factors of recurrence are currently used in prostate cancer recurrence risk stratification. The presence of tumour growth in the ducts of the prostate is one of those factors that increases the risk of recurrence. However, due to their small size, these tumour growths are often missed in tumour biopsies and patients are therefore not treated appropriately. In this project, I propose to use a technology named imaging mass spectrometry that allows the identification of molecules in very small regions of the prostate. The detection of these molecules can then be used to determine the presence of tumour growth in prostate ducts and provide patients with the appropriate treatment. I will also use a computational and statistical approach that will identify the set of molecules that provide the most accurate prediction of the presence of tumour growth in prostate cancer. The discovered molecules will make the diagnosis of prostate cancer more accurate and ensure that the treatment of patients is more tailored to their condition. Ultimately, my project will reduce prostate cancer recurrence and improve its survival rate.
Competitiondate
201812
Approvedterm2
1 yr 0 mth
Pinamesdelim
Shahryari Fard, Soroush
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~