Grant: Master's Award: Canada Graduate Scholarships
McGill University
$17,500.00
Quantitative Analysis of the Evolution of Radiomic Feature Values in Simulated Positron Emission Tomography Images
FY 2020-21
Summary
Cancer is one of the leading causes of death globally and accounted for about 9.6 million deaths in 2018. Extensive efforts from researchers to gain a better understanding of cancer have lead to the advancement of various medical imaging modalities and treatment methods. Medical imaging revealed distinct measurable characteristics between and within tumors that were later found to trigger adaptations in cancer cells for faster growth and resistance to treatment. Every tumor is different, and identifying the distinct characteristics in each tumor is crucial for modifying the treatment plan accordingly. Unfortunately, it is still unclear how these features are related to image properties in medical scans, tumor prognosis, and treatment outcomes. Radiomics is a method to quantitatively capture distinct tumor characteristics in medical images. Analysis of radiomic features provides information such as patterns, inter-pixel relationships, and textures in radiological images. Here we will use radiomics analysis to uncover how the features extracted from positron emission tomography (PET) imaging evolve with tumor growth. Movies of PET images will be acquired from my ongoing undergraduate thesis project on realistic tumor growth simulation. Radiomics analysis on these motion pictures will allow us to identify the most robust features that exhibit the most changes with tumor growth. These features will be optimal for tracking the disease progression and response to treatment. Successful identification of features can help design more sensitive image analysis methods that allows for personalized treatment for each cancer patient.
Department
Program
Master's Award: Canada Graduate Scholarships
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
449598
Name
Ahn Sae Hyun
Region
Québec
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Quantitative Analysis of the Evolution of Radiomic Feature Values in Simulated Positron Emission Tomography Images
Programtype2
Studentship Programs
Orgnameinp2
McGill University
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Cancer; Medical Imaging; Radiomics Analysis; Tumor Heterogeneity; Tumor Progression
Abstract
Cancer is one of the leading causes of death globally and accounted for about 9.6 million deaths in 2018. Extensive efforts from researchers to gain a better understanding of cancer have lead to the advancement of various medical imaging modalities and treatment methods. Medical imaging revealed distinct measurable characteristics between and within tumors that were later found to trigger adaptations in cancer cells for faster growth and resistance to treatment. Every tumor is different, and identifying the distinct characteristics in each tumor is crucial for modifying the treatment plan accordingly. Unfortunately, it is still unclear how these features are related to image properties in medical scans, tumor prognosis, and treatment outcomes. Radiomics is a method to quantitatively capture distinct tumor characteristics in medical images. Analysis of radiomic features provides information such as patterns, inter-pixel relationships, and textures in radiological images. Here we will use radiomics analysis to uncover how the features extracted from positron emission tomography (PET) imaging evolve with tumor growth. Movies of PET images will be acquired from my ongoing undergraduate thesis project on realistic tumor growth simulation. Radiomics analysis on these motion pictures will allow us to identify the most robust features that exhibit the most changes with tumor growth. These features will be optimal for tracking the disease progression and response to treatment. Successful identification of features can help design more sensitive image analysis methods that allows for personalized treatment for each cancer patient.
Competitiondate
202012
Approvedterm2
1 yr 0 mth
Pinamesdelim
Ahn, Sae Hyun
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~