Grant: Master's Award: Canada Graduate Scholarships
University of British Columbia
$17,500.00
Combining Multiplexed Immunohistochemistry and Deep Learning to Spatially Map the Tumour Microenvironment
EF 2020-21
Résumé
The tumour microenvironment(TME) is a highly complex mixture containing, epithelium, stroma and a diverse network of immune cells and the spatial organization of these immune cells within the TME reflects a crucial process in anti-tumor immunity. Different components of the TME play various roles in promoting tumor growth or suppressing it and thus, in determining the optimal treatment strategy, the heterogeneous tumor microenvironment must be fully considered for treatment planning. The usual standard of care for assessing if a patient has cancer, its stage and its likely future biological behaviour is visual examination of one or more stained sections. Immunohistochemistry(IHC) has changed the paradigm of digital pathology, moving from single-marker IHC towards multiplexed labeling, increasing the need for more advanced techniques that can be easily integrated in routine clinical pathology. To address the clinical need for high-dimensional analysis of tissue sections in clinical pathology, we propose to develop an automated multiplexed IHC technology combined with a deep learning cell segmentation method that would enable analysis of complex immune cell population's on a single slide through consecutive cycles of staining, destaining, hyperspectral imaging and spectral unmixing. Using deep learning to recognize/segment individual cell nuclei in multiplexed stained tissue sections, we can improve the accuracy of tissue classification based upon the measured characteristics of these cells and their spatial organization. The combination of the two would be transformative to multiple areas of clinical research, improving our understanding of the biological aggressiveness of specific cancers and enabling an accurate spatial cell level representation of the tissue.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database
Tel que publié
Id
449493
Name
Noureddine Kouther
Region
British Columbia
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Combining Multiplexed Immunohistochemistry and Deep Learning to Spatially Map the Tumour Microenvironment
Programtype2
Studentship Programs
Orgnameinp2
University of British Columbia
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Absorption Microscopy; Cancer Imaging; Cell Segmentation; Cell-Cell Interactions; Deep Learning; Digital Pathology; Immune Cells; Multiplex Immunohistochemistry; Tumour Heterogeneity; Tumour Microenvironment
Abstract
The tumour microenvironment(TME) is a highly complex mixture containing, epithelium, stroma and a diverse network of immune cells and the spatial organization of these immune cells within the TME reflects a crucial process in anti-tumor immunity. Different components of the TME play various roles in promoting tumor growth or suppressing it and thus, in determining the optimal treatment strategy, the heterogeneous tumor microenvironment must be fully considered for treatment planning. The usual standard of care for assessing if a patient has cancer, its stage and its likely future biological behaviour is visual examination of one or more stained sections. Immunohistochemistry(IHC) has changed the paradigm of digital pathology, moving from single-marker IHC towards multiplexed labeling, increasing the need for more advanced techniques that can be easily integrated in routine clinical pathology. To address the clinical need for high-dimensional analysis of tissue sections in clinical pathology, we propose to develop an automated multiplexed IHC technology combined with a deep learning cell segmentation method that would enable analysis of complex immune cell population's on a single slide through consecutive cycles of staining, destaining, hyperspectral imaging and spectral unmixing. Using deep learning to recognize/segment individual cell nuclei in multiplexed stained tissue sections, we can improve the accuracy of tissue classification based upon the measured characteristics of these cells and their spatial organization. The combination of the two would be transformative to multiple areas of clinical research, improving our understanding of the biological aggressiveness of specific cancers and enabling an accurate spatial cell level representation of the tissue.
Competitiondate
202012
Approvedterm2
1 yr 0 mth
Pinamesdelim
Noureddine, Kouther
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~