Grant: Master's Award: Canada Graduate Scholarships
McGill University
$27,000.00
Democratizing the diagnosis of Hirschsprung’s disease with artificial intelligence
EF 2024-25
Résumé
Hirschsprung disease (HD) is a condition that affects the large intestine of approximately 1 in every 5000 newborns. The disease is characterized by the inability to pass stool which can cause serious infections of intestinal tissues, resulting in symptoms of fever, pain, and diarrhea. Currently, the diagnosis of HD remains a great challenge. Although the diagnostic methods employed are fairly common procedures, a definitive diagnosis remains a difficult and time-consuming task even for experienced pediatric pathologists. The diagnostic challenge is hence greater in low- and middle-income countries where access to health care is limited, resulting in a high burden of morbidity and mortality. With the current rise of artificial intelligence (AI), it can help analyze, recognize, and classify images which have been critical in the progression towards AI-assisted disease diagnoses. However, there are currently no successful clinical use cases in assisting pathologists. In this study, we aim to develop an AI system to assist pathologists in diagnosing HD. By leveraging recent advances in computer vision, we hope to create an accurate and efficient tool that can identify the key features of HD in tissue samples. Our approach will use a large dataset of over 9000 existing biopsy slides from children tested for HD at a major hospital. These will be carefully annotated to highlight important cellular structures and used to train various deep learning AI models. If successful, this AI tool could significantly improve HD diagnosis, especially in resource-limited settings. It has the potential to speed up the diagnostic process, reduce the expertise required, and ultimately lead to faster treatment and better outcomes for affected children worldwide.
Programme
Master's Award: Canada Graduate Scholarships
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
CIHR Funding Decisions Database
Tel que publié
Id
529620
Name
Wang Yixuan E
Region
Québec
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Democratizing the diagnosis of Hirschsprung’s disease with artificial intelligence
Programtype2
Studentship Programs
Orgnameinp2
McGill University
Cihramount2
$27,000
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Computational Pathology; Computer Vision; Congenital Disease; Disease Diagnosis; Hirschsprung'S Disease; Pediatrics
Abstract
Hirschsprung disease (HD) is a condition that affects the large intestine of approximately 1 in every 5000 newborns. The disease is characterized by the inability to pass stool which can cause serious infections of intestinal tissues, resulting in symptoms of fever, pain, and diarrhea. Currently, the diagnosis of HD remains a great challenge. Although the diagnostic methods employed are fairly common procedures, a definitive diagnosis remains a difficult and time-consuming task even for experienced pediatric pathologists. The diagnostic challenge is hence greater in low- and middle-income countries where access to health care is limited, resulting in a high burden of morbidity and mortality. With the current rise of artificial intelligence (AI), it can help analyze, recognize, and classify images which have been critical in the progression towards AI-assisted disease diagnoses. However, there are currently no successful clinical use cases in assisting pathologists. In this study, we aim to develop an AI system to assist pathologists in diagnosing HD. By leveraging recent advances in computer vision, we hope to create an accurate and efficient tool that can identify the key features of HD in tissue samples. Our approach will use a large dataset of over 9000 existing biopsy slides from children tested for HD at a major hospital. These will be carefully annotated to highlight important cellular structures and used to train various deep learning AI models. If successful, this AI tool could significantly improve HD diagnosis, especially in resource-limited settings. It has the potential to speed up the diagnostic process, reduce the expertise required, and ultimately lead to faster treatment and better outcomes for affected children worldwide.
Competitiondate
202412
Approvedterm2
1 yr 0 mth
Pinamesdelim
Wang, Yixuan E
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $27,000~ $0~