Grant: Master's Award: Canada Graduate Scholarships
University of Alberta
$27,000.00
Improving surgical care for rectal cancer through the development of an automated artificial intelligence algorithm for magnetic resonance imaging interpretation
FY 2024-25
Summary
Magnetic resonance imaging (MRI) is the preferred method for evaluating rectal cancer (RC) severity. Accurately evaluating RC severity is critical for treatment decision making, which dictates whether patients receive immediate surgery or radiation therapy (RT) and/or chemotherapy before surgery. Inaccurate evaluation before surgery may lead to increased long-term complications if patients receive unnecessary treatment or conversely, do not receive appropriate treatment before their operation. Assessing pelvic MRI can be challenging; expertise in reading these MRIs is scarce and interpretations can vary widely. However, review by multiple interpreters can improve accuracy.At the University of Alberta Hospital (UAH), most RC MRIs are reviewed at multidisciplinary tumour board (MTB) meetings. Discussion may lead to changes in MRI interpretation, and subsequently, changes in treatment decisions. In a preliminary review of 49 UAH RC patients, 57% had significant discrepancies between their initial disease severity diagnosed prior to surgery and final disease severity after surgery. This discrepancy affected treatment plans, as nearly half (49%) would have received a different treatment plan. Applying an artificial intelligence (AI) tool as a trained additional interpreter could help reduce the discrepancy in MRI interpretation, ease decision making, and ultimately, improve patient outcomes. We propose a multiphase study to improve RC patient care by firstly, auditing historic MRI interpretation, MTB decision-making, and patient outcomes and secondly, developing and testing an AI tool to help with reliable RC severity evaluation. A successful AI tool may eventually be used at other sites nationally and internationally to continue to improve RC care.
Department
Program
Master's Award: Canada Graduate Scholarships
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
530290
Name
Muncner Susan
Region
Alberta
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Improving surgical care for rectal cancer through the development of an automated artificial intelligence algorithm for magnetic resonance imaging interpretation
Programtype2
Studentship Programs
Orgnameinp2
University of Alberta
Cihramount2
$27,000
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Magnetic Resonance Imaging; Rectal Cancer
Abstract
Magnetic resonance imaging (MRI) is the preferred method for evaluating rectal cancer (RC) severity. Accurately evaluating RC severity is critical for treatment decision making, which dictates whether patients receive immediate surgery or radiation therapy (RT) and/or chemotherapy before surgery. Inaccurate evaluation before surgery may lead to increased long-term complications if patients receive unnecessary treatment or conversely, do not receive appropriate treatment before their operation. Assessing pelvic MRI can be challenging; expertise in reading these MRIs is scarce and interpretations can vary widely. However, review by multiple interpreters can improve accuracy.At the University of Alberta Hospital (UAH), most RC MRIs are reviewed at multidisciplinary tumour board (MTB) meetings. Discussion may lead to changes in MRI interpretation, and subsequently, changes in treatment decisions. In a preliminary review of 49 UAH RC patients, 57% had significant discrepancies between their initial disease severity diagnosed prior to surgery and final disease severity after surgery. This discrepancy affected treatment plans, as nearly half (49%) would have received a different treatment plan. Applying an artificial intelligence (AI) tool as a trained additional interpreter could help reduce the discrepancy in MRI interpretation, ease decision making, and ultimately, improve patient outcomes. We propose a multiphase study to improve RC patient care by firstly, auditing historic MRI interpretation, MTB decision-making, and patient outcomes and secondly, developing and testing an AI tool to help with reliable RC severity evaluation. A successful AI tool may eventually be used at other sites nationally and internationally to continue to improve RC care.
Competitiondate
202412
Approvedterm2
1 yr 0 mth
Pinamesdelim
Muncner, Susan
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $27,000~ $0~