Grant: Master's Award: Canada Graduate Scholarships
University of Toronto
$17,500.00
Development of a hip fracture screening tool using computer vision assisted ultrasound imaging
FY 2023-24
Summary
Approximately 20% of Canadians live in rural and remote communities. Elderly patients who fall and fracture their hips in these communities have worse outcomes due to delays in getting to surgery. Better diagnosis of hip fractures within these communities could minimize unnecessary trips to the hospital for those without fractures and help to rapidly guide those who do have fractures to hospitals that can perform hip fracture surgery.
Point of care ultrasound (POCUS) is a safe, portable, and affordable imaging technology that can be used to diagnose hip fractures. POCUS is increasingly accessible in rural and remote communities and can be used by many health professionals including EMS (ambulance staff) and nurses in long term care facilities and remote medical stations. However, currently POCUS is infrequently used in assessing traumatic hip pain as acquiring and reading the images requires specialized training. This project aims to build a computer vision model that can solve these issues by providing ultrasound imaging guidance to untrained operators and real-time fracture detection. To do this, we have built a computer vision model which has already achieved excellent results in automatically evaluating hip fractures with POCUS in pigs. To optimize and evaluate our system in humans, we will collect POCUS images of human hip fractures in the emergency department (ED) and compare our ability to automatically diagnose fractures (and identify the fracture location and type) against gold standard x-ray imaging. Ultimately this novel technology can improve clinical assessment of falls in elderly patients in their homes, reduce unnecessary trips to the ED for those without a broken bone, and accelerate the pathway to trauma care for those with hip fractures.
Department
Program
Master's Award: Canada Graduate Scholarships
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
506567
Name
Yee Nicholas J
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Development of a hip fracture screening tool using computer vision assisted ultrasound imaging
Programtype2
Studentship Programs
Orgnameinp2
University of Toronto
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Computer Vision; Emergency Medicine; Hip Fracture; Image Analysis; Machine Learning; Orthopaedic Surgery; Orthopaedic Trauma; Rural And Remote Communities; Ultrasound
Abstract
Approximately 20% of Canadians live in rural and remote communities. Elderly patients who fall and fracture their hips in these communities have worse outcomes due to delays in getting to surgery. Better diagnosis of hip fractures within these communities could minimize unnecessary trips to the hospital for those without fractures and help to rapidly guide those who do have fractures to hospitals that can perform hip fracture surgery.
Point of care ultrasound (POCUS) is a safe, portable, and affordable imaging technology that can be used to diagnose hip fractures. POCUS is increasingly accessible in rural and remote communities and can be used by many health professionals including EMS (ambulance staff) and nurses in long term care facilities and remote medical stations. However, currently POCUS is infrequently used in assessing traumatic hip pain as acquiring and reading the images requires specialized training. This project aims to build a computer vision model that can solve these issues by providing ultrasound imaging guidance to untrained operators and real-time fracture detection. To do this, we have built a computer vision model which has already achieved excellent results in automatically evaluating hip fractures with POCUS in pigs. To optimize and evaluate our system in humans, we will collect POCUS images of human hip fractures in the emergency department (ED) and compare our ability to automatically diagnose fractures (and identify the fracture location and type) against gold standard x-ray imaging. Ultimately this novel technology can improve clinical assessment of falls in elderly patients in their homes, reduce unnecessary trips to the ED for those without a broken bone, and accelerate the pathway to trauma care for those with hip fractures.
Competitiondate
202312
Approvedterm2
1 yr 0 mth
Pinamesdelim
Yee, Nicholas J
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~