Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Alliance Grants

University of Toronto

$30,000.00

Non-Rigid Wound Image Registration System

FY 2023-24

Summary
In Canada, 30-50% of all health care involve wounds and incur a direct cost of $3.9Billion annually. Documentation of skin and wound assessments longitudinally is critical to both prevention of wounds and wound care. Such documentation is often executed via digital modalities. Clinicians usually center a digital image of the at-risk area or wound in the field of view. However, we have found that variations in distance, orientation, rotation, obliquity, and other parameters, make comparison of wound imagery over time extremely difficult. Uncertainty in the changes over time can lead to either inappropriate wound interventions or inaction by providers leading to negative health outcomes and increased health care burden. Aids to assist the user in obtaining images acquired at the same distance and perspective as previous imaging would greatly simplify the task of longitudinal evaluation of imagery. We have successfully applied convolutional neural network models that are trained on unrelated image datasets to biological images through transfer learning. In collaboration with others, our ongoing work utilizes tongue images to identify diabetic patients. More recently, we have investigated the use of facial video to extract ECG data. Images of interest for this project come from a mobile multispectral medical imaging device that captures digital, infrared, and near infrared images. The primary objective for this project is to develop a method or a system for non-rigid image registration. Achieving this aim will require developing machine learning models that extract image features from visible, infrared, and near infrared images to learn the spatial transformations across longitudinal wound images. Incorporating this system within the multispectral imaging device will greatly benefit medical practitioners and patients. We seek to leverage our knowledge and expertise to devise an image registration system that is specific to wound imagery and does not rely upon a rigid image capture mechanism. Upon completion of the project, we will continue to dedicate efforts towards the refinement of the resulting non-rigid registration system within wound care and the exploration of its use by non-healthcare practitioners and in other disease spaces.
Program
Alliance Grants
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
581001-2023
Name nom
Murty, Vijayakumar V
Department département
Mathematics (St. George Campus)
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
30000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1211
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Medical and health sciences
Area of application fr
Sciences médicales et de la santé
Research subject code
9000
Research subject group en
Medical sciences
Research subject group fr
Medical sciences
Research subject en
Sciences médicales
Research subject fr
Sciences médicales
Application title
Non-Rigid Wound Image Registration System
Keyword
Applied Mathematics; Digital Imagery; Health Science; Image Registration System; Machine Learning; Wound Care
Application summary
In Canada, 30-50% of all health care involve wounds and incur a direct cost of $3.9Billion annually. Documentation of skin and wound assessments longitudinally is critical to both prevention of wounds and wound care. Such documentation is often executed via digital modalities. Clinicians usually center a digital image of the at-risk area or wound in the field of view. However, we have found that variations in distance, orientation, rotation, obliquity, and other parameters, make comparison of wound imagery over time extremely difficult. Uncertainty in the changes over time can lead to either inappropriate wound interventions or inaction by providers leading to negative health outcomes and increased health care burden. Aids to assist the user in obtaining images acquired at the same distance and perspective as previous imaging would greatly simplify the task of longitudinal evaluation of imagery. We have successfully applied convolutional neural network models that are trained on unrelated image datasets to biological images through transfer learning. In collaboration with others, our ongoing work utilizes tongue images to identify diabetic patients. More recently, we have investigated the use of facial video to extract ECG data. Images of interest for this project come from a mobile multispectral medical imaging device that captures digital, infrared, and near infrared images. The primary objective for this project is to develop a method or a system for non-rigid image registration. Achieving this aim will require developing machine learning models that extract image features from visible, infrared, and near infrared images to learn the spatial transformations across longitudinal wound images. Incorporating this system within the multispectral imaging device will greatly benefit medical practitioners and patients. We seek to leverage our knowledge and expertise to devise an image registration system that is specific to wound imagery and does not rely upon a rigid image capture mechanism. Upon completion of the project, we will continue to dedicate efforts towards the refinement of the resulting non-rigid registration system within wound care and the exploration of its use by non-healthcare practitioners and in other disease spaces.