Grant: Discovery Grants Program - Individual
The University of British Columbia
$42,000.00
On-Device Continual Learning Methods for Point of Care Ultrasound
FY 2024-25
Summary
Artificial intelligence(AI) systems have been developed and deployed for a variety of tasks in our life, such as computer vision applications for smartphones, and autonomous robotics for healthcare and industry. However, existing AI systems have several drawbacks, including the inability to 1) adapt to continuously varying domains, and 2) effectively learn over time (life-long learning) from unseen noisy, limited, heterogeneous data streams. This is crucial to achieving high levels of performance when they interact with real-world environments. Furthermore, current AI systems consume large amounts of memory and require access to cloud computing resources, limiting their ability to be deployed on mobile devices.
The long-term vision of this research program is to develop novel AI systems, for industrial and clinical services and products, by diminishing the gap between exploratory engineering research and industry applications and bringing technologies from bench-to-bedside. The overarching goal, which forms the basis of this NSERC discovery grant (DG), is to develop robust, unsupervised AI-systems that can i) learn from unbalanced/limited, noisy, heterogeneous data,and ii) achieve high performance in real-world environments over time. The research program will also develop theoretical foundations to improve the learning capabilities, computational efficiency, and memory utilization of AI-powered mobile computing platforms. The specific application of this DG will be on point-of-care ultrasound (POCUS) imaging where challenges in AI learning are especially limiting.
Impact
POCUS aims to mitigate barriers to healthcare for rural and remote communities. Unfortunately, lack of proficiency and confidence has led to the under-utilization of POCUS in out-of-hospital settings. Our novel learning methods, once developed and integrated within POCUS devices, will improve the use of this technology and will have an important impact on the health of Canadians and the Canadian economy. Applications of US such as non-destructive testing and/or sound navigation and ranging, military/space exploration where mobile computing platforms are utilized will also benefit from the algorithms developed as part of this program.
AI is expected to contribute up to $15.7 trillion to the global economy in 2030, and Canada has been at the center of this AI revolution. The proposed research program will contribute to the Canadian AI infrastructure, in academia as well as in the global (Siemens, Google) and local industries located in BC (Synthesis Health, Satisfai Health, Clarius), by training 11 highly qualified personnel (HQP) over the funding period. Training of HQPs will be augmented by industry internships and participation in educational opportunities and public outreach, to prepare them for careers in the growing AI ecosystem in Canada and beyond. HQP will also be trained in equity, diversity, and inclusion through workshops, seminars, and certificate programs.
Program
Discovery Grants Program - Individual
Recipient
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2023-03575
Name nom
Hacihaliloglu, Ilker
Department département
Radiology and Medicine
Organization id
2
Institution établissement
The University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
42000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
Area of application code
1102
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Biomedical engineering
Area of application fr
Génie biomédical
Research subject code
1901
Research subject group en
Biomedical engineering
Research subject group fr
Génie biomédical
Research subject en
Biomedical technology
Research subject fr
Technologie biomédicale
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
On-Device Continual Learning Methods for Point of Care Ultrasound
Keywords
medical image analysis; ultrasound image processing; computer assisted interventions; computer assisted diagnosis; deep learning for medical imaging
Application summary
Artificial intelligence(AI) systems have been developed and deployed for a variety of tasks in our life, such as computer vision applications for smartphones, and autonomous robotics for healthcare and industry. However, existing AI systems have several drawbacks, including the inability to 1) adapt to continuously varying domains, and 2) effectively learn over time (life-long learning) from unseen noisy, limited, heterogeneous data streams. This is crucial to achieving high levels of performance when they interact with real-world environments. Furthermore, current AI systems consume large amounts of memory and require access to cloud computing resources, limiting their ability to be deployed on mobile devices.
The long-term vision of this research program is to develop novel AI systems, for industrial and clinical services and products, by diminishing the gap between exploratory engineering research and industry applications and bringing technologies from bench-to-bedside. The overarching goal, which forms the basis of this NSERC discovery grant (DG), is to develop robust, unsupervised AI-systems that can i) learn from unbalanced/limited, noisy, heterogeneous data,and ii) achieve high performance in real-world environments over time. The research program will also develop theoretical foundations to improve the learning capabilities, computational efficiency, and memory utilization of AI-powered mobile computing platforms. The specific application of this DG will be on point-of-care ultrasound (POCUS) imaging where challenges in AI learning are especially limiting.
Impact
POCUS aims to mitigate barriers to healthcare for rural and remote communities. Unfortunately, lack of proficiency and confidence has led to the under-utilization of POCUS in out-of-hospital settings. Our novel learning methods, once developed and integrated within POCUS devices, will improve the use of this technology and will have an important impact on the health of Canadians and the Canadian economy. Applications of US such as non-destructive testing and/or sound navigation and ranging, military/space exploration where mobile computing platforms are utilized will also benefit from the algorithms developed as part of this program.
AI is expected to contribute up to $15.7 trillion to the global economy in 2030, and Canada has been at the center of this AI revolution. The proposed research program will contribute to the Canadian AI infrastructure, in academia as well as in the global (Siemens, Google) and local industries located in BC (Synthesis Health, Satisfai Health, Clarius), by training 11 highly qualified personnel (HQP) over the funding period. Training of HQPs will be augmented by industry internships and participation in educational opportunities and public outreach, to prepare them for careers in the growing AI ecosystem in Canada and beyond. HQP will also be trained in equity, diversity, and inclusion through workshops, seminars, and certificate programs.