On October 16, 2019 it was announced that 29 new
Faculty Affiliates holding appointments at universities across Ontario
have been cross-appointed into the Vector Institute. Researchers
cross-appointed into the institute gain access to a collaborative community
based in Toronto’s MaRS Discovery District and computing resources to
catalyze foundational research and specific applications in areas such as
health care and business.

The Faculty Affiliates program brings together leading
researchers from across Ontario to expand expertise in deep learning, machine
learning and artificial intelligence more broadly.

Vector Faculty Affiliates play a key role in developing,
growing and diversifying knowledge and research within the local AI community,
and work with industry, where interests align. They have opportunities to host
events on related topics and participate in Vector programming, including
networking events, workshops, summer schools, and talks.

The 29 new Faculty Affiliates hold primary appointments at
institutions across the province, including St. Michael’s Hospital, the
University Health Network, the Krembil Centre for Neuroinformatics and the
Ontario Institute for Cancer Research and Queens, McMaster, and York University
and the Universities of Toronto, Ottawa, and Western Ontario.

Applicants and nominees were evaluated and selected
according to the strength of their research contributions to date and the
alignment of their interests with Vector’s vision, mission, and research
strengths.

Selections were made based on recommendations from a
committee comprised of Vector Faculty who hold appointments in a variety of
institutions. Faculty Affiliates are appointed for two years and nominations
are considered annually.

Learn more:

• All researchers at
  Vector

Vector Faculty Affiliate Program: 2019 Cohort

Amber Simpson, Queens University
Boyu Wang, Western University
Chris McIntosh, University Health Network
Daniel James Lizotte, Western University
David Richard Rokeby, University of Toronto
Fanny Chevalier, University of Toronto
Florian Shkurti, University of Toronto
Grace Yi, Western University
Issac Tamblyn, University of Ottawa
Jared Simpson, Ontario Institute for Cancer Research
Jason Millar, University of Ottawa
Jeffrey S. Rosenthal, University of Toronto
Joseph Jay Williams, University of Toronto
Katarina Grolinger, Western University
Linbo Wang, University of Toronto
Lincoln Stein, Ontario Institute for Cancer Research
Michael Brown, York University
Nisarg Shah, University of Toronto
Parvin Mousavi, Queens University
Paul David McNicholas, McMaster University
Sean Lewis Hill, University of Toronto and Krembil Centre for Neuroinformatics
Sushant Sachdeva, University of Toronto
Timothy Barfoot, University of Toronto
Timothy Chan, University of Toronto
Tracy Jenkin, Queens University
Xiaodan Zhu, Queens University
Yalda Mohsenzadeh, Western University
Yu Sun, University of Toronto

Today, the Vector Institute congratulates our very own Chief Scientific Advisor, Dr. Geoffrey Hinton, for winning the Honda Prize 2019 for his pioneering research in the field of deep learning in artificial intelligence (AI) and his contribution to practical application of the technology. Dr. Hinton is also VP and Engineering Fellow, Google, Professor Emeritus, University of Toronto and Advisor, Learning in Machine & Brain program, Canadian Institute for Advanced Research (CIFAR).
–
Established in 1980, the annual Honda Prize recognizes the work of individuals or groups generating new knowledge to drive the next generation, from the standpoint of eco-technology. AI is expected to play an important role not only in the advancement of science and technology but also in resolving many different global issues that humankind must address in the areas of energy and climate change.

The award caps off a year in which Dr. Hinton’s achievements, as well as the legacy of Canada’s pioneering role in AI, have yielded increasing accolades. In December, the Governor General of Canada appointed Dr. Hinton as a Companion of the Order of Canada. He was granted the 2019 Toronto Region Builder Award at a ceremony attended by Prime Minister Justin Trudeau in February and in March, the Association for Computing Machinery awarded this year’s A.M. Turing Award, to Dr. Hinton and his colleagues Yoshua Bengio, scientific director of Vector’s sibling organization Mila, and Yann LeCunn, Professor at New York University and Chief AI Scientist at Facebook.

Read more about the Honda Prize and Dr. Hinton’s work here.

Photo credit: Jim Gathany

By Ian Gormely

Toronto – Today, the Vector Institute, an independent, not-for-profit research institute focused on leading-edge machine learning, announced the third of its series of Pathfinder Projects to implement artificial intelligence (AI) in the health sector.

The third Pathfinder Project, performed in partnership with Public Health Ontario (PHO), will classify tick species using computer vision. Blacklegged ticks are the only ticks in Ontario known to carry B. burgdorferi, the bacteria that causes Lyme disease. Not all blacklegged ticks carry B. burgdorferi, but a bite from one is of more concern than a bite from a dog tick or another tick species that doesn’t carry the bacteria. For this project, Vector’s technical AI staff scientist Dr. Elham Dolatabadi, Dr. Vanessa Allen, Chief of Microbiology, PHO and Dr. Samir Patel, clinical microbiologist at PHO, will develop a method to automatically identify tick species using computer vision.

The first deliverable will be an AI algorithm that professionals at PHO will use to identify whether or not a tick is a blacklegged tick. The long-term goal is to create an app that anyone can use to simply take a photo of a tick. Once the app identifies the species, it will provide advice.

“The app we want to build would empower the public,” says Dr. Patel. PHO receives around 10,000 ticks each year for identification. Currently, the PHO laboratory has to identify each individual tick that is submitted. “Manually identifying and reporting each tick back to the submitter can take up to three weeks,” he says. The process can be automated using machine learning approaches so it is faster at PHO in the short term. “Once the app is developed the process will be even faster because the app can tell you right away whether or not it is a blacklegged tick and infer the risk of contracting Lyme disease.” The rapid identification of the blacklegged ticks will allow individuals to determine whether or not they should seek medical attention within the recommended 72 hours of tick removal.

Pathfinder Projects are small-scale efforts designed to produce results in 12 to 18 months that guide future research and technology adoption. With technical and resource support from the Vector Institute, the projects each bring together a multidisciplinary research team to tackle an important health care problem or opportunity using machine learning and AI more broadly. Each project was chosen for its potential to help identify a “path” through which world-class machine learning research can be translated into widespread benefits for patients.

About the Vector Institute

The Vector Institute is an independent, not-for-profit corporation dedicated to advancing artificial intelligence, excelling in machine and deep learning. The Vector Institute’s vision is to drive excellence and leadership in Canada’s knowledge, creation, and use of AI to foster economic growth and improve the lives of Canadians.

The Vector Institute is funded by the Province of Ontario, the Government of Canada through the Pan-Canadian AI Strategy administered by CIFAR, and industry sponsors from across the Canadian economy.

Tick Identification

Ticks, and the threat of Lyme disease, have become a regular feature of venturing outdoors in the summer months. For many Canadians, a thorough check for the tiny insects, which feed on our blood, is par for the course when returning from a hike or camping trip. Yet, only certain tick species actually carry the bacteria that causes Lyme disease. The challenge for most Ontarians is correctly identifying the type of tick that has decided to make you its lunch.

“Half of the ticks in Ontario are dog ticks,” explains Dr. Samir Patel, clinical microbiologist with Public Health Ontario (PHO). “They don’t carry the bacteria that causes Lyme disease.” However, blacklegged ticks are capable of carrying and transmitting that bacteria, with the risk of infection higher in certain parts of the province than others. Anyone who finds one on their body should consult a doctor.

PHO receives over 10,000 tick submissions every year — ticks sent to their laboratory site in Sault Ste. Marie — from Ontarians looking for guidance around a potential tick bite. Currently the laboratory has to manually identify each bug, a process that can take up to three weeks.

To ensure rapid and streamlined medical assessment of high risk tick bites, as well as reduce individuals’ anxiety about the potential Lyme disease after a tick bite, PHO is developing a mobile app to rapidly and accurately identify tick species and provide next-steps medical guidance. “There’s currently a gap in care,” admits Dr. Vanessa Allen, Chief of Medical Microbiology at PHO, “and this is one way to close that gap and improve the care and the delivery of services for Lyme disease in Ontario and beyond.”

Along with Dr. Allen and Vector’s technical AI staff scientist, Dr. Elham Dolatabadi, Dr. Patel is currently developing a computer vision model to differentiate between the two common tick species normally found in Ontario. “In the short-term we look forward to using computer vision for blacklegged tick identification at PHO.” he says. “Once the app is developed, it will empower the public. If you find a tick on your body, the app will be able to tell you right away whether it is a blacklegged tick or not.”

Tick populations have been increasing in recent years, as has awareness around tick bites and the threat of Lyme disease, says Dr. Allen. But both she and Dr. Patel caution that a tick bite, even from a blacklegged tick, doesn’t automatically mean that a person will contract Lyme disease and where appropriate, a single dose of prophylaxis should mitigate the chances of infection.

PHO plans to have the app available to the public by the end of next year. They also hope to use data from the user-submitted photos to help track tick populations in the province and better understand where ticks are moving, which can help inform future strategies, says Dr. Allen. “It’s not a magic bullet, but it’s a tool to speed up the process of both patient care and our understanding of Lyme disease.”

Vector’s Second Pathfinder Project to Enhance Radiology with AI

Toronto – Today, the Vector Institute, an independent, not-for-profit research institute focused on leading-edge machine learning, announced the second in its series of Pathfinder Projects to implement Artificial Intelligence (AI) in the health sector.

The second Pathfinder Project, performed in partnership with the University Health Network (UHN) and the University of Waterloo (UWaterloo) will enhance radiology diagnoses with AI.

Coral Review, a software solution developed at UHN, is a peer learning tool used by clinicians in diagnostic imaging to support continuous quality improvement of radiologist practice. Using an algorithm developed by Dr. H.R. Tizhoosh, Director of the Laboratory for Knowledge Inference in Medical Image Analysis (Kimia Lab) at UWaterloo and a Faculty Affiliate at the Vector Institute, an AI-enabled Coral Review would scan through thousands of existing medical images (i.e., x-rays) for ones similar to a patient’s and recommend a diagnosis to the attending physician.

“Coral Review currently enables anonymous peer reviews of medical imaging diagnoses. However, it is limited by the availability of physicians who perform the review or ‘second opinion’,” says Leon Goonaratne, Senior Director of Information Technology, UHN. “An AI-enabled peer review solution has the ability to provide the physician with more information when they perform the review, including the identification of images corresponding to rare or difficult to see cases”.

Pathfinder Projects are small-scale efforts designed to produce results in 12 to 18 months that guide future research and technology adoption. With technical and resource support from the Vector Institute, the projects each bring together a multidisciplinary research team to tackle an important health care problem or opportunity using machine learning and AI more broadly. Each project was chosen for its potential to help identify a “path” through which world-class machine learning research can be translated into widespread benefits for patients.

About the Vector Institute

The Vector Institute is an independent, not-for-profit corporation dedicated to advancing artificial intelligence, excelling in machine and deep learning. The Vector Institute’s vision is to drive excellence and leadership in Canada’s knowledge, creation, and use of AI to foster economic growth and improve the lives of Canadians.

The Vector Institute is funded by the Province of Ontario, the Government of Canada through the Pan-Canadian AI Strategy administered by CIFAR, and industry sponsors from across the Canadian economy.

About University Health Network

University Health Network consists of Toronto General and Toronto Western Hospitals, the Princess Margaret Cancer Centre, Toronto Rehabilitation Institute, and The Michener Institute of Education at UHN. The scope of research and complexity of cases at University Health Network has made it a national and international source for discovery, education and patient care. It has the largest hospital-based research program in Canada, with major research in cardiology, transplantation, neurosciences, oncology, surgical innovation, infectious diseases, genomic medicine and rehabilitation medicine. University Health Network is a research hospital affiliated with the University of Toronto. www.uhn.ca

AI-Enhanced Coral Review

Dr. H. R. Tizhoosh and his team have worked at the nexus of health care and artificial intelligence (AI) for over a quarter century. Yet, only now is the world beginning to see the fruits of that labour. “In spite of the progress we’ve made,” he says, “we’re at the very beginning if we want to bring the technology into hospitals.”

Director of Kimia Lab at the University of Waterloo (UWaterloo), Dr. Tizhoosh will be at the forefront of this important shift as he seeks to enhance University Health Network’s (UHN) medical imaging peer review system, Coral Review. It is the second of the Vector Institute’s Pathfinder Projects, which bring together multidisciplinary research teams to tackle important health care problems using machine learning.

Developed at UHN, Coral Review has been implemented at a number of hospitals across Ontario. Designed to bring focus to quality and education within medical imaging departments, the solution enables an anonymous peer review of a medical imaging diagnosis, as well as image quality.

“Coral Review has enabled a program of quality and education for many hospitals,” says Leon Goonaratne, Senior Director of Information Technology, UHN. “While this peer review process is helping identify and facilitate many learning and coaching opportunities across the province, we believe artificial intelligence is the next step to making the solution even more effective”.

To bring more regularity and efficiency into the system, Dr. Tizhoosh and his team are training a machine learning algorithm with a mixture of public and private data set of over 200,000 anonymized medical images. Once trained, the AI-enhanced Coral Review application would find similar looking images from past cases and offer suggested diagnoses, while leaving the final decision to doctors.

“It’s AI deployed in a slightly different way,” says Dr. Tizhoosh. “It allows the radiologist making the diagnosis to benefit from the knowledge of thousands of diagnoses made by other clinicians. That’s very different from making a diagnosis from scratch.”

The teams at UHN and Kimia Lab are starting relatively small, focusing on chest x-rays and specifically looking at pneumothorax, or collapsed lungs. The condition is a technical challenge for radiologists and a practical one for doctors; certain types can be difficult to see on an x-ray and a collapsed lung is both painful and potentially fatal. Small collapses pose a particularly significant challenge. “Doctors can miss small collapses in 40 percent of cases because you just can’t see it,” says Dr. Tizhoosh.

As it currently stands, their algorithm has about a 70 percent accuracy rate. But with technology and resources support from Vector they will fine tune it over the next year and hope to push that rate above 90 percent before incorporating it into the existing system. Dr. Tizhoosh also hopes to expand the project’s scope beyond pneumothorax. “Long term, we want to add a long list of problems that we automatically check,” he says. “We want to find more difficult problems and work on a larger scale in the radiology domain.”

Once implemented, the system will be the first of its kind: an AI-enabled diagnostic tool for medical images based on image retrieval. “Working with hospitals to implement AI in medical imaging is the most thrilling thing I have ever done in my career,” Dr. Tizhoosh enthuses. “I want to look back and say, ‘this is what I did as a computer scientist.’ It’s a very exciting time.”

AI-Enhanced Coral Review is the second in a series of Pathfinder Projects identified and supported by the Vector Institute.