The cluster seeks to support its members and students by collecting information on potential resources. Please contact Danielle Walker if you wish to add a resource to the list.
* Please refer to an institutions course schedule or calendar for the most up-to-date information. This guide is meant for informational purposes only.
UBC's Dynamic Circuits in Health and Disease have catalogued their available imaging systems.
This is a catalogue of all imaging systems available through the Dynamic Circuits cluster with information such as location, their scale and their applications. Find their inventory here
For a list of BMI-AI researchers imaging systems, please contact Danielle Walker. Assets are available, but have not been made public.
An in-depth tutorial on how to use Compute Canada in the most efficient and productive way for your deep learning experiments! By BMIAI member, Prashant Pandey.
High Capacity Storage and High Performance Computing Through Compute Canada:
Any faculty member at a Canadian university can register an account at the Computer Canada Database, and once registered can sponsor accounts for students, staff, and collaborators.
These accounts allow users access to Rapid Access Service (RAS), limited online storage and “fair share” access to HPC resources.
RAS allows users access to 2 TB of storage per person, up to 10 TB per lab. This storage is online accessible and well backed up, located on Canadian servers.
Compute Canada RAS also allow opportunistic use of High Performance Computing (HPC) resources.
Default accounts come with default priority, which means you can submit jobs to the scheduler, which will run them on HPC cores when they are available and return the results to you when the operations are completed.
These nodes are high powered and have huge memory resources. Submitting a job to the nodes in Compute Canada is akin to submitting a process on a linux computer, so most anything that can be run through the command line can be run on these resources.
GETTING STARTED WITH COMPUTE CANADA:
For BC, Compute Canada servers and resources are accessed through WestGrid. WestGrid has excellent training resourses for getting started and using these online resources for storage and High Performance Computing. For an overview with links to specific instructions, see here.
For more info on Westgrid, see here
If your lab needs more resources than can be provided by the RAS system, you can apply for more storage and higher priority access to computing resources through the Resource Allocation Competition (RAC). Essentially RAC is a grant request for specific resources from Compute Canada. Allocation of resources is based on the score of your proposal and available resources for allocation. In general RAC applications are due in early October, and are divided into Resources for Research Groups (RRGs) and Research Platforms and Portals (RPPs). RRGs are for dedicated allocations of processing power for HPC and/or dedicated online storage. RPPs are more for cloud computing services, mostly involving hosting data and research portals such as websites or online databases.
More information about Compute Canada RACs can be found here:
The cluster has an allocation available to members. Please email Danielle Walker if you would like to connect to our resource. We have GPU, CPU and storage available.
UBC ARC Sockeye is the new advanced research computing infrastructure now available to UBC researchers across all disciplines.
UBC ARC Sockeye is a general-purpose high-performance computing (HPC) platform available to UBC researchers. It is of particular benefit to early-career researchers and faculty who specialize in computationally intensive research. Indigenous people’s studies and health research that require processing of sensitive or confidential datasets can also be accommodated. Sockeye supplements the current national platform for digital research infrastructure, which is currently unable to meet the needs of all UBC researchers, helping to bridge this gap and meet the needs of UBC researchers.
Researchers with a staff or faculty appointment at UBC are eligible to request an allocation on the UBC ARC Sockeye platform to conduct computationally intensive research. Use of the system is contingent on acceptance of the ARC Sockeye Terms of Service.
Allocations are provided via Fair Share based access to UBC ARC Sockeye. Standard Tier allocations are configured with the same Fair Share Priority across all CPUs and each includes 5TB of data storage. A maximum of 120 allocations are available for the year. Extended Tier allocations are configured to provide access to CPU, GPU, and storage. A single allocation may request and be awarded more resources than in the Standard Allocation, up to a maximum of 36 CPU units, 40 GPU units, and 120TB of storage per allocation.
The Dynamic Brain Circuits and Connections in Health and Disease research cluster has written an excellent resource on data management at UBC. Their white paper aims to provide information, recommendations, and best practices in data management to aid labs in the Brain Circuits cluster, and the greater DMCBH community, to develop and maintain Data Management Plans (DMPs). This includes considerations to data storage, data sharing, research data workflows, and data stewardship throughout the research life cycle.
You can read their white paper and access resources here
Resources in BC
The Health Data Platform (HDP), a multi-partner initiative underway to create a better way of sharing health-related data, has recently launched. This work is being developed and led by the Ministry of Health with matched funding from the Canadian Institutes of Health Research (CIHR) strategy for Patient Oriented Research (SPOR) and the Province of BC.
The HDP supports research and analysis both within the health sector and in academia, by allowing access to health data from multiple sources to be brought together as required (on-demand), linked, de-identified and analyzed on a single secure platform.
The goals of the HDP are to:
Provide more timely, secure and consistent access to integrated ‘big’ health data
Establish a standard and enhanced privacy and security landscape
Increase process transparency and efficiency for data providers and data consumer
Resources across Canada
UHN's Advanced Imaging Core Lab (QIPCM) - QIPCM is a central repository for imaging data and analysis tools. They offer a variety of services, such as an AI sandbox and computing platforms transferring images from over 30 hospitals and research institutions around the world.
They have presented a tabular summary of existing datasets from trials whose PIs have demonstrated interest and given consent. Collaborative interest can be directed to the corresponding contact as listed. Access the list of available data sources here.
Registry of Research Data Repositories - Discover open data repositories across the globe
Federated Research Data Repository - FRDR crawls through multiple other Canadian data repositories including dataverses, FRDR’s own data and government open data, allowing users to search for and discover data from multiple sources
Allen Institute for AI - CORD-19: COVID-19 Open Research Dataset - CORD-19 is a free resource of over 44,000 scholarly articles, including over 29,000 with full text, about COVID-19 and the coronavirus family of viruses for use by the global research community. Download
PanNuke: An Open Pan-Cancer Histology Dataset for Nuclei Instance Segmentation and Classification. Access Dataset.
UBC Science has a comprehensive list of funding deadlines here.
UBC's SPARC Office : Institutional support for your funding proposal.
Federal funding agencies (Tri-Agency)- The main sources of Canadian federal research funding are three agencies:
NSERC Discovery Grant NOI: due Aug 4
Students can speak to a counsellor by phone, toll-free at 1 877 857-3397 or direct 604 642-5212. Students calling from outside Canada can dial 1 604 642-5212 (international calling charges may apply). More information here.
To support British Columbians of all ages during the COVID-19 pandemic, the Province is expanding existing mental health programs and launching new services. You can find a comprehensive list of resources here.
UBC Student Services Mental Health Resources, access it here.
Learn from ML experts at Google. Whether you’re just learning to code or you’re a seasoned machine learning practitioner, you’ll find information and exercises to help you develop your skills and advance your projects.
Springer has released 65 Machine Learning and Data books for free. You can find one list of all the books (65 in number) that are relevant to the data and Machine Learning field here.
MLT is a Tokyo-based nonprofit organization dedicated to democratizing Machine Learning. Find their Github with AI curriculum and resources here.
Open Deep Learning and Reinforcement Learning lectures from top Universities like Stanford University, MIT, UC Berkeley. MLT has put together a list of free lectures here.
A comprehensive 10-page probability cheatsheet that covers a semester's worth of introduction to probability.
Free Courses about COVID-19
As coronavirus spread, universities started launching free online courses about the pandemic. You can find the full course list here and a selection of courses below.
Harvard: Mechanical Ventilation for COVID-19
Stanford: CS472 Data science and AI for COVID-19
Johns Hopkins: Fighting COVID-19 with Epidemiology
Machine Learning from Standford - Taught by Andrew Ng, Starts April 27th (Free)
This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
iBiology’s mission is to convey, in the form of open-access free videos, the excitement of modern biology and the process by which scientific discoveries are made.
The Allen Cell Explorer is the data portal for the Allen Institute for Cell Science, where you can explore our publicly available data, tools and models. The portal provides an unprecedented view into the organizational diversity of human stem cells by combining large-scale 3D imaging data, predictive models, observations of cells, detailed methods, and cell lines that can be purchased for use in labs around the world.
Kaggle is the world's largest data science community with powerful tools and resources to help you achieve your data science goals.
ACM Presidential Task Force on What Conferences Can Do to Replace Face to Face Meetings, “Virtual Conferences, A Guide to Best Practices"
A set of tables comparing and ranking many open-source and commercial platforms.
Graduate Pathways to Success (Pathways) program is a palette of non-credit workshops, seminars and other activities designed to complement your graduate program's academic curriculum and mentorship experience.
The government will extend expiring federal graduate research scholarships and postdoctoral fellowships, and supplement existing federal research grants, to support students and post-doctoral fellows, by providing $291.6 million to the federal granting councils. In addition, the government intends to enhance work opportunities for graduate students and post-doctoral fellows through the National Research Council of Canada. Students will be eligible to receive $1,250 a month for the months of May through August this year.
UBC Awards: Find UBC's Scholarship database here.
January 27th, 2021 from 11:30am to 1:00pm, Online
Is your study right for an AI approach? Share the clinical challenges you face and get insight on potential data science solutions from a team of engineers focused on health applications.
Jan 19, 2021 | 12:00pm–1:00pm (EST)
'The AI Path to Deeper and more Accurate Medicine'
August 4th - MATLAB for Medical Imaging Applications
August 11th - Using MATLAB with Python
August 18th - Text Analytics and Machine Learning with MATLAB
August 25th - Data Science using MATLAB
September 1st - Big Data: Scale Up to the Cloud with MATLAB
September 8th - Machine Learning with MATLAB
September 15th - Automated Image Labeling and Iterative Learning
September 22nd - Deep Learning for Neuroscience
MIDL currently offers a three-day program with keynote presentations from invited speakers, oral presentations, posters, and live demonstrations of deep learning algorithms from academia and industry.
This year's conference will be fully virtual. You can register for free here.
Zoom webinars for the plenary sessions:
Youtube Links for the plenary sessions:
Day 1: https://youtu.be/wNJQScMgpsI
Day 2: https://youtu.be/qWTgWgurlR0
Day 3: https://youtu.be/fCjtNyUkji0
Maryam Tayyab & Tiffany Cameron
Start: 9 July 2020 11:00 am
End: 9 July 2020 12:00 pm
SBME Virtual Seminar Series
(To request access to Zoom details, email firstname.lastname@example.org prior to the start of the seminar.)
Host: Dr. Sid Fels
Trainee Talk 1:
Challenges in the Application of Multimodal Deep Learning on Biomedical Images and Medical Data
When: Thursday July 9 @ 11:00am
Deep learning has been applied to solve increasingly complex problems with various degrees of success. The ability to incorporate multi-modality data to improve prediction tasks in clinical context is a sought after yet a moving target. Medical data from various modalities and sources (images, phenotype, demographics, genotype etc.) has unique properties and distribution. My graduate research focuses on exploring strategies for efficient integration of heterogeneous clinical data for optimizing the clinical prediction tasks.
Speaker: Maryam Tayyab
MASc student, Dr. Roger Tam’ Lab
Trainee Talk 2:
Developing In Vitro models for studying Alzheimer’s Disease
When: Thursday July 9 @ 11:30am
This work focuses on developing an in vitro microfluidic model, as well as making modifications to a currently-used tissue-engineered model. These models will provide a gateway for understanding the mechanisms associated with Alzherimer’s Disease.
Speaker: Tiffany Cameron
MASc student, Drs. Cheryl Wellington & Karen Cheung’s Labs
Magnimind Academy presents AI Talks in Healthcare. We are starting a new talk series where we will host top AI experts in different fields of data science, biotech, and medicine. You will have a chance to learn the most recent trends in the field which may inspire you to transition to take an initiative as a data scientist. In this webinar, we will be listening to speakers from top AI companies in the healthcare field, and one of the best universities in the world.
This week, we are going to have our fourth "AI Talks in Healthcare" webinar. We will host Jayant Thomas who is the Sr.Director AI/ML at Change Healthcare.
Info: Jul 10, 2020 11:00 AM in Pacific Time (US and Canada)
The virtual event will bring together lead academic and research organizations in the field of biomedical imaging to share institutional research highlights and an overview of their current initiatives. The seminar aims to facilitate collaboration and identify new opportunities for partnership. Please join us on June 25th and learn how you can connect with our international and multi-institutional group of directors and researchers.
In addition to our keynote talks, the event will end with a closing panel on commercialization. Moderator Raphael Ronen, Director of Business Development at Sunnybrook Research Institute, will present on their new funding ($49M) opportunity that directly targets applications of AI in Image-Guided Therapeutics. It will be a great chance to learn more about the initiative and how to get involved.
June 25, 2020 | 9:30 AM-12:30 PM (Pacific Time)
9:30 - 9:35am
9:35 - 9:55am
Dr. Peter Zandstra, Director, School of Biomedical Engineering & Michael Smith Laboratories, University of British Columbia
9:55 - 10:15am
Dr. Aaron Fenster, Imaging Director, Robarts Research Institute
Dr. Gabor Fichtinger, Professor and Canada Research Chair, School of Computing
10:35 - 10:55am
Dr. Kullervo Hynynen, Vice President, Research & Innovation, Sunnybrook Research Institute, University of Toronto
10:55 - 11:15am
Drs. Matthew O'Donnell, Mike Averkiou & Ivan Pelivanov, Department of Bioengineering, University of Washington
11:15 - 11: 35am
Dr. Gino Fallone, Professor and Director, Division of Medical Physics, Department of Oncology, University of Alberta
11:35 - 11:55am
Dr. Stephanie Willerth, Director, Biomedical Engineering, University of Victoria
May 26, 15:00 – 16:00 CET
With the COVID-19 crisis underway, we have seen artificial intelligence help search for treatments, vaccines and exit strategies. But the risks of unregulated AI remain. Hitherto, governments in Brussels, Paris, Ottawa and Tokyo have been leaders in the international drive to reach consensus on AI governance. What’s the status report today, in the age of COVID-19? This Science|Business public webcast conference is the opening session of our ‘Data Rules’ programme of events and reports on the international governance of AI.
Using X-rays and machine learning to more accurately predict COVID-19 severity
Thursday, May 21 | NOON EDT
Canada CIFAR AI Chair Marzyeh Ghassemi and Joseph Paul Cohen (Mila) will join Elissa Strome, Executive Director of the CIFAR Pan-Canadian AI Strategy, to discuss a new AI and COVID-19 Catalyst Grant project applying the latest machine learning techniques to X-ray scans in order to predict COVID-19 severity.
Marzyeh Ghassemi is a Canada CIFAR AI Chair, an assistant professor at the University of Toronto, and a Vector Institute faculty member holding a Canada Research Chair. Her research focuses on applying machine learning to understand and improve health.
Joseph Paul Cohen is a postdoctoral fellow with Yoshua Bengio at Mila and the University of Montreal. Cohen is currently focusing on the limits of AI in medicine with respect to computer vision, genomics, and clinical data.
Elissa Strome is AVP Research and Executive Director of the Pan-Canadian Artificial Intelligence Strategy at CIFAR, working with research leaders across the country to implement Canada’s national research strategy in AI.
Learn how to use story, narrative and performance skills to share your complex message. Join Talk Boutique’s next FREE online training on May 21st here: https://lnkd.in/e4k8mRQ
This webinar, aimed at users with no experience in machine learning, is an introduction to the basic concepts of neural networks, followed by a simple example—the classic classification of the MNIST database of handwritten digits—using the Julia package Flux.
Date: April 30th & May 1, 2020
Time: 11:00 AM to 5:00 PM EDT
They'll have over 20 virtual booths sponsored by the top global companies in the industry. The virtual meeting rooms and lobby will hold workshops and give you the ability to interact with colleagues. Webinars during the virtual conference will be provided by IBM Watson Health, CureMetrix, Nuance, and others.
Their virtual auditorium will have six live keynote speakers and webinars covering:
• Artificial Intelligence for COVID-19 Detection • From Burned-Out to Benched • What Now for Artificial Intelligence? • The Clinical Impact of AI in Practice • Lung Ultrasound for COVID-19
• Leading Radiology's Fight Against COVID-19 • Radiology Preparedness in the Age of COVID-19 • The MD Anderson Experience • A Look at Women's Imaging in 2020
Develop a profound knowledge and understanding of AI for medical imaging.
Beginning April 7 |Tuesdays at 1:00 pm ET | Multiple Speakers
Examine the basic concepts and methods in AI, and how these methods are increasingly applied in imaging, including anatomic radiology and nuclear medicine/molecular imaging during this new 6-session webinar series. This new series, organized by the Physics Instrumentation and Data Sciences Council, will take place over six weeks on Tuesdays at 1:00 pm ET. Each webinar will be 60 minutes in length, with the exception of webinar #2, which will be 90 minutes in length. Register.
COVID-19 and its pandemic has disrupted our societies in a major way. Healthcare innovation and artificial intelligence are more needed than ever before as vital forces to meet the myriad of challenges of pandemics. This special seminar will gather some of the best minds in both innovation and intelligence as well as infectious diseases and global health to discuss present lessons learned and solutions for the future.
April 27 @ 1:00 pm - 3:00 pm PDT
1:00 – 1:10 – Dr. Anthony Chang Overview: Innovation and Intelligence for Pandemics
1:10 – 1:20 – Dr. Alberto Tozzi: Italy’s Lessons Learned for COVID-19
1:20 – 1:30 – Dr. Claudia Hoyen: Diagnosis and Therapy for COVID-1
1:30 – 1:40 – Tom Lawry: Importance of Data for AI in COVID-19
1:40 – 1:50 – Dr. Matthieu Komorosky: The Role of AI in the ER
1:50 – 2:00 – Dr. Todd Ponsky: Virtual Communication and Education
2:00 – 2:10 – John S. Brownstein, PhD: Modeling in Pandemics
Questions and Answers
2:10 – 2:20 – Spyro Mousses Moderator
2:20 – 2:30 – Dr. Iain Hennessey: Opportunities for Innovation in times of Pandemics
2:30 – 2:40 – Tiffany Wilson: Title TBC
2:40 – 2:50 – Dawn Wolff: Title TBC
Panel Discussion and Q and A
2:50 – 3:00 – Dr. Terence Sanger Moderator
The Biomedical Imaging and AI cluster is focused on increasing engagement and collaboration between our members. As part of this effort, we will be hosting monthly research exchanges virtually the last Wednesday of the month. Register to attend or present.