Validation of Cartilage Segmentation Accuracy using Deep Learning

Osteoarthritis is a degenerative disease that affects the majority of seniors and costs the Canadian economy > $30 Billion/year. The hallmark of osteoarthritis is damaged cartilage. Our understanding of how and why cartilage degenerates is not well understood. In order to identify how to stop or prevent cartilage degeneration we must have accurate and reproducible ways to measure cartilage health. The industry partner NeuralSeg has developed an algorithm that utilizes a form of artificial intelligence to measure cartilage health. The proposed research project consists of two phases.

Using Machine Learning for audio analysis and synthesize

Voices.com, the largest online marketplace for voice talent, have identified Machine Learning as an enabler for
future growth. In particular, incorporating Natural Language Processing (NLP) into structured queries and
automatic classification of sample recordings. The first phase of this research involving NLP is in the process of
being integrated into production. The second phase will be to automatically classify sound samples.

Development of Input and Evaluation Criteria for a Video-Based Occupational Risk Assessment Tool

Workplace injury prevalence and cost have created an immediate need for ergonomics risk assessment tools that require minimal ergonomics training, rooted in a foundation of experimental research, and provide comprehensive outputs that give some indication of risk and required action. Observation-based tools have been widely implemented in practice due to their simplicity, accessibility, and cost- and time-efficiency, but they typically require specialized training, present inconsistent risk categories, and depend on user interpretation of a specific set of static posture and load parameters.

Adding Rock ‘n’ Roll So Buildings Withstand Earthquakes

Although an earthquake can devastate in a few short seconds, restoration and reconstruction can take years to complete. In the 2011 Christchurch, New Zealand earthquake, there were only two major building collapses, yet 70 per cent of the city’s downtown had to be demolished because buildings were deemed uninhabitable. Restoration took five years. Earthquake recovery costs are huge. According to an Insurance Board of Canada study, an earthquake either in BC or Quebec would be nearly ten times as costly as the Fort McMurray fires, which cost over $8 billion.

Simultaneous Analysis of Endocannabinoids with Mass Spectrometry Methods in Human Serum using Point-of-care Collection Devices

Endocannabinoids are compounds produced by the human body that bind to and activate cannabinoid receptors. There are two major endocannabinoids: anandamide (AEA) and 2-arachidonoylglycerol (2-AG). Both play a role in regulating the firing of brain cells in the nervous system and attenuating immune system responses. As such, the endocannabinoid system is implicated in several clinically relevant processes including appetite regulation, pain management, fertility, and beyond.

Forecasting Profitability of Real Estate Assets using Machine Learning

This research project aims at applying machine learning over the existing financial forecasting methods currently employed in the commercial real estate industry. Businesses are actively collecting more data than what can be analyzed effectively using the standard spreadsheet models which have become industry standard over the past few decades. Machine learning algorithms are known to be able to extract complex relationship between many variables in data which make them perfect for an application geared towards forecasting the financial performance of commercial real estate assets.

Fractal-element based Magnetic Resonance Imaging Coils for Multi-nuclear Imaging

An MRI (Magnetic Resonance Imaging) scanner is a machine that uses magnets and radio waves to take pictures of the inside the human body without needing to use surgery. An MRI scanner is used to look at things like the brain, liver, heart, and other organs in your body. The scanner uses a “coil” placed near the body to take a picture of that area of the body. This research project uses new shapes of coils to better detect the organs hidden inside. The new shapes of coils can also help detect

Application of Brain 23Na "Big Data" for Future Disease Classification

Sodium is a chemical ion which is essential for a healthy brain. The body naturally regulates its concentration inside and outside of cells through normal metabolism. Disruptions in this intricate balance can be caused by various neurological disorders, such as multiple sclerosis, concussion, or Alzheimer's disease. In order to provide personalized medical care, a "big-data" approach is required whereby an individual's brain can be compared to a standardized template or atlas; unfortunately, a sodium atlas, representing normal sodium concentrations, is not currently available.

Improving 23Na – Magnetic Resonance Spectroscopic Imaging through RF Coil Development

Magnetic Resonance Imaging (MRI) machines use radiowaves and large magnets to safely produce pictures from the insides of the body. The radiowaves are emitted and detected by special antennas that surround the body. Most MRI scanning involves measuring of water in the body. But other atoms, like sodium, can also be seen too. This work described here involves designing new antennas to safely see sodium inside the body. More specifically these antennas will be designed based on novel geometric fractal shapes, which are regularly seen with cell phones.

Evidence-Based Dietary Protein Intake in Canadian Hospitals

Doctors are learning that nutrition plays a very important role in patient outcomes. Research has shown that protein is especially critical to patient health and recovery, especially for the elderly and severely ill. The quality of the protein, and the quantity of protein that patients receive makes a big difference. This project will examine how much Canadian health care centres are concerned about the protein their patients consume.

Pages