Robust Magnetic Resonance Imaging of Short T2 Tissues

Magnetic resonance imaging (MRI) is an imaging modality which can visualize the internal structure of the human body and is free of radiation. In this project, we would like to write a multi-functional and robust MRI software package using ultrashort echo time (UTE) technique to realize the imaging of the tissues, such as tendons, ligaments, and cortical bone, which are difficult to view through conventional MRI techniques.

Using multivariate deep-learning algorithms for automatic quality control of high-resolution MRI - Year two

NeuroRx is an imaging contract research organization (CRO) specialized in the central nervous system (CNS) that utilizes state-of-the-art digital image processing techniques to produce accurate and precise outcome measures for clinical trials of drugs in development. Prior to analysis, all scans must pass Quality Control (QC). The goal of this project will be to incorporate advanced computer algorithms to automatically classify the quality of high-resolution structural brain Magnetic Resonance Images. The advanced computer algorithms will include deep learning algorithms.

Improving Signal Prediction of a Real-time Radiotherapy Beam Monitor using Artificial Neural Network

The science and technology of Radiotherapy for treating cancerous tumor more accurately and precisely is improving constantly with the availability of cutting-edge imaging systems in Radiation Treatment room, and advancements in computer technologies. However, these improvements are associated with complexities and potential risks. To mitigate the risks, a new class of Quality Assurance (QA) systems are emerging.

Development of a simulation model for prediction of performance of a novel positive airway pressure (PAP) machine for treatment of sleep apnea

The gold standard of treatment for patients with sleep apnea are Positive-airway-pressure (PAP) machines. PAPs provide a one-size-fits-all solution of providing the same therapy in terms of airflow to every patient and every breath. This causes frustration and discomfort for patients, therefore patients don’t purchase PAPs or purchase and don’t use them; leading to 4 times higher chances of stroke and 3 times higher chances of heart attacks as well as huge costs on the healthcare system.

Development and Validation of Software for the Three-dimensional Quantification and Visualization of Blood Flow Hemodynamics in Patients with Aortic Insufficiency using 4D flow MRI. Year 2

The aim of this proposal is to assist in the development and validation of a dedicated 4D flow MRI analysis software for the evaluation of aortic valve insufficiency. Before being commercialized this software requires validation considering the large amount of data required to be pre-processed (over 2,000 files per case), elemental data corrections, data analysis preparation, data analysis algorithms, and 3D visualization.

Development of Smart Socks To Prevent Diabetic Foot Ulcers

Diabetic patients suffer from reduced sensation in their foot which will be leading to foot ulcers that are hard to treat, and often resulting in limb amputation. The existing health-care techniques usually fail to prevent foot ulcers because they cannot monitor the foot in real-time. In this work, we seek to develop smart socks based on textile technology to help patients to artificially feel sensory stimuli that they cannot realistically feel.

Self-powered microchips for rapid diagnosis and severity determination of urinary tract infections

Children presenting a fever without known sources are usually checked for bacterial urinary tract infection (UTI) which, in its more complicated forms, can result in permanent kidney damage. The gold standard conventional tests to diagnose complicated urinary tract infections are urine culture and kidney imaging with a radioactive tracer. However, these tests are lengthy (urine culture can take up to 48 hours to provide results) and expensive.

Multi-user Training Software Development and Otoscope Tracking for Otolaryngology Education

Simulation is being used increasingly to improve medical education by providing students and trainees with greater access and opportunity to learn critical skills without affecting actual patient care. To this end, OtoSim has developed a multi-user training platform and an otoscope tracking device. The multi-user training platform allows the trainee to self-learn while being electronically connected to a central database for monitoring and advice.

Automated CNC processing of complex and high-aspect-ratio microfluidic devices for biomedical applications

Disposable microfluidic devices, also known as labs-on-a-chip, made out of plastic materials have seen increasing applications in chemical and biomedical analysis. In most applications, microfluidic devices usually incorporate small channels and chambers for micro sized dimensions, using heights between a few hundred to a few micrometers. Currently, manufacturing processes have been established to create these sub-millimeter deep features. However, in other applications, higher (or deeper) features of a few millimeters may be needed.

10 Channel Prototype to 16 Channel Medical Grade EEG Headset

Epilepsy affects an estimated 50 million people worldwide. These people can experience unexpected seizures that makes it risky for them to engage in everyday activities like driving and walking. A portable wireless neuromonitoring headset prototype that is worn on the head has been developed by Avertus Inc. to address this issue. The headset is designed to read brain waves, and, through a wireless connection to a cell phone, warn the wearer that the device has measured brain activity characteristic with an oncoming seizure.