Grant: Collaborative Research and Development Grants

Prostate cancer remains the most common cancer diagnosed in men in Canada, with about 25,000 new cases per year. The gold standard for diagnosing this cancer is transrectal ultrasound-guided biopsy followed by pathology. The biopsy procedure is performed by taking eight to 12 tissue samples from the prostate using a standard protocol that is blind to individual patient anatomy or pathology, and has a high rate of false negatives. There is an acute need for image-based targeted biopsy techniques that have higher chance of detecting early stage cancer. In collaboration with our industrial partner, Philips Healthcare, this proposal aims to develop fundamental technologies that will form the basis for improving the detection rate of cancer in ultrasound images. By analyzing subtle variations of backscattered ultrasound signals from a tissue location over a short time span, referred to as ultrasound time series, our group has shown that it is possible to detect physical properties of the underlying tissue within a machine-learning framework. The objective of this NSERC CRD proposal is to understand the physical phenomena governing ultrasound time series interaction with tissue. As a result, this proposal paves the way for a clinically viable commercial product for cancer detection based on ultrasound time series technology. This technology has the potential to positively and rapidly impact the lives of all patients suffering not only from prostate cancer, but also from other types of cancer such as breast and liver cancers.