Low Dose Computed Tomography Denoising Using Deep Learning

CT (Computed Tomography) scans are widely used medical images used to diagnose disease such as cancer. CT Scanners pass x-rays through the body in order to generate cross-sectional images. Unfortunately pro-longed exposure to radiation (via x-rays) can damage the body, and thus one aims to minimize the x-ray dose they receive. However, modern CT scanners produce lower quality images when using low x-ray dose which defeats their purpose as a diagnostic tool. We propose a post-processing algorithm to enhance the quality of CT images produced at low radiation dose. The industry and partner organization will benefit from this by integrating this algorithm into products that can be marketed towards radiologists.

Faculty Supervisor:

Javad Alirezaie

Student:

Sepehr Ataei

Partner:

Dr. Paul Babyn Professional Medical Corporation

Discipline:

Engineering - computer / electrical

Sector:

Medical devices

University:

Ryerson University