Utilizing Graph-Cuts in Image Segmentation to Isolate the Heart within CT Scans

From REU@MU
Revision as of 16:27, 29 June 2018 by Saweiner (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Even for medical professionals with extensive training in X-ray imagery, it can be difficult for the human eye to accurately interpret the information provided by modern day CT scans. Advances in computer vision technology offer an opportunity to reduce the time, effort, and bias that medical professionals contribute to the process of interpreting CT scans. It is our hope that such technology will lead to faster and more accurate diagnoses. As a participant of Marquette's 10-week summer REU program, I will be researching applications of graph-theoretic image segmentation algorithms in the context of CT scans. I hope to complete at least one iteration of an algorithm that, using the graph-cuts method, consistently and successfully segments the heart from the background of CT scans.