Inference Engine for Skin Cancer Diagnosis
Department
Electrical and Computer Engineering
Major
Computer Engineering and Computer Science
Research Advisor
Shrestha, Bijaya
Moss, Randy Hays, 1953-
Advisor's Department
Electrical and Computer Engineering
Second Advisor's Department
Electrical and Computer Engineering
Funding Source
Missouri S&T Opportunities for Undergraduate Research Experiences (OURE) Program
Abstract
The development of our inference engine began by creating a search engine that would draw information from our knowledge base. It was designed such that when a user provides a description of a skin lesion, corresponding images from our database will be displayed. The search engine was programmed in C++ and the GUI was constructed by using the wxWidgets library. The knowledge gained from this portion of the project was essential for creating our inference engine.
The inference engine determines a diagnosis for a skin lesion by using image processing techniques to search for all features in a given image before comparing them with the dataset. Although accurate results can be obtained from this method, it is often time consuming and unnecessary to search for every feature. We have developed a decision tree algorithm to limit the amount of features searched based on trends in the database.
Biography
Kathryn is a senior at Missouri S&T majoring in computer science and computer engineering. She was born and raised in Mobile, Alabama. After graduating from the Alabama School of Math and Science in 2008, she attended Samford University in Birmingham, Alabama to study trumpet performance, piano performance, and computer science. In 2009, Katie transferred to Missouri S&T so that she could concentrate on computer engineering and computer science. While she was there, she conducted undergraduate research under Dr. Jonathan Kimble, worked with Power and Command and Data Handling on the Missouri S&T Satellite Team, and joined IEEE and ACM. In the future, she wants to continue her research and other personal programming projects, move towards a career involving the development of new technology, and eventually become a successful entrepreneur.
Research Category
Sciences
Presentation Type
Poster Presentation
Document Type
Poster
Location
Upper Atrium/Hallway
Presentation Date
10 Apr 2012, 9:00 am - 11:45 am
Inference Engine for Skin Cancer Diagnosis
Upper Atrium/Hallway
The development of our inference engine began by creating a search engine that would draw information from our knowledge base. It was designed such that when a user provides a description of a skin lesion, corresponding images from our database will be displayed. The search engine was programmed in C++ and the GUI was constructed by using the wxWidgets library. The knowledge gained from this portion of the project was essential for creating our inference engine.
The inference engine determines a diagnosis for a skin lesion by using image processing techniques to search for all features in a given image before comparing them with the dataset. Although accurate results can be obtained from this method, it is often time consuming and unnecessary to search for every feature. We have developed a decision tree algorithm to limit the amount of features searched based on trends in the database.
Comments
Joint project with Vincent Allen and Wenyu Zhou
Third advisor: Stanley, R. Joe, Electrical and Computer Engineering
"