University of Illinois Urbana-Champaign

Breast Cancer Detection through Hyperspectral Image Analysis and Machine Learning

Parawira, Sander; Brady, Spencer

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/47447

Description

Title
Breast Cancer Detection through Hyperspectral Image Analysis and Machine Learning
Author(s)
  • Parawira, Sander
  • Brady, Spencer
Contributor(s)
Do, Minh N.
Issue Date
2008-12
Keyword(s)
  • cancer detection
  • breast cancer detection
  • medical imaging
  • image analysis
  • hyperspectral image analysis
  • spectroscopy
  • Fourier transform infrared spectroscopy
Abstract
In this paper, we present a machine learning technique in hyperspectral image analysis for breast cancer detection. We consider the scenario where a band sequential image of a breast tissue specimen is collected using Fourier transform infrared (FTIR) spectroscopy. Our goal is to determine which parts of the image correspond to epithelium cells and which parts of the image correspond to stoma cells. We first discuss spectrum (band) selection and Principal Component Analysis (PCA) to reduce the dimensionality of the image. We then discuss Euclidean Distance and implemention of K-Means Clustering algorithm for data set represented as points in a high dimensional space. We finally add noise to the image and discuss the robustness of our technique.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/47447

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research