University of Illinois Urbana-Champaign

Cell classification for imaging-genomics analysis of breast cancer

Moscoso, Miguel

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/2142/91553

Description

Title
Cell classification for imaging-genomics analysis of breast cancer
Author(s)
Moscoso, Miguel
Contributor(s)
Do, Minh N.
Issue Date
2016-05
Keyword(s)
  • imaging-genomics
  • support vector machines
  • computational pathology
Abstract
Imaging-genomics aims to combine two separate medical modalities, imaging and genomics, to obtain more accurate and insightful prognoses. We use breast cancer histopathologic images and their features to determine how they are an expression of the underlying genotype. Our approach is to build an image analysis pipeline that consists of five key steps. First, we segment the image into nuclei and their corresponding cells, from which we extract features describing the cells shape, color, and texture. We then use these features to train a support vector machine classifier to allow for proper labeling of cells, specifically epithelial and stroma cells. The classification of cells allows us to understand spatial layout and morphometry, which are important prognosis indicators. Next, we collect high-level image features, to correlate with genomic data for new understandings and computational prognosis.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/91553

Owning Collections

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