Share Email Print

Journal of Medical Imaging

Forecasting new development of tumor areas using spatial and temporal distribution profiles of hemoglobin saturation in a mouse model
Author(s): Miguel R. Ossandon; Dhananjay S. Phatak; Brian S. Sorg; Konstantinos Kalpakis
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Features of the tumor microenvironment (TME), such as hemoglobin saturation (HbSat), can provide valuable information on early development and progression of tumors. HbSat correlates with high metabolism and precedes the formation of angiogenic tumors; therefore, changes in HbSat profile can be used as a biomarker for early cancer detection. In this project, we develop a methodology to evaluate HbSat for forecasting early tumor development in a mouse model. We built a delta (δ ) cumulative feature that includes spatial and temporal distribution of HbSat for classifying tumor/normal areas. Using a two-class (normal and tumor) logistic regression, the δ feature successfully forecasts tumor areas in two window chamber mice (AUC=0.90 and 0.85). To assess the performance of the logistic regression-based classifier utilizing the δ feature of each region, we conduct a 10-fold cross-validation analysis (AUC of the ROC=0.87 ). These results show that the TME features based on HbSat can be used to evaluate tumor progression and forecast new occurrences of tumor areas.

Paper Details

Date Published: 20 June 2014
PDF: 9 pages
J. Med. Img. 1(1) 014503 doi: 10.1117/1.JMI.1.1.014503
Published in: Journal of Medical Imaging Volume 1, Issue 1
Show Author Affiliations
Miguel R. Ossandon, Univ. of Maryland, Baltimore County (United States)
National Cancer Institute (United States)
Dhananjay S. Phatak, Univ. of Maryland, Baltimore County (United States)
Brian S. Sorg, National Cancer Institute (United States)
Konstantinos Kalpakis, Univ. of Maryland, Baltimore County (United States)

© SPIE. Terms of Use
Back to Top