skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Principal Component Analysis-Based Pattern Analysis of Dose-Volume Histograms and Influence on Rectal Toxicity

Abstract

Purpose: The variability of dose-volume histogram (DVH) shapes in a patient population can be quantified using principal component analysis (PCA). We applied this to rectal DVHs of prostate cancer patients and investigated the correlation of the PCA parameters with late bleeding. Methods and Materials: PCA was applied to the rectal wall DVHs of 262 patients, who had been treated with a four-field box, conformal adaptive radiotherapy technique. The correlated changes in the DVH pattern were revealed as 'eigenmodes,' which were ordered by their importance to represent data set variability. Each DVH is uniquely characterized by its principal components (PCs). The correlation of the first three PCs and chronic rectal bleeding of Grade 2 or greater was investigated with uni- and multivariate logistic regression analyses. Results: Rectal wall DVHs in four-field conformal RT can primarily be represented by the first two or three PCs, which describe {approx}94% or 96% of the DVH shape variability, respectively. The first eigenmode models the total irradiated rectal volume; thus, PC1 correlates to the mean dose. Mode 2 describes the interpatient differences of the relative rectal volume in the two- or four-field overlap region. Mode 3 reveals correlations of volumes with intermediate doses ({approx}40-45 Gy) andmore » volumes with doses >70 Gy; thus, PC3 is associated with the maximal dose. According to univariate logistic regression analysis, only PC2 correlated significantly with toxicity. However, multivariate logistic regression analysis with the first two or three PCs revealed an increased probability of bleeding for DVHs with more than one large PC. Conclusions: PCA can reveal the correlation structure of DVHs for a patient population as imposed by the treatment technique and provide information about its relationship to toxicity. It proves useful for augmenting normal tissue complication probability modeling approaches.« less

Authors:
 [1];  [1];  [2]
  1. Section of Biomedical Physics, University Hospital for Radiation Oncology, Tuebingen (Germany)
  2. Department of Radiation Oncology, William Beaumont Hospital, Royal Oak, MI (United States)
Publication Date:
OSTI Identifier:
21036220
Resource Type:
Journal Article
Journal Name:
International Journal of Radiation Oncology, Biology and Physics
Additional Journal Information:
Journal Volume: 69; Journal Issue: 1; Other Information: DOI: 10.1016/j.ijrobp.2007.04.066; PII: S0360-3016(07)00795-X; Copyright (c) 2007 Elsevier Science B.V., Amsterdam, The Netherlands, All rights reserved; Country of input: International Atomic Energy Agency (IAEA); Journal ID: ISSN 0360-3016
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; CARCINOMAS; CORRELATIONS; IRRADIATION; MULTIVARIATE ANALYSIS; PATIENTS; POLAR-CAP ABSORPTION; PROSTATE; RADIATION DOSES; RADIOTHERAPY; RECTUM; REGRESSION ANALYSIS; TOXICITY

Citation Formats

Soehn, Matthias, Alber, Markus, and Di, Yan. Principal Component Analysis-Based Pattern Analysis of Dose-Volume Histograms and Influence on Rectal Toxicity. United States: N. p., 2007. Web. doi:10.1016/j.ijrobp.2007.04.066.
Soehn, Matthias, Alber, Markus, & Di, Yan. Principal Component Analysis-Based Pattern Analysis of Dose-Volume Histograms and Influence on Rectal Toxicity. United States. https://doi.org/10.1016/j.ijrobp.2007.04.066
Soehn, Matthias, Alber, Markus, and Di, Yan. 2007. "Principal Component Analysis-Based Pattern Analysis of Dose-Volume Histograms and Influence on Rectal Toxicity". United States. https://doi.org/10.1016/j.ijrobp.2007.04.066.
@article{osti_21036220,
title = {Principal Component Analysis-Based Pattern Analysis of Dose-Volume Histograms and Influence on Rectal Toxicity},
author = {Soehn, Matthias and Alber, Markus and Di, Yan},
abstractNote = {Purpose: The variability of dose-volume histogram (DVH) shapes in a patient population can be quantified using principal component analysis (PCA). We applied this to rectal DVHs of prostate cancer patients and investigated the correlation of the PCA parameters with late bleeding. Methods and Materials: PCA was applied to the rectal wall DVHs of 262 patients, who had been treated with a four-field box, conformal adaptive radiotherapy technique. The correlated changes in the DVH pattern were revealed as 'eigenmodes,' which were ordered by their importance to represent data set variability. Each DVH is uniquely characterized by its principal components (PCs). The correlation of the first three PCs and chronic rectal bleeding of Grade 2 or greater was investigated with uni- and multivariate logistic regression analyses. Results: Rectal wall DVHs in four-field conformal RT can primarily be represented by the first two or three PCs, which describe {approx}94% or 96% of the DVH shape variability, respectively. The first eigenmode models the total irradiated rectal volume; thus, PC1 correlates to the mean dose. Mode 2 describes the interpatient differences of the relative rectal volume in the two- or four-field overlap region. Mode 3 reveals correlations of volumes with intermediate doses ({approx}40-45 Gy) and volumes with doses >70 Gy; thus, PC3 is associated with the maximal dose. According to univariate logistic regression analysis, only PC2 correlated significantly with toxicity. However, multivariate logistic regression analysis with the first two or three PCs revealed an increased probability of bleeding for DVHs with more than one large PC. Conclusions: PCA can reveal the correlation structure of DVHs for a patient population as imposed by the treatment technique and provide information about its relationship to toxicity. It proves useful for augmenting normal tissue complication probability modeling approaches.},
doi = {10.1016/j.ijrobp.2007.04.066},
url = {https://www.osti.gov/biblio/21036220}, journal = {International Journal of Radiation Oncology, Biology and Physics},
issn = {0360-3016},
number = 1,
volume = 69,
place = {United States},
year = {Sat Sep 01 00:00:00 EDT 2007},
month = {Sat Sep 01 00:00:00 EDT 2007}
}