Matthias Söhn1, Markus Alber, Di Yan. 1. Section of Biomedical Physics, University Hospital for Radiation Oncology, Tübingen, Germany. Soehn@med.uni-tuebingen.de
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 approximately 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 ( approximately 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.
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 cancerpatients 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 approximately 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 ( approximately 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.
Authors: Yun Liang; Karen Messer; Brent S Rose; John H Lewis; Steve B Jiang; Catheryn M Yashar; Arno J Mundt; Loren K Mell Journal: Int J Radiat Oncol Biol Phys Date: 2010-05-14 Impact factor: 7.038
Authors: Oscar Acosta; Gael Drean; Juan D Ospina; Antoine Simon; Pascal Haigron; Caroline Lafond; Renaud de Crevoisier Journal: Phys Med Biol Date: 2013-03-26 Impact factor: 3.609
Authors: Juan David Ospina; Frédéric Commandeur; Richard Ríos; Gaël Dréan; Juan Carlos Correa; Antoine Simon; Pascal Haigron; Renaud de Crevoisier; Oscar Acosta Journal: Med Image Comput Comput Assist Interv Date: 2013
Authors: Johanne Hermesse; Sylvie Biver; Nicolas Jansen; Eric Lenaerts; Nathalie De Patoul; Stefaan Vynckier; Philippe Coucke; Pierre Scalliet; Philippe Nickers Journal: Strahlenther Onkol Date: 2009-11-10 Impact factor: 3.621
Authors: S Vivekanandan; D B Landau; N Counsell; D R Warren; A Khwanda; S D Rosen; E Parsons; Y Ngai; L Farrelly; L Hughes; M A Hawkins; J D Fenwick Journal: Int J Radiat Oncol Biol Phys Date: 2017-04-27 Impact factor: 7.038