Predictive value of dose-volume histograms of organs at risk in volumetric modulated arc therapy plans for cervical cancer

Abstract

Objective To investigate the predictive value of dose-volume histograms (DVHs) of organs at risk (OARs) including the bladder, rectum, and small intestine in volumetric modulated arc therapy (VMAT) plans for cervical cancer. Methods A total of 100 VMAT plans for cervical cancer were assigned into the learning group. The correlation of the anatomical information with the V30, V40, and V50 values of the bladder, rectum, and small intestine was evaluated in the group. The support vector regression (SVR) algorithm was used to establish the correspondence between the anatomical information and the DVHs of OARs. The DVHs of OARs in the verification group containing 20 VMAT plans were predicted based on the anatomical information. Results The DVHs of the bladder, rectum, and small intestine were likely to be influenced mainly by the spatial relationship between these OARs and target volume. In the verification group, the prediction errors of V30, V40 and V50 by SVR algorithm were-2.4%±3.5%, -2.5%±3.8%, and-1.5%±4.9% for the bladder, 0.5%±2.6%, -1.5%±5.1%, and-2.0%±7.4% for the rectum, and-2.9%±5.3%, 2.7%±7.7%, and 5.3%±11.1% for the small intestine, respectively. Conclusions After learning the correlation between the anatomical information and the DVHs of OARs from prior VMAT plans for cervical cancer, SVR algorithm can precisely predict the DVHs of the bladder, rectum, and small intestine based on the anatomical information. Key words: Cervical neoplasms/volumetric modulated arc therapy; Dose volume histograms; Support vector regression algorithm