A planning quality evaluation tool for prostate adaptive IMRT based on machine learning.

PURPOSE To ensure plan quality for adaptive IMRT of the prostate, we developed a quantitative evaluation tool using a machine learning approach. This tool generates dose volume histograms (DVHs) of organs-at-risk (OARs) based on prior plans as a reference, to be compared with the adaptive plan derived from fluence map deformation. METHODS Under the same configuration using seven-field 15 MV photon beams, DVHs of OARs (bladder and rectum) were estimated based on anatomical information of the patient and a model learned from a database of high quality prior plans. In this study, the anatomical information was characterized by the organ volumes and distance-to-target histogram (DTH). The database consists of 198 high quality prostate plans and was validated with 14 cases outside the training pool. Principal component analysis (PCA) was applied to DVHs and DTHs to quantify their salient features. Then, support vector regression (SVR) was implemented to establish the correlation between the features of the DVH and the anatomical information. RESULTS DVH/DTH curves could be characterized sufficiently just using only two or three truncated principal components, thus, patient anatomical information was quantified with reduced numbers of variables. The evaluation of the model using the test data set demonstrated its accuracy approximately 80% in prediction and effectiveness in improving ART planning quality. CONCLUSIONS An adaptive IMRT plan quality evaluation tool based on machine learning has been developed, which estimates OAR sparing and provides reference in evaluating ART.

[1]  He Wang,et al.  An automatic CT-guided adaptive radiation therapy technique by online modification of multileaf collimator leaf positions for prostate cancer. , 2005, International journal of radiation oncology, biology, physics.

[2]  J. Mechalakos,et al.  IMRT commissioning: multiple institution planning and dosimetry comparisons, a report from AAPM Task Group 119. , 2009, Medical physics.

[3]  M. Zelefsky,et al.  Principal component, Varimax rotation and cost analysis of volume effects in rectal bleeding in patients treated with 3D-CRT for prostate cancer , 2006, Physics in Medicine and Biology.

[4]  F Nüsslin,et al.  Adapting inverse planning to patient and organ geometrical variation: algorithm and implementation. , 2003, Medical physics.

[5]  G T Chen,et al.  Dose volume histogram analysis of liver radiation tolerance. , 1986, International journal of radiation oncology, biology, physics.

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  J Wong,et al.  The use of adaptive radiation therapy to reduce setup error: a prospective clinical study. , 1998, International journal of radiation oncology, biology, physics.

[8]  D. Yan,et al.  Developing quality assurance processes for image-guided adaptive radiation therapy. , 2008, International journal of radiation oncology, biology, physics.

[9]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[10]  Warren D D'Souza,et al.  The minimum knowledge base for predicting organ-at-risk dose–volume levels and plan-related complications in IMRT planning , 2010, Physics in medicine and biology.

[11]  H. Rehbinder,et al.  Adaptive radiation therapy for compensation of errors in patient setup and treatment delivery. , 2004, Medical physics.

[12]  Di Yan,et al.  Adaptive radiation therapy for prostate cancer. , 2010, Seminars in radiation oncology.

[13]  F. Yin,et al.  Investigation of the support vector machine algorithm to predict lung radiation-induced pneumonitis. , 2007, Medical physics.

[14]  Andrew Jackson,et al.  Geometric factors influencing dosimetric sparing of the parotid glands using IMRT. , 2006, International journal of radiation oncology, biology, physics.

[15]  K. Langen,et al.  Organ motion and its management. , 2001, International journal of radiation oncology, biology, physics.

[16]  Vira Chankong,et al.  Comparison of online IGRT techniques for prostate IMRT treatment: adaptive vs repositioning correction. , 2009, Medical physics.

[17]  R. Cormack,et al.  Automatic online adaptive radiation therapy techniques for targets with significant shape change: a feasibility study , 2006, Physics in medicine and biology.

[18]  Alan Nichol,et al.  Integration of on-line imaging, plan adaptation and radiation delivery: proof of concept using digital tomosynthesis. , 2009, Physics in medicine and biology.

[19]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[20]  Lawrence B Marks,et al.  Integral dose conservation in radiotherapy. , 2009, Medical physics.

[21]  D. Yan,et al.  Adaptive radiation therapy , 1997, Physics in medicine and biology.

[22]  Russell H. Taylor,et al.  Patient geometry-driven information retrieval for IMRT treatment plan quality control. , 2009, Medical physics.

[23]  Di Yan,et al.  Principal component analysis-based pattern analysis of dose-volume histograms and influence on rectal toxicity. , 2007, International journal of radiation oncology, biology, physics.

[24]  Raj Shekhar,et al.  Direct aperture deformation: an interfraction image guidance strategy. , 2006, Medical physics.

[25]  G K Svensson,et al.  A computer-controlled radiation therapy machine for pelvic and para-aortic nodal areas. , 1981, International journal of radiation oncology, biology, physics.

[26]  He Wang,et al.  Use of deformed intensity distributions for on-line modification of image-guided IMRT to account for interfractional anatomic changes. , 2005, International journal of radiation oncology, biology, physics.

[27]  Bernhard Schölkopf,et al.  On a Kernel-Based Method for Pattern Recognition, Regression, Approximation, and Operator Inversion , 1998, Algorithmica.

[28]  Vira Chankong,et al.  On-line re-optimization of prostate IMRT plans for adaptive radiation therapy , 2008, Physics in medicine and biology.