+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Knowledge‐based planning for intensity‐modulated radiation therapy: A review of data‐driven approaches

      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.



          Intensity‐Modulated Radiation Therapy ( IMRT), including its variations (including IMRT, Volumetric Arc Therapy ( VMAT), and Tomotherapy), is a widely used and critically important technology for cancer treatment. It is a knowledge‐intensive technology due not only to its own technical complexity, but also to the inherently conflicting nature of maximizing tumor control while minimizing normal organ damage. As IMRT experience and especially the carefully designed clinical plan data are accumulated during the past two decades, a new set of methods commonly termed knowledge‐based planning ( KBP) have been developed that aim to improve the quality and efficiency of IMRT planning by learning from the database of past clinical plans. Some of this development has led to commercial products recently that allowed the investigation of KBP in numerous clinical applications. In this literature review, we will attempt to present a summary of published methods of knowledge‐based approaches in IMRT and recent clinical validation results.


          In March 2018, a literature search was conducted in the NIH Medline database using the PubMed interface to identify publications that describe methods and validations related to KBP in IMRT including variations such as VMAT and Tomotherapy. The search criteria were designed to have a broad scope to capture relevant results with high sensitivity. The authors filtered down the search results according to a predefined selection criteria by reviewing the titles and abstracts first and then by reviewing the full text. A few papers were added to the list based on the references of the reviewed papers. The final set of papers was reviewed and summarized here.


          The initial search yielded a total of 740 articles. A careful review of the titles, abstracts, and eventually the full text and then adding relevant articles from reviewing the references resulted in a final list of 73 articles published between 2011 and early 2018. These articles described methods for developing knowledge models for predicting such parameters as dosimetric and dose‐volume points, voxel‐level doses, and objective function weights that improve or automate IMRT planning for various cancer sites, addressing different clinical and quality assurance needs, and using a variety of machine learning approaches. A number of articles reported carefully designed clinical studies that assessed the performance of KBP models in realistic clinical applications. Overwhelming majority of the studies demonstrated the benefits of KBP in achieving comparable and often improved quality of IMRT planning while reducing planning time and plan quality variation.


          The number of KBP‐related studies has been steadily increasing since 2011 indicating a growing interest in applying this approach to clinical applications. Validation studies have generally shown KBP to produce plans with quality comparable to expert planners while reducing the time and efforts to generate plans. However, current studies are mostly retrospective and leverage relatively small datasets. Larger datasets collected through multi‐institutional collaboration will enable the development of more advanced models to further improve the performance of KBP in complex clinical cases. Prospective studies will be an important next step toward widespread adoption of this exciting technology.

          Related collections

          Most cited references 79

          • Record: found
          • Abstract: found
          • Article: not found

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

          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. 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. 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. An adaptive IMRT plan quality evaluation tool based on machine learning has been developed, which estimates OAR sparing and provides reference in evaluating ART.
            • Record: found
            • Abstract: found
            • Article: not found

            Predicting dose-volume histograms for organs-at-risk in IMRT planning.

            The objective of this work was to develop a quality control (QC) tool to reduce intensity modulated radiotherapy (IMRT) planning variability and improve treatment plan quality using mathematical models that predict achievable organ-at-risk (OAR) dose-volume histograms (DVHs) based on individual patient anatomy. A mathematical framework to predict achievable OAR DVHs was derived based on the correlation of expected dose to the minimum distance from a voxel to the PTV surface. OAR voxels sharing a range of minimum distances were computed as subvolumes. A three-parameter, skew-normal probability distribution was used to fit subvolume dose distributions, and DVH prediction models were developed by fitting the evolution of the skew-normal parameters as a function of distance with polynomials. Cohorts of 20 prostate and 24 head-and-neck IMRT plans with identical clinical objectives were used to train organ-specific average models for rectum, bladder, and parotids. A sum of residuals analysis quantifying the integrated difference between the clinically approved DVH and predicted DVH evaluated similarity between DVHs. The ability of the average models to prospectively predict DVHs was evaluated on an independent validation cohort of 20 prostate plans. Statistical comparison of the sums of residuals between training and validation cohorts quantified the accuracy of the average model. Restricted sums of residuals (RSR) were used to identify potential outliers, where large values of RSR indicate a clinical DVH that exceeds the predicted DVH by a considerable amount. A refined model was obtained for each organ by excluding outliers with large RSR values from the training cohort. The refined model was applied to the original training cohort and restricted sums of residuals were utilized to estimate potential DVH improvements. All cases were replanned and evaluated by the physician that approved the original plan. The ability of the refined models to correctly identify outliers was assessed using the residual sum between the original and replanned DVHs to quantify dosimetric gains realized under replanning. Statistical analysis of average sum of residuals for rectum (SR(rectum)=0.003±0.037), bladder (SR(bladder)=-0.008±0.037), and parotid (SR(parotid)=-0.003±0.060) training cohorts yielded mean values near zero and small with respect to the standard deviations, indicating that the average models are capturing the essential behavior of the training cohorts. The predictive abilities of the average rectum and bladder models were statistically indistinguishable between the training and validation sets, with SR(rectum)=0.002±0.044 and SR(bladder)=-0.018±0.058 for the validation set. The refined models' ability to detect outliers and predict achievable OAR DVHs was demonstrated by a strong correlation between predicted gains (RSR) and realized gains after replanning with sample correlation coefficients of r = 0.92 for the rectum, r = 0.88 for the bladder, and r = 0.84 for the parotid glands. The results demonstrate that our mathematical framework and modest training cohorts successfully predict achievable OAR DVHs based on individual patient anatomy. The models correctly identified suboptimal plans that demonstrated further OAR sparing after replanning. This modeling technique requires no manual intervention except for appropriate selection of a training set with identical evaluation criteria. Clinical implementation is in progress to evaluate impact on real-time IMRT QC.
              • Record: found
              • Abstract: found
              • Article: not found

              Quantitative analysis of the factors which affect the interpatient organ-at-risk dose sparing variation in IMRT plans.

              The authors present an evidence-based approach to quantify the effects of an array of patient anatomical features of the planning target volumes (PTVs) and organs-at-risk (OARs) and their spatial relationships on the interpatient OAR dose sparing variation in intensity modulated radiation therapy (IMRT) plans by learning from a database of high-quality prior plans. The authors formulized the dependence of OAR dose volume histograms (DVHs) on patient anatomical factors into feature models which were learned from prior plans by a stepwise multiple regression method. IMRT plans for 64 prostate, 82 head-and-neck (HN) treatments were used to train the models. Two major groups of anatomical features were considered in this study: the volumetric information and the spatial information. The geometry of OARs relative to PTV is represented by the distance-to-target histogram, DTH. Important anatomical and dosimetric features were extracted from DTH and DVH by principal component analysis. The final models were tested by additional 24 prostate and 24 HN plans. Significant patient anatomical factors contributing to OAR dose sparing in prostate and HN IMRT plans have been analyzed and identified. They are: the median distance between OAR and PTV, the portion of OAR volume within an OAR specific distance range, and the volumetric factors: the fraction of OAR volume which overlaps with PTV and the portion of OAR volume outside the primary treatment field. Overall, the determination coefficients R(2) for predicting the first principal component score (PCS1) of the OAR DVH by the above factors are above 0.68 for all the OARs and they are more than 0.53 for predicting the second principal component score (PCS2) of the OAR DVHs except brainstem and spinal cord. Thus, the above set of anatomical features combined has captured significant portions of the DVH variations for the OARs in prostate and HN plans. To test how well these features capture the interpatient organ dose sparing variations in general, the DVHs and specific dose-volume indices calculated from the regression models were compared with the actual DVHs and dose-volume indices from each patient's plan in the validation dataset. The dose-volume indices compared were V99%, V85%, and V50% for bladder and rectum in prostate plans and parotids median dose in HN plans. The authors found that for the bladder and rectum models, 17 out of 24 plans (71%) were within 6% OAR volume error and 21 plans (85%) were within 10% error; For the parotids model, the median dose values for 30 parotids out of 48 (63%) were within 6% prescription dose error and the values in 40 parotids (83%) were within 10% error. Quantitative analysis of patient anatomical features and their correlation with OAR dose sparing has identified a number of important factors that explain significant amount of interpatient DVH variations in OARs. These factors can be incorporated into evidence-based learning models as effective features to provide patient-specific OAR dose sparing goals.

                Author and article information

                Med Phys
                Med Phys
                Medical Physics
                John Wiley and Sons Inc. (Hoboken )
                24 April 2019
                June 2019
                : 46
                : 6 ( doiID: 10.1002/mp.2019.46.issue-6 )
                : 2760-2775
                [ 1 ] Department of Software and Information Systems University of North Carolina at Charlotte Charlotte NC 28223 USA
                [ 2 ] Department of Radiation Oncology Duke University Medical Center Durham NC 27710 USA
                Author notes
                [* ]Author to whom correspondence should be addressed. Electronic mail: jackie.wu@ .
                © 2019 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.

                This is an open access article under the terms of the License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

                Page count
                Figures: 6, Tables: 7, Pages: 16, Words: 10732
                Funded by: NIH/NCI
                Award ID: R01CA201212
                Review Article
                Review Article
                Custom metadata
                June 2019
                Converter:WILEY_ML3GV2_TO_NLMPMC version:5.6.5 mode:remove_FC converted:10.07.2019


                Comment on this article