Dataset Information

Implementation of a Knowledge-Based Treatment Planning Model for Cardiac-Sparing Lung Radiation Therapy.

ABSTRACT:

Purpose

High radiation doses to the heart have been correlated with poor overall survival in patients receiving radiation therapy for stage III non-small cell lung cancer (NSCLC). We built a knowledge-based planning (KBP) tool to limit the dose to the heart during creation of volumetric modulated arc therapy (VMAT) treatment plans for patients being treated to 60 Gy in 30 fractions for stage III NSCLC.

Methods and materials

A previous study at our institution retrospectively delineated intracardiac volumes and optimized VMAT treatment plans to reduce dose to these substructures and to the whole heart. Two RapidPlan (RP) KBP models were built from this cohort, 1 model using the clinical plans and a separate model using the cardiac-optimized plans. Using target volumes and 6 organs at risk (OARs), models were trained to generate treatment plans in a semiautomated process. The cardiac-sparing KBP model was tested in the same cohort used for training, and both models were tested on an external validation cohort of 30 patients.

Results

Both RP models produced clinically acceptable plans in terms of target coverage, dose uniformity, and dose to OARs. Compared with the previously created cardiac-optimized plans, cardiac-sparing RPs showed significant reductions in the mean dose to the esophagus and lungs while performing similarly or better in all evaluated heart dose metrics. When comparing the 2 models, the cardiac-sparing RP showed reduced (P < .05) heart mean and maximum doses as well as volumes receiving 60 Gy, 50 Gy, and 30 Gy.

Conclusions

By using a set of cardiac-optimized treatment plans for training, the proposed KBP model provided a means to reduce the dose to the heart and its substructures without the need to explicitly delineate cardiac substructures. This tool may offer reduced planning time and improved plan quality and might be used to improve patient outcomes.

SUBMITTER: Harms J

PROVIDER: S-EPMC8463738 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Recent research efforts investigating dose escalation techniques for three-dimensional conformal radiation therapy (3D CRT) and intensity modulated radiation therapy (IMRT) have demonstrated great benefit when high-dose hypofractionated treatment schemes are implemented. The use of these paradigms emphasizes the importance of smaller treatment margins to avoid high dose to surrounding normal tissue or organs at risk (OARs). However, tighter margins may lead to underdosage of the target due to the presence of organ motion. It is important to characterize organ motion and possibly account for it during treatment delivery. The need for real-time localization of dynamic targets has encouraged the use and development of more continuous motion monitoring systems such as kilo-voltage/fluoroscopic imaging, electromagnetic tracking, and optical monitoring systems.This paper presents the implementation of an algorithm to quantify translational and rotational interfractional and intrafractional prostate motion and compute the dosimetric effects of these motion patterns. The estimated delivered dose is compared with the static plan dose to evaluate the success of delivering the plan in the presence of prostate motion. The method is implemented on a commercial treatment planning system (Pinnacle(3), Philips Radiation Oncology Systems, Philips Healthcare) and is termed delivered dose investigational tool (DiDIT). The DiDIT implementation in Pinnacle(3) is validated by comparisons with previously published results. Finally, different workflows are discussed with respect to the potential use of this tool in clinical treatment planning.The DiDIT dose estimation process took approximately 5-20 min (depending on the number of fractions analyzed) on a Pinnacle(3) 9.100 research version running on a Dell M90 system (Dell, Inc., Round Rock, TX, USA) equipped with an Intel Core 2 Duo processor (Intel Corporation, Santa Clara, CA, USA). The DiDIT implementation in Pinnacle(3) was found to be in agreement with previously published results, on the basis of the percent dose difference (PDD). This metric was also utilized to compare plan dose versus delivered dose, for prostate targets in three clinically acceptable treatment plans.This paper presents results from the implementation of an algorithm on a commercially available treatment planning system that quantifies the dosimetric effects of interfractional and intrafractional motion in external beam radiation therapy (EBRT) of prostate cancer. The implementation of this algorithm within a commercial treatment planning system such as Pinnacle(3) enables easy deployment in the existing clinical workflow. The results of the PDD tests validate the implementation of the DiDIT algorithm in Pinnacle(3), in comparison with previously published results.

Project description:To introduce a method to efficiently identify and calculate meaningful tradeoffs between criteria in an interactive IMRT treatment planning procedure. The method provides a systematic approach to developing high-quality radiation therapy treatment plans.Treatment planners consider numerous dosimetric criteria of varying importance that, when optimized simultaneously through multicriteria optimization, yield a Pareto frontier which represents the set of Pareto-optimal treatment plans. However, generating and navigating this frontier is a time-consuming, nontrivial process. A lexicographic ordering (LO) approach to IMRT uses a physician's criteria preferences to partition the treatment planning decisions into a multistage treatment planning model. Because the relative importance of criteria optimized in the different stages may not necessarily constitute a strict prioritization, the authors introduce an interactive process, sensitivity analysis in lexicographic ordering (SALO), to allow the treatment planner control over the relative sequential-stage tradeoffs. By allowing this flexibility within a structured process, SALO implicitly restricts attention to and allows exploration of a subset of the Pareto efficient frontier that the physicians have deemed most important.Improvements to treatment plans over a LO approach were found by implementing the SALO procedure on a brain case and a prostate case. In each stage, a physician assessed the tradeoff between previous stage and current stage criteria. The SALO method provided critical tradeoff information through curves approximating the relationship between criteria, which allowed the physician to determine the most desirable treatment plan.The SALO procedure provides treatment planners with a directed, systematic process to treatment plan selection. By following a physician's prioritization, the treatment planner can avoid wasting effort considering clinically inferior treatment plans. The planner is guided by criteria importance, but given the information necessary to accurately adjust the relative importance at each stage. Through these attributes, the SALO procedure delivers an approach well balanced between efficiency and flexibility.

Project description:PurposeThis work aims to study the generalizability of a pre-developed deep learning (DL) dose prediction model for volumetric modulated arc therapy (VMAT) for prostate cancer and to adapt the model, via transfer learning with minimal input data, to three different internal treatment planning styles and one external institution planning style.MethodsWe built the source model with planning data from 108 patients previously treated with VMAT for prostate cancer. For the transfer learning, we selected patient cases planned with three different styles, 14-29 cases per style, in the same institution and 20 cases treated in a different institution to adapt the source model to four target models in total. We compared the dose distributions predicted by the source model and the target models with the corresponding clinical plan dose used for patient treatments and quantified the improvement in the prediction quality for the target models over the source model using the Dice similarity coefficients (DSC) of 0% to 100% isodose volumes and the dose-volume-histogram (DVH) parameters of the planning target volume and the organs-at-risk.ResultsThe source model accurately predicts dose distributions for plans generated in the same source style, but performs sub-optimally for the three different internal and one external target styles, with the mean DSC ranging between 0.81-0.94 and 0.82-0.91 for the internal and the external styles, respectively. With transfer learning, the target model predictions improved the mean DSC to 0.88-0.95 and 0.92-0.96 for the internal and the external styles, respectively. Target model predictions significantly improved the accuracy of the DVH parameter predictions to within 1.6%.ConclusionWe demonstrated the problem of model generalizability for DL-based dose prediction and the feasibility of using transfer learning to solve this problem. With 14-29 cases per style, we successfully adapted the source model into several different practice styles. This indicates a realistic way forward to widespread clinical implementation of DL-based dose prediction.

Project description:To determine clinically helpful dose-volume and clinical metrics correlating with symptomatic radiation pneumonitis (RP) in malignant pleural mesothelioma (MPM) patients with 2 lungs treated with hemithoracic intensity modulated pleural radiation therapy (IMPRINT).Treatment plans and resulting normal organ dose-volume histograms of 103 consecutive MPM patients treated with IMPRINT (February 2005 to January 2015) to the highest dose ?50.4 Gy satisfying departmental normal tissue constraints were uniformly recalculated. Patient records provided maximum RP grade (Common Terminology Criteria for Toxicity and Adverse Event version 4.0) and clinical and demographic information. Correlations analyzed with the Cox model were grade ?2 RP (RP2+) and grade ?3 RP (RP3+) with clinical variables, with volumes of planning target volume (PTV) and PTV-lung overlap and with mean dose, percent volume receiving dose D (VD), highest dose encompassing % volume V, (DV), and heart, total, ipsilateral, and contralateral lung volumes.Twenty-seven patients had RP2+ (14 with RP3+). The median prescription dose was 46.8 Gy (39.6-50.4 Gy, 1.8 Gy/fraction). The median age was 67.6 years (range, 42-83 years). There were 79 men, 40 never-smokers, and 44 with left-sided MPM. There were no significant (P?.05) correlations with clinical variables, prescription dose, total lung dose-volume metrics, and PTV-lung overlap volume. Dose-volume correlations for heart were RP2+ with VD (35 ? D ? 47 Gy, V43 strongest at P=.003), RP3+ with VD (31 ? D ? 45 Gy), RP2+ with DV (5 ? V ? 30%), RP3+ with DV (15 ? V ? 35%), and mean dose. Significant for ipsilateral lung were RP2+ with VD (38 ? D ? 44 Gy), RP3+ with V41, RP2+ and RP3+ with minimum dose, and for contralateral lung, RP2+ with maximum dose. Correlation of PTV with RP2+ was strong (P<.001) and also significant with RP3+.Heart dose correlated strongly with symptomatic RP in this large cohort of MPM patients with 2 lungs treated with IMPRINT. Planning constraints to reduce future heart doses are suggested.