Knowledge-based Radiation Therapy Research Articles

ICON-P – A double-blind evaluation of quality improvements with individualized CONstraints from low-cost knowledge-based radiation therapy planning in prostate cancer

/Objective(S)A low-cost, prior knowledge-based individualized dose-constraint generator for organs-at-risk has been developed for prostate cancer radiation therapy (RT) planning. In this study, we aimed to evaluate the feasibility and improvements in organs-at-risk (OAR) doses in prostate cancer RT planning using this tool served on a web application. A set of previously treated prostate cancer cases planned and treated with generic constraints were replanned using individualized dose constraints derived from a library of cases with similar volumes of target, OAR, and overlap regions and served on the web-based application. The goal was to assess the reduction in mean dose, specified dose volumes (V59Gy, V56Gy, V53Gy, V47Gy, and V40Gy), and generalized equivalent uniform dose (gEUD) to the rectum and bladder. Planners and assessors were blinded to the initial achieved doses and penalties. Sample size estimation was based on improvement in V53Gy for the rectum and bladder with a paired evaluation. Twenty-four patients were replanned. All the plans had a PTV D95 of at least 97% of the prescribed dose. The individualized OAR constraints could be met for 87.5% of patients for all dose levels. The mean dose, V59Gy, V53Gy, and V47Gy for the bladder was reduced by 7.5Gy, 1.12%, 5.51%, and 10.53% respectively. Similarly for the rectum, the mean dose, V59Gy, V53Gy, V47Gy and was reduced by 5.5Gy, 4.34%, 6.97%, and 11.61% respectively. All dose reductions were statistically significant. The gEUD of the bladder was reduced by 2.47Gy (p<0.001) and the rectum by 3.21Gy (p<0.001). Treatment planning based on individualized dose constraints served on a web application is feasible and leads to improvement at clinically important dose volumes in prostate cancer RT planning. This application can be served publicly for improvements in RT plan quality.

Performance of Knowledge-Based Radiation Therapy Planning for the Glioblastoma Disease Site

The presence of multiple serial organs at risk (OARs) in close proximity to the tumor makes treatment planning for glioblastoma (GBM) complex and time consuming. The present study aimed to create a knowledge-based (KB) radiation therapy model for GBM patients using RapidPlan. An initial model was trained using 82 glioblastoma patients treated with 60Gy in 30 fractions. Plans were created using either volumetric modulated arc therapy (VMAT) or intensity modulated radiation therapy (IMRT). To improve the goodness-of-fit of the model, an intermediate model was generated by using the dose-volume histograms (DVHs) of best spared OARs of the initial model. Using the intermediate model and manual refinement, all 82 cases were replanned, resulting in the final model. The final model was validated on an independent set of 45 patients with GBM, astrocytoma, oligodendroglioma, and meningioma. The plans created by the final model exhibited superior planning target volume (PTV) dose metrics compared with manual clinical plans: ΔD99%=-0.52±0.20Gy, and ΔD1%=0.80±0.13Gy (differences are computed as clinical-model). OAR maximum doses were statistically similar, with improved optic apparatus sparing (ΔDmax=2.78±0.82Gy). Stated improvements correspond to P<.05. The KB planning time is typically 7minutes for IMRT and 13minutes for VMAT, compared with a typical 4hours for manual planning. The KB approach results in significant improvement in planning efficiency and in superior PTV coverage and better normal tissue sparing irrespective of tumor size and location within the brain.

Knowledge-based semi-automated optimization of intensity-modulated radiotherapy plans using a volume modulated arc therapy-configured model

Objective To evaluate the feasibility and dosimetric features of a volume modulated arc therapy (VMAT)-configured model in knowledge-based optimization of fixed-field dynamic intensity-modulated radiotherapy (IMRT) plans based on the Varian RapidPlan system. Methods ① A dose-volume histogram prediction model was trained with 81 qualified preoperative VMAT plans for rectal cancer and then statistically verified. ② For clinically approved 10 IMRT plans with the same dose prescription, the above model was used to automatically generate new optimization parameters and dynamic multileaf collimator (MLC) sequences with field geometry and beam energy unchanged. ③ In order to rule out the disparities between different versions, a single algorithm was used to calculate the absolute doses of the original and new plans. ④ Statistical analyses were performed on dosimetric parameters after comparable target dose coverage was achieved in the two plans by appropriate normalization. Results On the basis of similar target dose homogeneity and coverage, RapidPlan significantly reduced the doses to the urinary bladder (D50% by 9.01 Gy, P=0.000; Dmean by 8.08 Gy, P=0.005) and the femoral head (D50% by 4.20 Gy, P=0.000; Dmean by 3.84 Gy, P=0.005) but significantly elevated the mean total number of monitor units (1211±99 vs. 771±79, P=0.000) and the number of fields with multiple MLC carriage groups. The knowledge-based semi-automated optimization caused a significantly larger number of high-dose hotspots but a similar D2%(52.54 vs. 52.71 Gy, P=0.239). Conclusions The VMAT model can be used for the knowledge-based semi-automated optimization of IMRT plans to enhance the efficiency and OAR protection. However, the resulting high-dose hotspots need further manual intervention. Key words: Knowledge-based radiation therapy; Volume modulated arc treatment; Dose volume histogram; Intensity-modulated radiotherapy; Rectal neoplasms

Comparison of Knowledge Based Radiation Therapy Treatment Plans Against Expert Plans for Prostate VMAT

Comparison of Knowledge Based Radiation Therapy Treatment Plans Against Expert Plans for Prostate VMAT

SU‐E‐P‐58: Dosimetric Study of Conventional Intensity‐Modulated Radiotherapy and Knowledge‐Based Radiation Therapy for Postoperation of Cervix Cancer

Purpose:To compare the dosimetric difference of the target volume and organs at risk(OARs) between conventional intensity‐modulated radiotherapy(C‐IMRT) and knowledge‐based radiation therapy (KBRT) plans for cervix cancer.Methods:39 patients with cervical cancer after surgery were randomly selected, 20 patient plans were used to create the model, the other 19 cases used for comparative evaluation. All plans were designed in Eclipse system. The prescription dose was 30.6Gy, 17 fractions, OARs dose satisfied to the clinical requirement. A paired t test was used to evaluate the differences of dose‐volume histograms (DVH).Results:Comparaed to C‐IMRT plan, the KBRT plan target can achieve the similar target dose coverage, D98,D95,D2,HI and CI had no difference (P≥0.05). The dose of rectum, bladder and femoral heads had no significant differences(P≥0.05). The time was used to design treatment plan was significant reduced.Conclusion:This study shows that postoperative radiotherapy of cervical KBRT plans can achieve the similar target and OARs dose, but the shorter designing time.

SU-E-T-357: Semi-Automated Knowledge-Based Radiation Therapy (KBRT) Planning for Head-And-Neck Cancer (HNC): Can KBRT Plans Achieve Better Results Than Manual Planning?

Purpose: Knowledge Based Radiation Therapy Treatment (KBRT) planning can be used to semi-automatically generate IMRT plans for new patients using constraints derived from previously manually-planned, geometrically similar patients. We investigate whether KBRT plans can achieve greater dose sparing than manual plans using optimized, organspecific constraint weighting factors. Methods: KBRT planning of HNC radiotherapy cases geometrically matched each new (query) case to one of the 105 clinically approved plans in our database. The dose distribution of the planned match was morphed to fit the querys geometry. Dose-volume constraints extracted from the morphed dose distribution were used to run the IMRT optimization with no user input. In the first version, all constraints were multiplied by a weighting factor of 0.7. The weighting factors were then systematically optimized (in order of OARs with increasing separation from the target) to maximize sparing to each OAR without compromising other OARs. The optimized, second version plans were compared against the first version plans and the clinically approved plans for 45 unilateral/bilateral target cases using the dose metrics: mean, median and maximum (brainstem and cord) doses. Results: Compared to the first version, the second version significantly reduced mean/median contralateral parotid doses (>2Gy) for bilateral cases. Other changes between the two versions were not clinically meaningful. Compared to the original clinical plans, both bilateral and unilateral plans in the second version had lower average dose metrics for 5 of the 6 OARs. Compared to the original plans, the second version achieved dose sparing that was at least as good for all OARs and better for the ipsilateral parotid (bilateral) and oral cavity (bilateral/unilateral). Differences in planning target volume coverage metrics were not clinically significant. Conclusion: HNC-KBRT planning generated IMRT plans with at least equivalent dose sparing to manually generated plans; greater dose sparing was achieved in selected OARs.

TU‐C‐17A‐09: Multi‐Case Knowledge‐Based IMRT Treatment Planning in Head and Neck Cancer: Are Six Heads Better Than One?

Purpose:HNC IMRT treatment planning is a challenging process that relies heavily on the planner’s experience. Previously, we used the single, best match from a library of manually planned cases to semi‐automatically generate IMRT plans for a new patient. The current multi‐case Knowledge Based Radiation Therapy (MC‐KBRT) study utilized different matching cases for each of six individual organs‐at‐risk (OARs), then combined those six cases to create the new treatment plan.Methods:From a database of 103 patient plans created by experienced planners, MC‐KBRT plans were created for 40 (17 unilateral and 23 bilateral) HNC “query” patients. For each case, 2D beam’s‐eye‐view images were used to find similar geometric “match” patients separately for each of 6 OARs. Dose distributions for each OAR from the 6 matching cases were combined and then warped to suit the query case’s geometry. The dose‐volume constraints were used to create the new query treatment plan without the need for human decision‐making throughout the IMRT optimization. The optimized MC‐KBRT plans were compared against the clinically approved plans and Version 1 (original KBRT) using the dose metrics: mean, median, and maximum (brainstem and cord+5mm) doses.Results:Compared to Version 1, MC‐KBRT had no significant reduction of the dose to any of the OARs in either unilateral/bilateral cases. Compared to the manually‐planned unilateral cases, there was significant reduction of the oral cavity mean/median dose (&gt;2Gy) at the expense of the contralateral parotid. Compared to the manually‐planned bilateral cases, reduction of dose was significant in the ipsilateral parotid, larynx, and oral cavity (&gt;3Gy mean/median) while maintaining PTV coverage.Conclusion:MC‐KBRT planning in head and neck cancer generates IMRT plans with equivalent dose sparing to manually created plans. MC‐KBRT using multiple case matches does not show significant dose reduction compared to using a single match case with dose warping.