Evaluation of dual-arc VMAT radiotherapy treatment plans automatically generated via dose mimicking

Comparison of volumetric modulated arc therapy and helical tomotherapy for prostate cancer using Pareto fronts

BACKGROUND

Studies comparing different radiotherapy treatment techniques-such as volumetric modulated arc therapy (VMAT) and helical tomotherapy (HT)-typically compare one treatment plan per technique. Often, some dose metrics favor one plan and others favor the other, so the final plan decision involves subjective preferences. Pareto front comparisons provide a more objective framework for comparing different treatment techniques. A Pareto front is the set of all treatment plans where improvement in one criterion is possible only by worsening another criterion. However, different Pareto fronts can be obtained depending on the chosen machine settings.

PURPOSE

To compare VMAT and HT using Pareto fronts and blind expert evaluation, to explain the observed differences, and to illustrate limitations of using Pareto fronts.

METHODS

We generated Pareto fronts for twenty-four prostate cancer patients treated at our clinic for VMAT and HT techniques using an in-house script that controlled a commercial treatment planning system. We varied the PTV under-coverage (100% - V95%) and the rectum mean dose, and fixed the mean doses to the bladder and femoral heads. In order to ensure a fair comparison, those fixed mean doses were the same for the two treatment techniques and the sets of objective functions were chosen so that the conformity indexes of the two treatment techniques were also the same. We used the same machine settings as are used in our clinic. Then, we compared the VMAT and HT Pareto fronts using a specific metric (clinical distance measure) and validated the comparison using a blinded expert evaluation of treatment plans on these fronts for all patients in the cohort. Furthermore, we investigated the observed differences between VMAT and HT and pointed out limitations of using Pareto fronts.

RESULTS

Both clinical distance and blind treatment plan comparison showed that VMAT Pareto fronts were better than HT fronts. VMAT fronts for 10 and 6 MV beam energy were almost identical. HT fronts improved with different machine settings, but were still inferior to VMAT fronts.

CONCLUSIONS

That VMAT Pareto fronts are better than HT fronts may be explained by the fact that the linear accelerator can rapidly vary the dose rate. This is an advantage in simple geometries that might vanish in more complex geometries. Furthermore, one should be cautious when speaking about Pareto optimal plans as the best possible plans, as their calculation depends on many parameters.

Comparison of Ethos template-based planning and AI-based dose prediction: General performance, patient optimality, and limitations

PURPOSE

Ethos proposes a template-based automatic dose planning (Etb) for online adaptive radiotherapy. This study evaluates the general performance of Etb for prostate cancer, as well as the ability to generate patient-optimal plans, by comparing it with another state-of-the-art automatic planning method, i.e., deep learning dose prediction followed by dose mimicking (DP + DM).

MATERIALS

General performances and capability to produce patient-optimal plan were investigated through two studies: Study-S1 generated plans for 45 patients using our initial Ethos clinical goals template (EG_init), and compared them to manually generated plans (MG). For study-S2, 10 patients which showed poor performances at study-S1 were selected. S2 compared the quality of plans generated with four different methods: 1) Ethos initial template (EG_init_selected), 2) Ethos updated template-based on S1 results (EG_upd_selected), 3) DP + DM, and 4) MG plans.

RESULTS

EG_init plans showed satisfactory performance for dose level above 50 Gy: reported mean metrics differences (EG_init minus MG) never exceeded 0.6 %. However, lower dose levels showed loosely optimized metrics, mean differences for V30Gy to rectum and V20Gy to anal canal were of 6.6 % and 13.0 %. EG_init_selected showed amplified differences in V30Gy to rectum and V20Gy to anal canal: 8.5 % and 16.9 %, respectively. These dropped to 5.7 % and 11.5 % for EG_upd_selected plans but strongly increased V60Gy to rectum for 2 patients. DP + DM plans achieved differences of 3.4 % and 4.6 % without compromising any V60Gy.

CONCLUSION

General performances of Etb were satisfactory. However, optimizing with template of goals might be limiting for some complex cases. Over our test patients, DP + DM outperformed the Etb approach.

Influence of optimisation parameters on directly deliverable Pareto fronts explored for prostate cancer

PURPOSE

In inverse radiotherapy treatment planning, the Pareto front is the set of optimal solutions to the multi-criteria problem of adequately irradiating the planning target volume (PTV) while reducing dose to organs at risk (OAR). The Pareto front depends on the chosen optimisation parameters whose influence (clinically relevant versus not clinically relevant) is investigated in this paper.

METHODS

Thirty-one prostate cancer patients treated at our clinic were randomly selected. We developed an in-house Python script that controlled the commercial treatment planning system RayStation to calculate directly deliverable Pareto fronts. We calculated reference Pareto fronts for a given set of objective functions, varying the PTV coverage and the mean dose of the primary OAR (rectum) and fixing the mean doses of the secondary OARs (bladder and femoral heads). We calculated the fronts for different sets of objective functions and different mean doses to secondary OARs. We compared all fronts using a specific metric (clinical distance measure).

RESULTS

The in-house script was validated for directly deliverable Pareto front calculations in two and three dimensions. The Pareto fronts depended on the choice of objective functions and fixed mean doses to secondary OARs, whereas the parameters most influencing the front and leading to clinically relevant differences were the dose gradient around the PTV, the weight of the PTV objective function, and the bladder mean dose.

CONCLUSIONS

Our study suggests that for multi-criteria optimisation of prostate treatments using external therapy, dose gradient around the PTV and bladder mean dose are the most influencial parameters.

Evaluation of the clinical value of automatic online dose restoration for adaptive proton therapy of head and neck cancer

INTRODUCTION

Intensity modulated proton therapy (IMPT) is highly sensitive to anatomical variations which can cause inadequate target coverage during treatment. This study compares not-adapted (NA) robust plans to two adaptive IMPT methods - a fully-offline adaptive (FOA) and a simplified automatic online adaptive strategy (dose restoration (DR)) to determine the benefit of DR, in head and neck cancer (HNC).

MATERIAL/METHODS

Robustly optimized clinical IMPT doses in planning-CTs (pCTs) were available for a cohort of 10 HNC patients. During robust re-optimization, DR used isodose contours, generated from the clinical dose on pCTs, and patient specific objectives to reproduce the clinical dose in every repeated-CT(rCT). For each rCT(n=50), NA, DR and FOA plans were robustly evaluated.

RESULTS

An improvement in DVH-metrics and robustness was seen for DR and FOA plans compared to NA plans. For NA plans, 74%(37/50) of rCTs did not fulfill the CTV coverage criteria (D98%>95%Dprescription). DR improved target coverage, target homogeneity and variability on critical risk organs such as the spinal cord. After DR, 52%(26/50) of rCTs met all clinical goals. Because of large anatomical changes and/or inaccurate patient repositioning, 48%(24/50) of rCTs still needed full offline adaptation to ensure an optimal treatment since dose restoration was not able to re-establish the initial plan quality.

CONCLUSION

Robust optimization together with fully-automatized DR avoided offline adaptation in 52% of the cases. Implementation of dose restoration in clinical routine could ensure treatment plan optimality while saving valuable human and material resources to radiotherapy departments.

Clinical evaluation of two AI models for automated breast cancer plan generation

Background

Artificial intelligence (AI) shows great potential to streamline the treatment planning process. However, its clinical adoption is slow due to the limited number of clinical evaluation studies and because often, the translation of the predicted dose distribution to a deliverable plan is lacking. This study evaluates two different, deliverable AI plans in terms of their clinical acceptability based on quantitative parameters and qualitative evaluation by four radiation oncologists.

Methods

For 20 left-sided node-negative breast cancer patients, treated with a prescribed dose of 40.05 Gy, using tangential beam intensity modulated radiotherapy, two model-based treatment plans were evaluated against the corresponding manual plan. The two models used were an in-house developed U-net model and a vendor-developed contextual atlas regression forest model (cARF). Radiation oncologists evaluated the clinical acceptability of each blinded plan and ranked plans according to preference. Furthermore, a comparison with the manual plan was made based on dose volume histogram parameters, clinical evaluation criteria and preparation time.

Results

The U-net model resulted in a higher average and maximum dose to the PTV (median difference 0.37 Gy and 0.47 Gy respectively) and a slightly higher mean heart dose (MHD) (0.01 Gy). The cARF model led to higher average and maximum doses to the PTV (0.30 and 0.39 Gy respectively) and a slightly higher MHD (0.02 Gy) and mean lung dose (MLD, 0.04 Gy). The maximum MHD/MLD difference was ≤ 0.5 Gy for both AI plans. Regardless of these dose differences, 90–95% of the AI plans were considered clinically acceptable versus 90% of the manual plans. Preferences varied between the radiation oncologists. Plan preparation time was comparable between the U-net model and the manual plan (287 s vs 253 s) while the cARF model took longer (471 s). When only considering user interaction, plan generation time was 121 s for the cARF model and 137 s for the U-net model.

Conclusions

Two AI models were used to generate deliverable plans for breast cancer patients, in a time-efficient manner, requiring minimal user interaction. Although the AI plans resulted in slightly higher doses overall, radiation oncologists considered 90–95% of the AI plans clinically acceptable.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-022-01993-9.

Development and evaluation of radiotherapy deep learning dose prediction models for breast cancer

Background and purpose

Treatment planning of radiotherapy is a time-consuming and planner dependent process that can be automated by dose prediction models. The purpose of this study was to evaluate the performance of two machine learning models for breast cancer radiotherapy before possible clinical implementation.

Materials and methods

An in-house developed model, based on U-net architecture, and a contextual atlas regression forest (cARF) model integrated in the treatment planning software were trained. Obtained dose distributions were mimicked to create clinically deliverable plans. For training and validation, 90 patients were used, 15 patients were used for testing. Treatment plans were scored on predefined evaluation criteria and percent errors with respect to clinical dose were calculated for doses to planning target volume (PTV) and organs at risk (OARs).

Results

The U-net plans before mimicking met all criteria for all patients, both models failed one evaluation criterion in three patients after mimicking. No significant differences (p < 0.05) were found between clinical and predicted U-net plans before mimicking. Doses to OARs in plans of both models differed significantly from clinical plans, but no clinically relevant differences were found. After mimicking, both models had a mean percent error within 1.5% for the average dose to PTV and OARs. The mean errors for maximum doses were higher, within 6.6%.

Conclusions

Differences between predicted doses to OARs of the models were small when compared to clinical plans, and not found to be clinically relevant. Both models show potential in automated treatment planning for breast cancer.

A Review on Application of Deep Learning Algorithms in External Beam Radiotherapy Automated Treatment Planning

Treatment planning plays an important role in the process of radiotherapy (RT). The quality of the treatment plan directly and significantly affects patient treatment outcomes. In the past decades, technological advances in computer and software have promoted the development of RT treatment planning systems with sophisticated dose calculation and optimization algorithms. Treatment planners now have greater flexibility in designing highly complex RT treatment plans in order to mitigate the damage to healthy tissues better while maximizing radiation dose to tumor targets. Nevertheless, treatment planning is still largely a time-inefficient and labor-intensive process in current clinical practice. Artificial intelligence, including machine learning (ML) and deep learning (DL), has been recently used to automate RT treatment planning and has gained enormous attention in the RT community due to its great promises in improving treatment planning quality and efficiency. In this article, we reviewed the historical advancement, strengths, and weaknesses of various DL-based automated RT treatment planning techniques. We have also discussed the challenges, issues, and potential research directions of DL-based automated RT treatment planning techniques.

Accurate estimation of daily delivered radiotherapy dose with an external treatment planning system

Accurate estimation of the daily radiotherapy dose is challenging in a multi-institutional collaboration when the institution specific treatment planning system (TPS) is not available. We developed and evaluated a method to tackle this problem. Residual errors in daily estimations were minimized with single correction based on the planned dose. For nine patients, medians of the absolute estimation errors for targets and OARs were less than 0.2 Gy (Dmean), 0.3 Gy (D1), and 0.1 Gy (D99). In general, mimicking errors were significantly smaller than dose differences caused by anatomical changes. The demonstrated accuracy may facilitate dose accumulation in a multi-institutional/multi-vendor setting.

Probabilistic optimization of dose coverage in radiotherapy

BACKGROUND AND PURPOSE

Probabilistic optimization is an alternative to margins for handling geometrical uncertainties in treatment planning of radiotherapy where uncertainties are explicitly incorporated in the optimization. We present a novel probabilistic method based on the same statistical measures as those behind conventional margin based planning.

MATERIAL AND METHODS

Percentile Dosage (PD) was defined as the dose coverage that a treatment plan meet or exceed to a given probability. For optimization, we used the convex measure Expected Percentile Dosage (EPD) defined as the average dose coverage below a given PD. An iterative method gradually adjusted the constraint tolerance associated with the EPD until the desired target PD was met. It was applied to planning of cervical cancer patients focusing on systematic uncertainty caused by organ deformation. The resulting plans were compared to margin based plans using target and organ at risk PDs.

RESULTS

The EPD tolerance converged in less than ten iterations to produce a PD within 0.1 Gy of the requested. The PD was on average within 0.5% of the requested PD when validated versus independent scenarios. The rectum volume, extracted from the PDs, receiving 90% of the intended target dose was decreased with 16% for the same target PD in comparison to margin based plans.

CONCLUSIONS

The proposed probabilistic optimization method enabled prescription of a dose volume histogram metric to a chosen confidence. The probabilistic plans showed improved target dose homogeneity and decreased rectum dose for the same target dose coverage compared to margin based plans.

A treatment planning comparison of contemporary photon-based radiation techniques for breast cancer

Background and purpose

Adjuvant radiation therapy (RT) of the whole breast (WB) is still the standard treatment for early breast cancer. A variety of radiation techniques is currently available according to different delivery strategies. This study aims to provide a comparison of six treatment planning strategies commonly adopted for breast-conserving adjuvant RT and to use the Pareto concept in an attempt to assess the degree of plan optimization.

Materials and methods

Two groups of six left- and five right-sided cases with different dose prescriptions were involved (22 patients in total). Field-in-Field (FiF), two and four Fields static-IMRT (sIMRT-2f and sIMRT-4f), Volumetric-Modulated-Arc-Therapy (VMAT), Helical Tomotherapy (HT) and Static-Angles Tomotherapy (TomoDirect™ – TD) were planned. Dose volume constraints were taken from the RTOG protocol 1005. Pareto fronts were built for a selected case to evaluate the reliability of the plan optimization process.

Results

The best target dose coverage was observed for TD able to improve significantly (p < 0.01) the V95% in a range varying from 1.2% to 7.5% compared to other techniques. The V105% was significantly reduced up to 2% for HT (p < 0.05) although FiF and VMAT produced similar values. For the ipsilateral lung, V5Gy, V10Gy and Dmean were significantly lower than all other techniques (p < 0.02) for TD while the lowest value of V20Gy was observed for HT. The maximum dose to contralateral breast was significantly lowest for TD (p < 0.02) and for FiF (p < 0.05). Minor differences were observed for the heart in left-sided patients. Plans for all tested techniques were found to lie on their respective Pareto fronts.

Conclusions

Overall, TD provided significantly better results in terms of target coverage and dose sparing of ipsilateral lung with respect to all other evaluated techniques. It also significantly minimized dose to contralateral breast together with FiF. Pareto front analysis confirmed the reliability of the optimization for a selected case.

Correlation of dual-source computed tomography/dual-energy imaging with pathological grading of lung adenocarcinoma and its clinical value

Objective:

To explore the correlation of dual-source computed tomography (DSCT)/dual-energy imaging with pathological grading of lung adenocarcinoma.

Methods:

A total of 47 patients with lung adenocarcinoma were selected. Tissues were histopathologically confirmed by routine DSCT scanning and dual-energy enhanced scanning. Arterial-phase and venous-phase iodine distribution images and single-energy images at 40-190 keV were obtained. The region of interest was outlined to obtain CT values. The iodine concentrations of each tumor in two phases were recorded to calculate normalized iodine concentrations (NICs).

Results:

The maximum diameter and minimum diameter of tumors in low differentiation (LD) group were significantly higher than those of high differentiation (HD) group (P<0.05). In LD group, 70.8% of margins were lobulated, which significantly exceeded that of HD group (30.4%) (P<0.05). Besides, 26.1% of patients in HD group were complicated with ground-glass opacity, which was significantly higher than that of LD group (4.2%) (P<0.05). In venous phase, there were significant differences between the two groups at low energy levels (40-70 keV) (P<0.05). At high energy levels (80-190 keV), the CT values of LD group were slightly higher than those of HD group. In arterial and venous phases, NICs of HD group were lower than those of LD group (P>0.05).

Conclusion:

HD and LD groups could be predictably distinguished by single-energy images at low energy levels (40-70 keV) in the venous phase. Quantitative analysis of NIC in the venous phase is also valuable for predicting the pathological grade of lung adenocarcinoma.

Fully automated treatment planning for head and neck radiotherapy using a voxel-based dose prediction and dose mimicking method

Recent works in automated radiotherapy treatment planning have used machine learning based on historical treatment plans to infer the spatial dose distribution for a novel patient directly from the planning image. We present a probabilistic, atlas-based approach which predicts the dose for novel patients using a set of automatically selected most similar patients (atlases). The output is a spatial dose objective, which specifies the desired dose-per-voxel, and therefore replaces the need to specify and tune dose-volume objectives. Voxel-based dose mimicking optimization then converts the predicted dose distribution to a complete treatment plan with dose calculation using a collapsed cone convolution dose engine. In this study, we investigated automated planning for right-sided oropharaynx head and neck patients treated with IMRT and VMAT. We compare four versions of our dose prediction pipeline using a database of 54 training and 12 independent testing patients by evaluating 14 clinical dose evaluation criteria. Our preliminary results are promising and demonstrate that automated methods can generate comparable dose distributions to clinical. Overall, automated plans achieved an average of 0.6% higher dose for target coverage evaluation criteria, and 2.4% lower dose at the organs at risk criteria levels evaluated compared with clinical. There was no statistically significant difference detected in high-dose conformity between automated and clinical plans as measured by the conformation number. Automated plans achieved nine more unique criteria than clinical across the 12 patients tested and automated plans scored a significantly higher dose at the evaluation limit for two high-risk target coverage criteria and a significantly lower dose in one critical organ maximum dose. The novel dose prediction method with dose mimicking can generate complete treatment plans in 12-13 min without user interaction. It is a promising approach for fully automated treatment planning and can be readily applied to different treatment sites and modalities.