Automated treatment planning of postmastectomy radiotherapy

Synthesizing Efficiency Tools in Radiotherapy to Increase Patient Flow: A Comprehensive Literature Review

The promise of novel technologies to increase access to radiotherapy in low- and middle-income countries (LMICs) is crucial, given that the cost of equipping new radiotherapy centres or upgrading existing machinery remains a major obstacle to expanding access to cancer treatment. The study aims to provide a thorough analysis overview of how technological advancement may revolutionize radiotherapy (RT) to improve level of care provided to cancer patients. A comprehensive literature review following some steps of systematic review (SLR) was performed using the Web of Science (WoS), PubMed, and Scopus databases. The study findings are classified into different technologies. Artificial intelligence (AI), knowledge-based planning, remote planning, radiotherapy, and scripting are all ways to increase patient flow across radiation oncology, including initial consultation, treatment planning, delivery, verification, and patient follow-up. This review found that these technologies improve delineation of organ at risks (OARs) and considerably reduce waiting times when compared with conventional treatment planning in RT. In this review, AI, knowledge-based planning, remote radiotherapy treatment planning, and scripting reduced waiting times and improved organ at-risk delineation compared with conventional RT treatment planning. A combination of these technologies may lower cancer patients' risk of disease progression due to reduced workload, quality of therapy, and individualized treatment. Efficiency tools, such as the application of AI, knowledge-based planning, remote radiotherapy planning, and scripting, are urgently needed to reduce waiting times and improve OAR delineation accuracy in cancer treatment compared with traditional treatment planning methods. The study's contribution is to present the potential of technological advancement to optimize RT planning process, thereby improving patient care and resource utilization. The study may be extended in the future to include digital integration and technology's impact on patient safety, outcomes, and risk. Therefore, in radiotherapy, research on more efficient tools pioneers the development and implementation of high-precision radiotherapy for cancer patients.

Development and validation of an automated Tomotherapy planning method for cervical cancer

PURPOSE

This study aimed to develop an automated Tomotherapy (TOMO) planning method for cervical cancer treatment, and to validate its feasibility and effectiveness.

MATERIALS AND METHODS

The study enrolled 30 cervical cancer patients treated with TOMO at our center. Utilizing scripting and Python environment within the RayStation (RaySearch Labs, Sweden) treatment planning system (TPS), we developed automated planning methods for TOMO and volumetric modulated arc therapy (VMAT) techniques. The clinical manual TOMO (M-TOMO) plans for the 30 patients were re-optimized using automated planning scripts for both TOMO and VMAT, creating automated TOMO (A-TOMO) and automated VMAT (A-VMAT) plans. We compared A-TOMO with M-TOMO and A-VMAT plans. The primary evaluated relevant dosimetric parameters and treatment plan efficiency were assessed using the two-sided Wilcoxon signed-rank test for statistical analysis, with a P-value < 0.05 indicating statistical significance.

RESULTS

A-TOMO plans maintained similar target dose uniformity compared to M-TOMO plans, with improvements in target conformity and faster dose drop-off outside the target, and demonstrated significant statistical differences (P+ < 0.01). A-TOMO plans also significantly outperformed M-TOMO plans in reducing V50Gy, V40Gy and Dmean for the bladder and rectum, as well as Dmean for the bowel bag, femoral heads, and kidneys (all P+ < 0.05). Additionally, A-TOMO plans demonstrated better consistency in plan quality. Furthermore, the quality of A-TOMO plans was comparable to or superior than A-VMAT plans. In terms of efficiency, A-TOMO significantly reduced the time required for treatment planning to approximately 20 min.

CONCLUSION

We have successfully developed an A-TOMO planning method for cervical cancer. Compared to M-TOMO plans, A-TOMO plans improved target conformity and reduced radiation dose to OARs. Additionally, the quality of A-TOMO plans was on par with or surpasses that of A-VMAT plans. The A-TOMO planning method significantly improved the efficiency of treatment planning.

Multi-centre real-world validation of automated treatment planning for breast radiotherapy

PURPOSE

To present the results of the first multi-centre real-world validation of autoplanning for whole breast irradiation after breast-sparing surgery, encompassing high complexity cases (e.g. with a boost or regional lymph nodes) and a wide range of clinical practices.

METHODS

The 24 participating centers each included 10 IMRT/VMAT/Tomotherapy patients, previously treated with a manually generated plan ('manplan'). There were no restrictions regarding case complexity, planning aims, plan evaluation parameters and criteria, fractionation, treatment planning system or treatment machine/technique. In addition to dosimetric comparisons of autoplans with manplans, blinded plan scoring/ranking was conducted by a clinician from the treating center. Autoplanning was performed using a single configuration for all patients in all centres. Deliverability was verified through measurements at delivery units.

RESULTS

Target dosimetry showed comparability, while reductions in OAR dose parameters were 21.4 % for heart Dmean, 16.7 % for ipsilateral lung Dmean, and 101.9 %, 45.5 %, and 35.7 % for contralateral breast D0.03cc, D5% and Dmean, respectively (all p < 0.001). Among the 240 patients included, the clinicians preferred the autoplan for 119 patients, with manplans preferred for 96 cases (p = 0.01). Per centre there were on average 5.0 ± 2.9 (1SD) patients with a preferred autoplan (range [0-10]), compared to 4.0 ± 2.7 with a preferred manplan ([0,9]). No differences were observed regarding deliverability.

CONCLUSION

The automation significantly reduced the hands-on planning workload compared to manual planning, while also achieving an overall superiority. However, fine-tuning of the autoplanning configuration prior to clinical implementation may be necessary in some centres to enhance clinicians' satisfaction with the generated autoplans.

Evaluating automatically generated normal tissue contours for safe use in head and neck and cervical cancer treatment planning

PURPOSE

Volumetric-modulated arc therapy (VMAT) is a widely accepted treatment method for head and neck (HN) and cervical cancers; however, creating contours and plan optimization for VMAT plans is a time-consuming process. Our group has created an automated treatment planning tool, the Radiation Planning Assistant (RPA), that uses deep learning models to generate organs at risk (OARs), planning structures and automates plan optimization. This study quantitatively evaluates the quality of contours generated by the RPA tool.

METHODS

For patients with HN (54) and cervical (39) cancers, we retrospectively generated autoplans using the RPA. Autoplans were generated using deep-learning and RapidPlan models developed in-house. The autoplans were, then, applied to the original, physician-drawn contours, which were used as a ground truth (GT) to compare with the autocontours (RPA). Using a "two one-sided tests" (TOST) procedure, we evaluated whether the autocontour normal tissue dose was equivalent to that of the ground truth by a margin, δ, that we determined based on clinical judgement. We also calculated the number of plans that met established clinically accepted dosimetric criteria.

RESULTS

For HN plans, 91.8% and 91.7% of structures met dosimetric criteria for automatic and manual contours, respectively; for cervical plans, 95.6% and 95.7% of structures met dosimetric criteria for automatic and manual contours, respectively. Autocontours were equivalent to the ground truth for 71% and 75% of common DVH metrics for the HN and cervix, respectively.

CONCLUSIONS

This study shows that dosimetrically equivalent normal tissue contours can be created for HN and cervical cancers using deep learning techniques. In general, differences between the contours did not affect the passing or failing of clinical dose tolerances.

Automated treatment planning for whole breast irradiation with individualized tangential IMRT fields

PURPOSES

This study aimed to develop and validate algorithms for automating intensity modulated radiation therapy (IMRT) planning in breast cancer patients, with a focus on patient anatomical characteristics.

MATERIAL AND METHODS

We retrospectively selected 400 breast cancer patients without lymph node involvement for automated treatment planning. Automation was achieved using the Eclipse Scripting Application Programming Interface (ESAPI) integrated into the Eclipse Treatment Planning System. We employed three beam insertion geometries and three optimization strategies, resulting in 3600 plans, each delivering a 40.05 Gy dose in 15 fractions. Gantry angles in the tangent fields were selected based on a criterion involving the minimum intersection area between the Planning Target Volume (PTV) and the ipsilateral lung in the Beam's Eye View projection. ESAPI was also used to gather patient anatomical data, serving as input for Random Forest models to select the optimal plan. The Random Forest classification considered both beam insertion geometry and optimization strategy. Dosimetric data were evaluated in accordance with the Radiation Therapy Oncology Group (RTOG) 1005 protocol.

RESULTS

Overall, all approaches generated high-quality plans, with approximately 94% meeting the acceptable dose criteria for organs at risk and/or target coverage as defined by RTOG guidelines. Average automated plan generation time ranged from 6 min and 37 s to 9 min and 22 s, with the mean time increasing with additional fields. The Random Forest approach did not successfully enable automatic planning strategy selection. Instead, our automated planning system allows users to choose from the tested geometry and strategy options.

CONCLUSIONS

Although our attempt to correlate patient anatomical features with planning strategy using machine learning tools was unsuccessful, the resulting dosimetric outcomes proved satisfactory. Our algorithm consistently produced high-quality plans, offering significant time and efficiency advantages.

Inter-institutional variability of knowledge-based plan prediction of left whole breast irradiation

PURPOSE

Within a multi-institutional project, we aimed to assess the transferability of knowledge-based (KB) plan prediction models in the case of whole breast irradiation (WBI) for left-side breast irradiation with tangential fields (TF).

METHODS

Eight institutions set KB models, following previously shared common criteria. Plan prediction performance was tested on 16 new patients (2 pts per centre) extracting dose-volume-histogram (DVH) prediction bands of heart, ipsilateral lung, contralateral lung and breast. The inter-institutional variability was quantified by the standard deviations (SDint) of predicted DVHs and mean-dose (Dmean). The transferability of models, for the heart and the ipsilateral lung, was evaluated by the range of geometric Principal Component (PC1) applicability of a model to test patients of the other 7 institutions.

RESULTS

SDint of the DVH was 1.8 % and 1.6 % for the ipsilateral lung and the heart, respectively (20 %-80 % dose range); concerning Dmean, SDint was 0.9 Gy and 0.6 Gy for the ipsilateral lung and the heart, respectively (<0.2 Gy for contralateral organs). Mean predicted doses ranged between 4.3 and 5.9 Gy for the ipsilateral lung and 1.1-2.3 Gy for the heart. PC1 analysis suggested no relevant differences among models, except for one centre showing a systematic larger sparing of the heart, concomitant to a worse PTV coverage, due to high priority in sparing the left anterior descending coronary artery.

CONCLUSIONS

Results showed high transferability among models and low inter-institutional variability of 2% for plan prediction. These findings encourage the building of benchmark models in the case of TF-WBI.

Validation of an automated contouring and treatment planning tool for pediatric craniospinal radiation therapy

Purpose

Treatment planning for craniospinal irradiation (CSI) is complex and time-consuming, especially for resource-constrained centers. To alleviate demanding workflows, we successfully automated the pediatric CSI planning pipeline in previous work. In this work, we validated our CSI autosegmentation and autoplanning tool on a large dataset from St. Jude Children's Research Hospital.

Methods

Sixty-three CSI patient CT scans were involved in the study. Pre-planning scripts were used to automatically verify anatomical compatibility with the autoplanning tool. The autoplanning pipeline generated 15 contours and a composite CSI treatment plan for each of the compatible test patients (n=51). Plan quality was evaluated quantitatively with target coverage and dose to normal tissue metrics and qualitatively with physician review, using a 5-point Likert scale. Three pediatric radiation oncologists from 3 institutions reviewed and scored 15 contours and a corresponding composite CSI plan for the final 51 test patients. One patient was scored by 3 physicians, resulting in 53 plans scored total.

Results

The algorithm automatically detected 12 incompatible patients due to insufficient junction spacing or head tilt and removed them from the study. Of the 795 autosegmented contours reviewed, 97% were scored as clinically acceptable, with 92% requiring no edits. Of the 53 plans scored, all 51 brain dose distributions were scored as clinically acceptable. For the spine dose distributions, 92%, 100%, and 68% of single, extended, and multiple-field cases, respectively, were scored as clinically acceptable. In all cases (major or minor edits), the physicians noted that they would rather edit the autoplan than create a new plan.

Conclusions

We successfully validated an autoplanning pipeline on 51 patients from another institution, indicating that our algorithm is robust in its adjustment to differing patient populations. We automatically generated 15 contours and a comprehensive CSI treatment plan for each patient without physician intervention, indicating the potential for increased treatment planning efficiency and global access to high-quality radiation therapy.

Clinical application of a template-guided automated planning routine

PURPOSE

Determine the dosimetric quality and the planning time reduction when utilizing a template-based automated planning application.

METHODS

A software application integrated through the treatment planning system application programing interface, QuickPlan, was developed to facilitate automated planning using configurable templates for contouring, knowledge-based planning structure matching, field design, and algorithm settings. Validations are performed at various levels of the planning procedure and assist in the evaluation of readiness of the CT image, structure set, and plan layout for automated planning. QuickPlan is evaluated dosimetrically against 22 hippocampal-avoidance whole brain radiotherapy patients. The required times to treatment plan generation are compared for the validations set as well as 10 prospective patients whose plans have been automated by QuickPlan.

RESULTS

The generations of 22 automated treatment plans are compared against a manual replanning using an identical process, resulting in dosimetric differences of minor clinical significance. The target dose to 2% volume and homogeneity index result in significantly decreased values for automated plans, whereas other dose metric evaluations are nonsignificant. The time to generate the treatment plans is reduced for all automated plans with a median difference of 9' 50″ ± 4' 33″.

CONCLUSIONS

Template-based automated planning allows for reduced treatment planning time with consistent optimization structure creation, treatment field creation, plan optimization, and dose calculation with similar dosimetric quality. This process has potential expansion to numerous disease sites.

Automating the treatment planning process for 3D-conformal pediatric craniospinal irradiation therapy

PURPOSE

Pediatric patients with medulloblastoma in low- and middle-income countries (LMICs) are most treated with 3D-conformal photon craniospinal irradiation (CSI), a time-consuming, complex treatment to plan, especially in resource-constrained settings. Therefore, we developed and tested a 3D-conformal CSI autoplanning tool for varying patient lengths.

METHODS AND MATERIALS

Autocontours were generated with a deep learning model trained:tested (80:20 ratio) on 143 pediatric medulloblastoma CT scans (patient ages: 2-19 years, median = 7 years). Using the verified autocontours, the autoplanning tool generated two lateral brain fields matched to a single spine field, an extended single spine field, or two matched spine fields. Additional spine subfields were added to optimize the corresponding dose distribution. Feathering was implemented (yielding nine to 12 fields) to give a composite plan. Each planning approach was tested on six patients (ages 3-10 years). A pediatric radiation oncologist assessed clinical acceptability of each autoplan.

RESULTS

The autocontoured structures' average Dice similarity coefficient ranged from .65 to .98. The average V95 for the brain/spinal canal for single, extended, and multi-field spine configurations was 99.9% ± 0.06%/99.9% ± 0.10%, 99.9% ± 0.07%/99.4% ± 0.30%, and 99.9% ± 0.06%/99.4% ± 0.40%, respectively. The average maximum dose across all field configurations to the brainstem, eyes (L/R), lenses (L/R), and spinal cord were 23.7 ± 0.08, 24.1 ± 0.28, 13.3 ± 5.27, and 25.5 ± 0.34 Gy, respectively (prescription = 23.4 Gy/13 fractions). Of the 18 plans tested, all were scored as clinically acceptable as-is or clinically acceptable with minor, time-efficient edits preferred or required. No plans were scored as clinically unacceptable.

CONCLUSION

The autoplanning tool successfully generated pediatric CSI plans for varying patient lengths in 3.50 ± 0.4 minutes on average, indicating potential for an efficient planning aid in a resource-constrained settings.

Automated Contouring and Planning in Radiation Therapy: What Is 'Clinically Acceptable'?

Developers and users of artificial-intelligence-based tools for automatic contouring and treatment planning in radiotherapy are expected to assess clinical acceptability of these tools. However, what is 'clinical acceptability'? Quantitative and qualitative approaches have been used to assess this ill-defined concept, all of which have advantages and disadvantages or limitations. The approach chosen may depend on the goal of the study as well as on available resources. In this paper, we discuss various aspects of 'clinical acceptability' and how they can move us toward a standard for defining clinical acceptability of new autocontouring and planning tools.

Spot delivery error predictions for intensity modulated proton therapy using robustness analysis with machine learning

The purpose of this work is to assess the robustness of treatment plans when spot delivery errors were predicted with a machine learning (ML) model for intensity modulated proton therapy (IMPT). Over 6000 machine log files from delivered IMPT treatment plans were included in this study. From these log files, over 4.1  × $ \times \ $ 10⁶ delivered proton spots were used to train the ML model. The presented model was tested and used to predict the spot position as well as the monitor units (MU) per spot, based on the original planning parameters. Two patient plans (one accelerated partial breast irradiation [APBI] and one ependymoma) were recalculated with the predicted spot position/MUs by the ML model and then were re-analyzed for robustness. Plans with ML predicted spots were less robust than the original clinical plans. In the APBI plan, dosimetric changes to the left lung and heart were not clinically relevant. In the ependymoma plan, the hot spot in the brainstem decreased and the hot spot in the cervical cord increased. Despite these differences, after robustness analysis, both ML spot delivery error plans resulted in >95% of the CTV receiving >95% of the prescription dose. The presented workflow has the potential benefit of including realistic spots information for plan quality checks in IMPT. This work demonstrates that in the two example plans, the plans were still robust when accounting for spot delivery errors as predicted by the ML model.

Automated field-in-field whole brain radiotherapy planning

PURPOSE

We developed and tested an automatic field-in-field (FIF) solution for whole-brain radiotherapy (WBRT) planning that creates a homogeneous dose distribution by minimizing hotspots, resulting in clinically acceptable plans.

METHODS

A configurable auto-planning algorithm was developed to automatically generate FIF WBRT plans independent of the treatment planning system. Configurable parameters include the definition of hotspots, target volume, maximum number of subfields, and minimum number of monitor units per field. This algorithm iteratively identifies a hotspot, creates two opposing subfields, calculates the dose, and optimizes the beam weight based on user-configured constraints of dose-volume histogram coverage and least-squared cost functions. The algorithm was retrospectively tested on 17 whole-brain patients. First, an in-house landmark-based automated beam aperture technique was used to generate the treatment fields and initial plans. Second, the FIF algorithm was employed to optimize the plans using physician-defined goals of 99.9% of the brain volume receiving 100% of the prescription dose (30 Gy in 10 fractions) and a target hotspot definition of 107% of the prescription dose. The final auto-optimized plans were assessed for clinical acceptability by an experienced radiation oncologist using a five-point scale.

RESULTS

The FIF algorithm reduced the mean (± SD) plan hotspot percentage dose from 35.0 Gy (116.6%) ± 0.6 Gy (2.0%) to 32.6 Gy (108.8%) ± 0.4 Gy (1.2%). Also, it decreased the mean (± SD) hotspot V107% [cm³ ] from 959 ± 498 cm³ to 145 ± 224 cm³ . On average, plans were produced in 16 min without any user intervention. Furthermore, 76.5% of the auto-plans were clinically acceptable (needing no or minor stylistic edits), and all of them were clinically acceptable after minor clinically necessary edits.

CONCLUSIONS

This algorithm successfully produced high-quality WBRT plans and can improve treatment planning efficiency when incorporated into an automatic planning workflow.

Statistical process control to monitor use of a web-based autoplanning tool

PURPOSE

To investigate the use of statistical process control (SPC) for quality assurance of an integrated web-based autoplanning tool, Radiation Planning Assistant (RPA).

METHODS

Automatically generated plans were downloaded and imported into two treatment planning systems (TPSs), RayStation and Eclipse, in which they were recalculated using fixed monitor units. The recalculated plans were then uploaded back to the RPA, and the mean dose differences for each contour between the original RPA and the TPSs plans were calculated. SPC was used to characterize the RPA plans in terms of two comparisons: RayStation TPS versus RPA and Eclipse TPS versus RPA for three anatomical sites, and variations in the machine parameters dosimetric leaf gap (DLG) and multileaf collimator transmission factor (MLC-TF) for two algorithms (Analytical Anisotropic Algorithm [AAA]) and Acuros in the Eclipse TPS. Overall, SPC was used to monitor the process of the RPA, while clinics would still perform their routine patient-specific QA.

RESULTS

For RayStation, the average mean percent dose differences across all contours were 0.65% ± 1.05%, -2.09% ± 0.56%, and 0.28% ± 0.98% and average control limit ranges were 1.89% ± 1.32%, 2.16% ± 1.31%, and 2.65% ± 1.89% for the head and neck, cervix, and chest wall, respectively. In contrast, Eclipse's average mean percent dose differences across all contours were -0.62% ± 0.34%, 0.32% ± 0.23%, and -0.91% ± 0.98%, while average control limit ranges were 1.09% ± 0.77%, 3.69% ± 2.67%, 2.73% ± 1.86%, respectively. Averaging all contours and removing outliers, a 0% dose difference corresponded with a DLG value of 0.202 ± 0.019 cm and MLC-TF value of 0.020 ± 0.001 for Acuros and a DLG value of 0.135 ± 0.031 cm and MLC-TF value of 0.015 ± 0.001 for AAA.

CONCLUSIONS

Differences in mean dose and control limits between RPA and two separately commissioned TPSs were determined. With varying control limits and means, SPC provides a flexible and useful process quality assurance tool for monitoring a complex automated system such as the RPA.

Automation of radiation treatment planning for rectal cancer

Purpose

To develop an automated workflow for rectal cancer three‐dimensional conformal radiotherapy (3DCRT) treatment planning that combines deep learning (DL) aperture predictions and forward‐planning algorithms.

Methods

We designed an algorithm to automate the clinical workflow for 3DCRT planning with field aperture creations and field‐in‐field (FIF) planning. DL models (DeepLabV3+ architecture) were trained, validated, and tested on 555 patients to automatically generate aperture shapes for primary (posterior–anterior [PA] and opposed laterals) and boost fields. Network inputs were digitally reconstructed radiographs, gross tumor volume (GTV), and nodal GTV. A physician scored each aperture for 20 patients on a 5‐point scale (>3 is acceptable). A planning algorithm was then developed to create a homogeneous dose using a combination of wedges and subfields. The algorithm iteratively identifies a hotspot volume, creates a subfield, calculates dose, and optimizes beam weight all without user intervention. The algorithm was tested on 20 patients using clinical apertures with varying wedge angles and definitions of hotspots, and the resulting plans were scored by a physician. The end‐to‐end workflow was tested and scored by a physician on another 39 patients.

Results

The predicted apertures had Dice scores of 0.95, 0.94, and 0.90 for PA, laterals, and boost fields, respectively. Overall, 100%, 95%, and 87.5% of the PA, laterals, and boost apertures were scored as clinically acceptable, respectively. At least one auto‐plan was clinically acceptable for all patients. Wedged and non‐wedged plans were clinically acceptable for 85% and 50% of patients, respectively. The hotspot dose percentage was reduced from 121% (σ = 14%) to 109% (σ = 5%) of prescription dose for all plans. The integrated end‐to‐end workflow of automatically generated apertures and optimized FIF planning gave clinically acceptable plans for 38/39 (97%) of patients.

Conclusion

We have successfully automated the clinical workflow for generating radiotherapy plans for rectal cancer for our institution.

Assessing the practicality of using a single knowledge‐based planning model for multiple linac vendors

Purpose

Knowledge‐based planning (KBP) has been shown to be an effective tool in quality control for intensity‐modulated radiation therapy treatment planning and generating high‐quality plans. Previous studies have evaluated its ability to create consistent plans across institutions and between planners within the same institution as well as its use as teaching tool for inexperienced planners. This study evaluates whether planning quality is consistent when using a KBP model to plan across different treatment machines.

Materials and methods

This study used a RapidPlan model (Varian Medical Systems) provided by the vendor, to which we added additional planning objectives, maximum dose limits, and planning structures, such that a clinically acceptable plan is achieved in a single optimization. This model was used to generate and optimize volumetric‐modulated arc therapy plans for a cohort of 50 patients treated for head‐neck cancer. Plans were generated using the following treatment machines: Varian 2100, Elekta Versa HD, and Varian Halcyon. A noninferiority testing methodology was used to evaluate the hypothesis that normal and target metrics in our autoplans were no worse than a set of clinically‐acceptable baseline plans by a margin of 1.8 Gy or 3% dose‐volume. The quality of these plans were also compared through the use of common clinical dose‐volume histogram criteria.

Results

The Versa HD met our noninferiority criteria for 23 of 34 normal and target metrics; while the Halcyon and Varian 2100 machines met our criteria for 24 of 34 and 26 of 34 metrics, respectively. The experimental plans tended to have less volume coverage for prescription dose planning target volume and larger hotspot volumes. However, comparable plans were generated across different treatment machines.

Conclusions

These results support the use of a head‐neck RapidPlan models in centralized planning workflows that support clinics with different linac models/vendors, although some fine‐tuning for targets may be necessary.

Development and validation of a checklist for use with automatically generated radiotherapy plans

Purpose

To develop a checklist that improves the rate of error detection during the plan review of automatically generated radiotherapy plans.

Methods

A custom checklist was developed using guidance from American Association of Physicists in Medicine task groups 275 and 315 and the results of a failure modes and effects analysis of the Radiation Planning Assistant (RPA), an automated contouring and treatment planning tool. The preliminary checklist contained 90 review items for each automatically generated plan. In the first study, eight physicists were recruited from our institution who were familiar with the RPA. Each physicist reviewed 10 artificial intelligence‐generated resident treatment plans from the RPA for safety and plan quality, five of which contained errors. Physicists performed plan checks, recorded errors, and rated each plan's clinical acceptability. Following a 2‐week break, physicists reviewed 10 additional plans with a similar distribution of errors using our customized checklist. Participants then provided feedback on the usability of the checklist and it was modified accordingly. In a second study, this process was repeated with 14 senior medical physics residents who were randomly assigned to checklist or no checklist for their reviews. Each reviewed 10 plans, five of which contained errors, and completed the corresponding survey.

Results

In the first study, the checklist significantly improved the rate of error detection from 3.4 ± 1.1 to 4.4 ± 0.74 errors per participant without and with the checklist, respectively (p = 0.02). Error detection increased by 20% when the custom checklist was utilized. In the second study, 2.9 ± 0.84 and 3.5 ± 0.84 errors per participant were detected without and with the revised checklist, respectively (p = 0.08). Despite the lack of statistical significance for this cohort, error detection increased by 18% when the checklist was utilized.

Conclusion

Our results indicate that the use of a customized checklist when reviewing automated treatment plans will result in improved patient safety.

Evaluation of an automated template-based treatment planning system for radiotherapy of anal, rectal and prostate cancer

•

Automated treatment planning system compared to manual planning.

•

Equivalent plan quality between VMAT manually generated- and IMRT automatically generated plans.

•

Evaluation of anal, prostate and rectum treatment plans.

•

Generation of highly consistent IMRT automated plan within 2 to 3.5 min.

Background and purpose

The Ethos system has enabled online adaptive radiotherapy (oART) by implementing an automated treatment planning system (aTPS) for both intensity-modulated radiotherapy (IMRT) and volumetric modulated arc radiotherapy (VMAT) plan creation. The purpose of this study is to evaluate the quality of aTPS plans in the pelvic region.

Material and Methods

Sixty patients with anal (n = 20), rectal (n = 20) or prostate (n = 20) cancer were retrospectively re-planned with the aTPS. Three IMRT (7-, 9- and 12-field) and two VMAT (2 and 3 arc) automatically generated plans (APs) were created per patient. The duration of the automated plan generation was registered. The best IMRT-AP and VMAT-AP for each patient were selected based on target coverage and dose to organs at risk (OARs). The AP quality was analyzed and compared to corresponding clinically accepted and manually generated VMAT plans (MPs) using several clinically relevant dose metrics. Calculation-based pre-treatment plan quality assurance (QA) was performed for all plans.

Results

The median total duration to generate the five APs with the aTPS was 55 min, 39 min and 35 min for anal, prostate and rectal plans, respectively. The target coverage and the OAR sparing were equivalent for IMRT-APs and VMAT-MPs, while VMAT-Aps.

demonstrated lower target dose homogeneity and higher dose to some OARs. Both conformity and homogeneity index were equivalent (rectal) or better (anal and prostate) for IMRT-APs compared to VMAT-MPs. All plans passed the patient-specific QA tolerance limit.

Conclusions

The aTPS generates plans comparable to MPs within a short time-frame which is highly relevant for oART treatments.

Artificial Intelligence-Based Automated Treatment Planning of Postmastectomy Volumetric Modulated Arc Radiotherapy

As a useful tool, artificial intelligence has surpassed human beings in many fields. Artificial intelligence-based automated radiotherapy planning strategies have been proposed in lots of cancer sites and are the future of treatment planning. Postmastectomy radiotherapy (PMRT) decreases local recurrence probability and improves overall survival, and volumetric modulated arc therapy (VMAT) has gradually become the mainstream technique of radiotherapy. However, there are few customized effective automated treatment planning schemes for postmastectomy VMAT so far. This study investigated an artificial intelligence based automated planning using the MD Anderson Cancer Center AutoPlan (MDAP) system and Pinnacle treatment planning system (TPS), to effectively generate high-quality postmastectomy VMAT plans. In this study, 20 patients treated with PMRT were retrospectively investigated, including 10 left- and 10 right-sided postmastectomy patients. Chest wall and the supraclavicular, subclavicular, and internal mammary regions were delineated as target volume by radiation oncologists, and 50 Gy in 25 fractions was prescribed. Organs at risk including heart, spinal cord, left lung, right lung, and lungs were also contoured. All patients were planned with VMAT using 2 arcs. An optimization objective template was summarized based on the dose of clinical plans and requirements from oncologists. Several treatment planning parameters were investigated using an artificial intelligence algorithm, including collimation angle, jaw collimator mode, gantry spacing resolution (GSR), and number of start optimization times. The treatment planning parameters with the best performance or that were most preferred were applied to the automated treatment planning method. Dosimetric indexes of automated treatment plans (autoplans) and manual clinical plans were compared by the paired t-test. The jaw tracking mode, 2-degree GSR, and 3 rounds of optimization were selected in all the PMRT autoplans. Additionally, the 350- and 10-degree collimation angles were selected in the left- and right-sided PMRT autoplans, respectively. The uniformity index and conformity index of the planning target volume, mean heart dose, spinal cord D_0.03cc, mean lung dose, and V_5Gy and V_20Gy of the lung of autoplans were significantly better compared with the manual clinical plans. An artificial intelligence-based automated treatment planning method for postmastectomy VMAT has been developed to ensure plan quality and improve clinical efficiency.

Development and Implementation of an Open Source Template Interpretation Class Library for Automated Treatment Planning

PURPOSE

Widespread implementation of automated treatment planning in radiation therapy remains elusive due to variability in clinic and physician preferences making it difficult to ensure consistent plan parameters. We have developed an open-source class library with the aim to improve efficiency and consistency for automated treatment planning in radiation therapy.

METHODS AND MATERIALS

An open source class library has been developed that interprets clinical templates within a commercial treatment planning system into a treatment plan for automated planning. This code was leveraged for the automated planning of 39 patients and retrospectively compared to the 78 clinically approved manual plans.

RESULTS

From the initial 39 patients, 74 of 78 plans were successfully generated without manual intervention. Target dose was more homogenous for automated plans, with an average homogeneity index of 3.30 vs 3.11 for manual and automated plans, respectively (p = 0.107). Generalized equivalent uniform dose decreased in the femurs and rectum for automated plans, with mean gEUD of 3746 cGy vs 3338 cGy (p ≤ 0.001) and 5761 cGy vs 5634 cGy (p ≤ 0.001) for femurs and rectum, respectively. Dose metrics for bladder and rectum (V6500 cGy and V4000 cGy) show recognizable but insignificant improvements. All automated plans delivered for quality assurance passed a gamma analysis (>95%) with an average composite pass rate of 99.3% and 98.8% for pelvis and prostate plans, respectively. Deliverability parameters such as total monitor units and aperture complexity indicate deliverable plans.

CONCLUSIONS

Prostate cancer and pelvic node radiotherapy can be automated using VMAT planning and clinical templates based on a standardized clinical workflow. The class library developed in this study conveniently interfaces between the plan template and the treatment planning system to automatically generate high quality plans on customizable templates.

Comparison of volumetric modulated arc therapy and intensity-modulated radiotherapy for left-sided whole-breast irradiation using automated planning

Background

Published treatment technique comparisons for postoperative left-sided whole breast irradiation (WBI) with deep-inspiration breath-hold (DIBH) are scarce, small, and inconclusive. In this study, fully automated multi-criterial plan optimization, generating a single high-quality, Pareto-optimal plan per patient and treatment technique, was used to compare for a large patient cohort 1) intensity modulated radiotherapy (IMRT) with two tangential fields and 2) volumetric modulated arc therapy (VMAT) with two small tangential subarcs.

Materials and methods

Forty-eight randomly selected patients recently treated with DIBH and 16 × 2.66 Gy were included. The optimizer was configured for the clinical planning protocol. Comparisons between IMRT and VMAT included dosimetric plan parameters, estimated excess relative risks (ERR) for toxicities, delivery times, MUs, and deliverability accuracy at a linac.

Results

The automatically generated IMRT and VMAT plans applied in this study were similar or higher in quality than the manually generated clinical plans. For equal PTVin V95% (98.4 ± 0.9%), VMAT had significant advantages compared to IMRT regarding breast dose homogeneity and doses in heart and ipsilateral lung, at the cost of some minor deteriorations for contralateral breast (few cases with larger deteriorations) and lung. Conformality improved from 1.38 to 1.18 (p < 0.001). With VMAT, ERR for major coronary events and ipsilateral lung tumors were reduced by 3% (range: −1–12%) and 16% (range: −3–38%), respectively. MUs and delivery times were higher for VMAT. There were no statistical differences in γ passing rates.

Conclusion

For WBI in conservative therapy of left-sided breast patients treated with DIBH, VMAT with two tangential subarcs was generally dosimetrically superior to IMRT with two tangential static fields. Results need confirmation by robustness analyses.

Assessing the performance of an automated breast treatment planning software

Purpose

To assess the dosimetric performance of an automated breast planning software.

Methods

We retrospectively reviewed 15 breast cancer patients treated with tangent fields according to the RTOG 1005 protocol and 30 patients treated off‐protocol. Planning with electronic compensators (eComps) via manual, iterative fluence editing was compared to an automated planning program called EZFluence (EZF) (Radformation, Inc.). We compared the minimum dose received by 95% of the volume (D95%), D90%, the volume receiving at least 105% of prescription (V105%), V95%, the conformity index of the V95% and PTV volumes (CI95%), and total monitor units (MUs). The PTV_Eval structure generated by EZF was compared to the RTOG 1005 breast PTV_Eval structure.

Results

The average D95% was significantly greater for the EZF plans, 95.0%, vs. the original plans 93.2% (P = 0.022). CI95% was less for the EZF plans, 1.18, than the original plans, 1.48 (P = 0.09). D90% was only slightly greater for EZF, averaging at 98.3% for EZF plans and 97.3% for the original plans (P = 0.0483). V105% (cc) was, on average, 27.8cc less in the EZF breast plans, which was significantly less than for those manually planned. The average number of MUs for the EZF plans, 453, was significantly less than original protocol plans, 500 (P = 8 × 10⁻⁶). The average difference between the protocol PTV volume and the EZF PTV volume was 196 cc, with all but two cases having a larger EZF PTV volume (P = 0.020).

Conclusion

EZF improved dose homogeneity, coverage, and MU efficiency vs. manually produced eComp plans. The EZF‐generated PTV eval is based on the volume encompassed by the tangents, and is not appropriate for dosimetric comparison to constraints for RTOG 1005 PTV eval. EZF produced dosimetrically similar or superior plans to manual, iteratively derived plans and may also offer time and efficiency benefits.

Clinical Experience With Machine Learning-Based Automated Treatment Planning for Whole Breast Radiation Therapy

PURPOSE

The machine learning-based automated treatment planning (MLAP) tool has been developed and evaluated for breast radiation therapy planning at our institution. We implemented MLAP for patient treatment and assessed our clinical experience for its performance.

METHODS AND MATERIALS

A total of 102 patients of breast or chest wall treatment plans were prospectively evaluated with institutional review board approval. A human planner executed MLAP to create an auto-plan via automation of fluence maps generation. If judged necessary, a planner further fine-tuned the fluence maps to reach a final plan. Planners recorded the time required for auto-planning and manual modification. Target (ie, breast or chest wall and nodes) coverage and dose homogeneity were compared between the auto-plan and final plan.

RESULTS

Cases without nodes (n = 71) showed negligible (<1%) differences for target coverage and dose homogeneity between the auto-plan and final plan. Cases with nodes (n = 31) also showed negligible difference for target coverage. However, mean ± standard deviation of volume receiving 105% of the prescribed dose and maximum dose were reduced from 43.0% ± 26.3% to 39.4% ± 23.7% and 119.7% ± 9.5% to 114.4% ± 8.8% from auto-plan to final plan, respectively, all with P ≤ .01 for cases with nodes (n = 31). Mean ± standard deviation time spent for auto-plans and additional fluence modification for final plans were 12.1 ± 9.3 and 13.1 ± 12.9 minutes, respectively, for cases without nodes, and 16.4 ± 9.7 and 26.4 ± 16.4 minutes, respectively, for cases with nodes.

CONCLUSIONS

The MLAP tool has been successfully implemented for routine clinical practice and has significantly improved planning efficiency. Clinical experience indicates that auto-plans are sufficient for target coverage, but improvement is warranted to reduce high dose volume for cases with nodal irradiation. This study demonstrates the clinical implementation of auto-planning for patient treatment and the significant importance of integrating human experience and feedback to improve MLAP for better clinical translation.

Generating High-Quality Lymph Node Clinical Target Volumes for Head and Neck Cancer Radiation Therapy Using a Fully Automated Deep Learning-Based Approach

PURPOSE

To develop a deep learning model that generates consistent, high-quality lymph node clinical target volumes (CTV) contours for head and neck cancer (HNC) patients, as an integral part of a fully automated radiation treatment planning workflow.

METHODS AND MATERIALS

Computed tomography (CT) scans from 71 HNC patients were retrospectively collected and split into training (n = 51), cross-validation (n = 10), and test (n = 10) data sets. All had target volume delineations covering lymph node levels Ia through V (Ia-V), Ib through V (Ib-V), II through IV (II-IV), and retropharyngeal (RP) nodes, which were previously approved by a radiation oncologist specializing in HNC. Volumes of interest (VOIs) about nodal levels were automatically identified using computer vision techniques. The VOI (cropped CT image) and approved contours were used to train a U-Net autosegmentation model. Each lymph node level was trained independently, with model parameters optimized by assessing performance on the cross-validation data set. Once optimal model parameters were identified, overlap and distance metrics were calculated between ground truth and autosegmentations on the test set. Lastly, this final model was used on 32 additional patient scans (not included in original 71 cases) and autosegmentations visually rated by 3 radiation oncologists as being "clinically acceptable without requiring edits," "requiring minor edits," or "requiring major edits."

RESULTS

When comparing ground truths to autosegmentations on the test data set, median Dice Similarity Coefficients were 0.90, 0.90, 0.89, and 0.81, and median mean surface distance values were 1.0 mm, 1.0 mm, 1.1 mm, and 1.3 mm for node levels Ia-V, Ib-V, II-IV, and RP nodes, respectively. Qualitative scoring varied among physicians. Overall, 99% of autosegmented target volumes were either scored as being clinically acceptable or requiring minor edits (ie, stylistic recommendations, <2 minutes).

CONCLUSIONS

We developed a fully automated artificial intelligence approach to autodelineate nodal CTVs for patients with intact HNC. Most autosegmentations were found to be clinically acceptable after qualitative review when considering recommended stylistic edits. This promising work automatically delineates nodal CTVs in a robust and consistent manner; this approach can be implemented in ongoing efforts for fully automated radiation treatment planning.

Clinical Acceptability of Automated Radiation Treatment Planning for Head and Neck Cancer Using the Radiation Planning Assistant

PURPOSE

Radiation treatment planning for head and neck cancer is a complex process with much variability; automated treatment planning is a promising option to improve plan quality and efficiency. This study compared radiation plans generated from a fully automated radiation treatment planning system to plans generated manually that had been clinically approved and delivered.

METHODS AND MATERIALS

The study cohort consisted of 50 patients treated by a specialized head and neck cancer team at a tertiary care center. An automated radiation treatment planning system, the Radiation Planning Assistant, was used to create autoplans for all patients using their original, approved contours. Common dose-volume histogram (DVH) criteria were used to compare the quality of autoplans to the clinical plans. Fourteen radiation oncologists, each from a different institution, then reviewed and compared the autoplans and clinical plans in a blinded fashion.

RESULTS

Autoplans and clinical plans were very similar with regard to DVH metrics for coverage and critical structure constraints. Physician reviewers found both the clinical plans and autoplans acceptable for use; overall, 78% of the clinical plans and 88% of the autoplans were found to be usable as is (without any edits). When asked to choose which plan would be preferred for approval, 27% of physician reviewers selected the clinical plan, 47% selected the autoplan, 25% said both were equivalent, and 0% said neither. Hence, overall, 72% of physician reviewers believed the autoplan or either the clinical or autoplan was preferable.

CONCLUSIONS

Automated radiation treatment planning creates consistent, clinically acceptable treatment plans that meet DVH criteria and are found to be appropriate on physician review.

Evaluation of a multiview architecture for automatic vertebral labeling of palliative radiotherapy simulation CT images

PURPOSE

The purpose of this work was to evaluate the performance of X-Net, a multiview deep learning architecture, to automatically label vertebral levels (S2-C1) in palliative radiotherapy simulation CT scans.

METHODS

For each patient CT scan, our automated approach 1) segmented spinal canal using a convolutional-neural network (CNN), 2) formed sagittal and coronal intensity projection pairs, 3) labeled vertebral levels with X-Net, and 4) detected irregular intervertebral spacing using an analytic methodology. The spinal canal CNN was trained via fivefold cross validation using 1,966 simulation CT scans and evaluated on 330 CT scans. After labeling vertebral levels (S2-C1) in 897 palliative radiotherapy simulation CT scans, a volume of interest surrounding the spinal canal in each patient's CT scan was converted into sagittal and coronal intensity projection image pairs. Then, intensity projection image pairs were augmented and used to train X-Net to automatically label vertebral levels using fivefold cross validation (n = 803). Prior to testing upon the final test set (n = 94), CT scans of patients with anatomical abnormalities, surgical implants, or other atypical features from the final test set were placed in an outlier group (n = 20), whereas those without these features were placed in a normative group (n = 74). The performance of X-Net, X-Net Ensemble, and another leading vertebral labeling architecture (Btrfly Net) was evaluated on both groups using identification rate, localization error, and other metrics. The performance of our approach was also evaluated on the MICCAI 2014 test dataset (n = 60). Finally, a method to detect irregular intervertebral spacing was created based on the rate of change in spacing between predicted vertebral body locations and was also evaluated using the final test set. Receiver operating characteristic analysis was used to investigate the performance of the method to detect irregular intervertebral spacing.

RESULTS

The spinal canal architecture yielded centroid coordinates spanning S2-C1 with submillimeter accuracy (mean ± standard deviation, 0.399 ± 0.299 mm; n = 330 patients) and was robust in the localization of spinal canal centroid to surgical implants and widespread metastases. Cross-validation testing of X-Net for vertebral labeling revealed that the deep learning model performance (F1 score, precision, and sensitivity) improved with CT scan length. The X-Net, X-Net Ensemble, and Btrfly Net mean identification rates and localization errors were 92.4% and 2.3 mm, 94.2% and 2.2 mm, and 90.5% and 3.4 mm, respectively, in the final test set and 96.7% and 2.2 mm, 96.9% and 2.0 mm, and 94.8% and 3.3 mm, respectively, within the normative group of the final test set. The X-Net Ensemble yielded the highest percentage of patients (94%) having all vertebral bodies identified correctly in the final test set when the three most inferior and superior vertebral bodies were excluded from the CT scan. The method used to detect labeling failures had 67% sensitivity and 95% specificity when combined with the X-Net Ensemble and flagged five of six patients with atypical vertebral counts (additional thoracic (T13), additional lumbar (L6) or only four lumbar vertebrae). Mean identification rate on the MICCAI 2014 dataset using an X-Net Ensemble was increased from 86.8% to 91.3% through the use of transfer learning and obtained state-of-the-art results for various regions of the spine.

CONCLUSIONS

We trained X-Net, our unique convolutional neural network, to automatically label vertebral levels from S2 to C1 on palliative radiotherapy CT images and found that an ensemble of X-Net models had high vertebral body identification rate (94.2%) and small localization errors (2.2 ± 1.8 mm). In addition, our transfer learning approach achieved state-of-the-art results on a well-known benchmark dataset with high identification rate (91.3%) and low localization error (3.3 mm ± 2.7 mm). When we pre-screened radiotherapy CT images for the presence of hardware, surgical implants, or other anatomic abnormalities prior to the use of X-Net, it labeled the spine correctly in more than 97% of patients and 94% of patients when scans were not prescreened. Automatically generated labels are robust to widespread vertebral metastases and surgical implants and our method to detect labeling failures based on neighborhood intervertebral spacing can reliably identify patients with an additional lumbar or thoracic vertebral body.

Optimization of autogenerated chest-wall radiation treatment plans developed for postmastectomy breast cancer patients in underserved clinics

Over the past decade, several strides have been made to improve the management of breast cancer in developing countries; however, there are still obstacles present. In the area of radiation therapy, these hurdles include limited access to radiotherapy treatment and scarcity of oncology specialists. In an effort to reduce inequities in cancer care while improving patient outcomes, our research is focused on developing automated postmastectomy radiation therapy (PMRT) plans for breast cancer patients in these underserved communities that can be further improved upon through treatment planning system (TPS) specific optimization guidelines. The automated planning tool utilized algorithms integrated with Varian's Eclipse TPS. The tool created PMRT plans that used monoisocentric tangents and supraclavicular (SCV) fields with a mix of high and low energy photon beams along with field-in-field (FIF) segments. The completed autogenerated PMRT plans were imported into Phillip's Pinnacle 9.10 and Varian's Eclipse 13.6 TPSs to be further improved through manual optimization; the time required to complete this step was measured and assessed. A senior dosimetrist, physicist, and physician evaluated the optimized plans for clinical acceptability. Guidelines were developed for the planning systems that can be implemented by personnel with either limited experience in radiation treatment planning or those with limited time to produce treatment plans. The autogenerated plans in conjunction with our guidelines have shown to significantly reduce the time required to produce a clinically acceptable PMRT plan from approximately 120 ± 60 minutes to just 13 ± 11 (Pinnacle) and 12 ± 7 (Eclipse) minutes, reducing the total uninterrupted treatment planning time by an average of 108 ± 51 minutes. The results from this research indicate that the autogenerated PMRT plans along with the optimization guidelines are a viable option to provide quality and clinically acceptable PMRT plans that are more efficient and consistent for postmastectomy breast cancer patients in severely underserved communities.