Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System

To develop and evaluate an automated whole-brain radiotherapy (WBRT) treatment planning pipeline with a deep learning-based autocontouring and customizable landmark-based field aperture design. Methods: The pipeline consisted of the following steps:(1) Auto-contour normal structures on computed tomography scans and digitally reconstructed radiographs using deep learning techniques, (2) locate the landmark structures using the beam's-eye-view, (3) generate field apertures based on eight different landmark rules addressing different clinical purposes and physician preferences. Two parallel approaches for generating field apertures were developed for quality control. The performance of the generated field shapes and dose distributions were compared with the original clinical plans. The clinical acceptability of the plans was assessed by five radiation oncologists from four hospitals. Results: The performance of the generated field apertures was evaluated by the Hausdorff distance (HD) and mean surface distance (MSD) from 182 patients' field apertures used in the clinic. The average HD and MSD for the generated field apertures were 16 ± 7 and 7 ± 3 mm for the first approach, respectively, and 17 ± 7 and 7 ± 3 mm, respectively, for the second approach. The differences regarding HD and MSD between the first and the second approaches were 1 ± 2 and 1 ± 3 mm, respectively. A clinical review of the field aperture design, conducted using 30 patients, achieved a 100% acceptance rate for both the first and second approaches, and the plan review achieved a 100% acceptance rate for the first approach and a 93% acceptance rate for the second approach. The average acceptance rate for meeting lens dosimetric recommendations was 80% (left lens) and 77% (right lens) for the first approach, and 70% (both left and right lenses) for the second approach, compared with 50% (left lens) and 53% (right lens) for the clinical plans. Conclusion:This study provided an automated pipeline with two field aperture generation approaches to automatically generate WBRT treatment plans. Both quantitative and qualitative evaluations demonstrated that our novel pipeline was comparable with the original clinical plans.

Section: Discussionmentioning

confidence: 99%

Customizable landmark‐based field aperture design for automated whole‐brain radiotherapy treatment planning

Xiao

Cárdenas

Rhee

et al. 2022

“…The RPA is an automated contouring and treatment planning tool currently under development to provide high‐quality radiation therapy treatments to low‐resource communities throughout the world 18 . The RPA is a web‐based system that uses artificial intelligence to simplify the planning process.…”

Section: Methodsmentioning

confidence: 99%

“…In this study, we used hazard testing to evaluate the human component of radiation oncology workflows, which is often not addressed in commissioning processes, using the Radiation Planning Assistant (RPA), an automated contouring and treatment planning software tool, as a case study 18 …”

Section: Introductionmentioning

confidence: 99%

Hazard testing to reduce risk in the development of automated planning tools

Nealon

Douglas

Han

et al. 2023

Self Cite

Purpose Hazard scenarios were created to assess and reduce the risk of planning errors in automated planning processes. This was accomplished through iterative testing and improvement of examined user interfaces. Methods Automated planning requires three user inputs: a computed tomography (CT), a prescription document, known as the service request, and contours. We investigated the ability of users to catch errors that were intentionally introduced into each of these three stages, according to an FMEA analysis. Five radiation therapists each reviewed 15 patient CTs, containing three errors: inappropriate field of view, incorrect superior border, and incorrect identification of isocenter. Four radiation oncology residents reviewed 10 service requests, containing two errors: incorrect prescription and treatment site. Four physicists reviewed 10 contour sets, containing two errors: missing contour slices and inaccurate target contour. Reviewers underwent video training prior to reviewing and providing feedback for various mock plans. Results Initially, 75% of hazard scenarios were detected in the service request approval. The visual display of prescription information was then updated to improve the detectability of errors based on user feedback. The change was then validated with five new radiation oncology residents who detected 100% of errors present. 83% of the hazard scenarios were detected in the CT approval portion of the workflow. For the contour approval portion of the workflow none of the errors were detected by physicists, indicating this step will not be used for quality assurance of contours. To mitigate the risk from errors that could occur at this step, radiation oncologists must perform a thorough review of contour quality prior to final plan approval. Conclusions Hazard testing was used to pinpoint the weaknesses of an automated planning tool and as a result, subsequent improvements were made. This study identified that not all workflow steps should be used for quality assurance and demonstrated the importance of performing hazard testing to identify points of risk in automated planning tools.

“…Simulation CT scans and radiotherapy treatment plans from 310 patients with cervical cancer previously treated at our institution were retrospectively used in this study after institutional review board approval. All patients had physician‐approved four‐field box radiotherapy treatment plans generated by the Radiation Planning Assistant, an automated treatment planning platform 18 . DRRs were created using the Radiation Planning Assistant 18,19 and had an isotropic pixel length of 0.68 mm with a resulting matrix size of 512 × 512 (field of view 350 mm).…”

Section: Methodsmentioning

confidence: 99%

Identifying the optimal deep learning architecture and parameters for automatic beam aperture definition in 3D radiotherapy

Gay,

Kisling,

Anderson

et al. 2023

PurposeTwo‐dimensional radiotherapy is often used to treat cervical cancer in low‐ and middle‐income countries, but treatment planning can be challenging and time‐consuming. Neural networks offer the potential to greatly decrease planning time through automation, but the impact of the wide range of hyperparameters to be set during training on model accuracy has not been exhaustively investigated. In the current study, we evaluated the effect of several convolutional neural network architectures and hyperparameters on 2D radiotherapy treatment field delineation.MethodsSix commonly used deep learning architectures were trained to delineate four‐field box apertures on digitally reconstructed radiographs for cervical cancer radiotherapy. A comprehensive search of optimal hyperparameters for all models was conducted by varying the initial learning rate, image normalization methods, and (when appropriate) convolutional kernel size, the number of learnable parameters via network depth and the number of feature maps per convolution, and nonlinear activation functions. This yielded over 1700 unique models, which were all trained until performance converged and then tested on a separate dataset.ResultsOf all hyperparameters, the choice of initial learning rate was most consistently significant for improved performance on the test set, with all top‐performing models using learning rates of 0.0001. The optimal image normalization was not consistent across architectures. High overlap (mean Dice similarity coefficient = 0.98) and surface distance agreement (mean surface distance < 2 mm) were achieved between the treatment field apertures for all architectures using the identified best hyperparameters. Overlap Dice similarity coefficient (DSC) and distance metrics (mean surface distance and Hausdorff distance) indicated that DeepLabv3+ and D‐LinkNet architectures were least sensitive to initial hyperparameter selection.ConclusionDeepLabv3+ and D‐LinkNet are most robust to initial hyperparameter selection. Learning rate, nonlinear activation function, and kernel size are also important hyperparameters for improving performance.