Deep Learning–Based Dose Prediction for Automated, Individualized Quality Assurance of Head and Neck Radiation Therapy Plans

Gronberg, Mary; Beadle, Beth M.; Garden, Adam S.; Skinner, Heath D.; Gay, Skylar; Netherton, Tucker; Cao, Wenhua; Cárdenas, Carlos; Chung, Christine H.; Fuentes, David; Fuller, C.D.; Howell, Rebecca M.; Jhingran, Anuja; Lim, Tze Yee; Marquez, Barbara; Mumme, Raymond; Olanrewaju, Adenike; Peterson, Christine B.; Vazquez, Ivan; Whitaker, Thomas J.; Wooten, Zachary; Yang, Ming; Court, Laurence E.

doi:10.1016/j.prro.2022.12.003

Cited by 20 publications

(24 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The model architecture was a 3D Dense Dilated U‐Net, which gave us accurate dose prediction results in our prior work on head and neck cancers 2,19 . Several custom loss functions were investigated, and model performance was compared with quantitative and qualitative evaluations of predicted dose distributions on the validation set.…”

Section: Methodsmentioning

confidence: 99%

“…The potential of deep learning–based dose prediction to develop patient‐specific plan quality assurance tools should be further investigated. In our prior work, we showed the ability of deep learning–based dose predictions to automatically identify suboptimal head and neck plans 2 . Here, we have expanded on our prior work in artificial intelligence–based plan quality assurance.…”

Section: Introductionmentioning

confidence: 94%

See 1 more Smart Citation

Deep learning–based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers

Gronberg,

Jhingran,

Netherton

et al. 2023

Medical Physics

Self Cite

View full text Add to dashboard Cite

BackgroundIn recent years, deep‐learning models have been used to predict entire three‐dimensional dose distributions. However, the usability of dose predictions to improve plan quality should be further investigated.PurposeTo develop a deep‐learning model to predict high‐quality dose distributions for volumetric modulated arc therapy (VMAT) plans for patients with gynecologic cancer and to evaluate their usability in driving plan quality improvements.MethodsA total of 79 VMAT plans for the female pelvis were used to train (47 plans), validate (16 plans), and test (16 plans) 3D dense dilated U‐Net models to predict 3D dose distributions. The models received the normalized CT scan, dose prescription, and target and normal tissue contours as inputs. Three models were used to predict the dose distributions for plans in the test set. A radiation oncologist specializing in the treatment of gynecologic cancers scored the test set predictions using a 5‐point scale (5, acceptable as‐is; 4, prefer minor edits; 3, minor edits needed; 2, major edits needed; and 1, unacceptable). The clinical plans for which the dose predictions indicated that improvements could be made were reoptimized with constraints extracted from the predictions.ResultsThe predicted dose distributions in the test set were of comparable quality to the clinical plans. The mean voxel‐wise dose difference was −0.14 ± 0.46 Gy. The percentage dose differences in the predicted target metrics of and were −1.05% ± 0.59% and 0.21% ± 0.28%, respectively. The dose differences in the predicted organ at risk mean and maximum doses were −0.30 ± 1.66 Gy and −0.42 ± 2.07 Gy, respectively. A radiation oncologist deemed all of the predicted dose distributions clinically acceptable; 12 received a score of 5, and four received a score of 4. Replanning of flagged plans (five plans) showed that the original plans could be further optimized to give dose distributions close to the predicted dose distributions.ConclusionsDeep‐learning dose prediction can be used to predict high‐quality and clinically acceptable dose distributions for VMAT female pelvis plans, which can then be used to identify plans that can be improved with additional optimization.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 94%

Deep learning–based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers

Gronberg,

Jhingran,

Netherton

et al. 2023

Medical Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Dose prediction as a quality assurance tool was recently suggested by Gronberg et al, in which they propose to flag OARs that receive excess dose as determined by an evaluation of the difference between an existing plan's dose and the model's dose prediction. 11 Despite recent activity in the topic of H&N dose prediction, we could not identify any prior works that trained patient-specific dose prediction models for ART.…”

Section: Introductionmentioning

confidence: 99%

Intentional deep overfit learning for patient‐specific dose predictions in adaptive radiotherapy

et al. 2023

View full text Add to dashboard Cite

BackgroundThe framework of adaptive radiation therapy (ART) was crafted to address the underlying sources of intra‐patient variation that were observed throughout numerous patients' radiation sessions. ART seeks to minimize the consequential dosimetric uncertainty resulting from this daily variation, commonly through treatment planning re‐optimization. Re‐optimization typically consists of manual evaluation and modification of previously utilized optimization criteria. Ideally, frequent treatment plan adaptation through re‐optimization on each day's computed tomography (CT) scan may improve dosimetric accuracy and minimize dose delivered to organs at risk (OARs) as the planning target volume (PTV) changes throughout the course of treatment.PurposeRe‐optimization in its current form is time‐consuming and inefficient. In response to this ART bottleneck, we propose a deep learning based adaptive dose prediction model that utilizes a head and neck (H&N) patient's initial planning data to fine‐tune a previously trained population model towards a patient‐specific model. Our fine‐tuned, patient‐specific (FT‐PS) model, which is trained using the intentional deep overfit learning (IDOL) method, may enable clinicians and treatment planners to rapidly evaluate relevant dosimetric changes daily and re‐optimize accordingly.MethodsAn adaptive population (AP) model was trained using adaptive data from 33 patients. Separately, 10 patients were selected for training FT‐PS models. The previously trained AP model was utilized as the base model weights prior to re‐initializing model training for each FT‐PS model. Ten FT‐PS models were separately trained by fine‐tuning the previous model weights based on each respective patient's initial treatment plan. From these 10 patients, 26 ART treatment plans were withheld from training as the test dataset for retrospective evaluation of dose prediction performance between the AP and FT‐PS models. Each AP and FT‐PS dose prediction was compared against the ground truth dose distribution as originally generated during the patient's course of treatment. Mean absolute percent error (MAPE) evaluated the dose differences between a model's prediction and the ground truth.ResultsMAPE was calculated within the 10% isodose volume region of interest for each of the AP and FT‐PS models dose predictions and averaged across all test adaptive sessions, yielding 5.759% and 3.747% respectively. MAPE differences were compared between AP and FT‐PS models across each test session in a test of statistical significance. The differences were statistically significant in a paired t‐test with two‐tailed p‐value equal to and 95% confidence interval (CI) equal to [−2.483, −1.542]. Furthermore, MAPE was calculated using each individually segmented structure as an ROI. Nineteen of 24 structures demonstrated statistically significant differences between the AP and FT‐PS models.ConclusionWe utilized the IDOL method to fine‐tune a population‐based dose prediction model into an adaptive, patient‐specific model. The averaged MAPE across the test dataset was 5.759% for the population‐based model versus 3.747% for the fine‐tuned, patient‐specific model, and the difference in MAPE between models was found to be statistically significant. Our work demonstrates the feasibility of patient‐specific models in adaptive radiotherapy, and offers unique clinical benefit by utilizing initial planning data that contains the physician's treatment intent.

show abstract

“…1,2 Knowledge-based planning (KBP) is an approach that has been shown to improve plan quality in multi-institutional clinical trials, 3,4 and identify low-quality treatment plans during peer review. [5][6][7] There is great interest within radiation oncology for developing high-quality KBP models, as evidenced by the 2020 OpenKBP AAPM Grand Challenge, which included 195 participants from 28 countries. 8 KBP models are typically used to either directly estimate a dose distribution [9][10][11][12] or predict a dose-volume histogram.…”

Section: Introductionmentioning

confidence: 99%

“…Radiation treatment plan quality across institutions or even across planners within a given institution can be highly heterogeneous, partially due to planner experience 1,2 . Knowledge‐based planning (KBP) is an approach that has been shown to improve plan quality in multi‐institutional clinical trials, 3,4 and identify low‐quality treatment plans during peer review 5–7 …”

Section: Introductionmentioning

confidence: 99%

Automated evaluation for rapid implementation of knowledge‐based radiotherapy planning models

Harms,

Pogue,

Cardenas

et al. 2023

J Applied Clin Med Phys

Self Cite

View full text Add to dashboard Cite

PurposeKnowledge‐based planning (KBP) offers the ability to predict dose‐volume metrics based on information extracted from previous plans, reducing plan variability and improving plan quality. As clinical integration of KBP is increasing there is a growing need for quantitative evaluation of KBP models. A .NET‐based application, RapidCompare, was created for automated plan creation and analysis of Varian RapidPlan models.MethodsRapidCompare was designed to read calculation parameters and a list of reference plans. The tool copies the reference plan field geometry and structure set, applies the RapidPlan model, optimizes the KBP plan, and generates data for quantitative evaluation of dose‐volume metrics. A cohort of 85 patients, divided into training (50), testing (10), and validation (25) groups, was used to demonstrate the utility of RapidCompare. After training and tuning, the KBP model was paired with three different optimization templates to compare various planning strategies in the validation cohort. All templates used the same set of constraints for the planning target volume (PTV). For organs‐at‐risk, the optimization template provided constraints using the whole dose‐volume histogram (DVH), fixed‐dose/volume points, or generalized equivalent uniform dose (gEUD). The resulting plans from each optimization approach were compared using DVH metrics.ResultsRapidCompare allowed for the automated generation of 75 total plans for comparison with limited manual intervention. In comparing optimization techniques, the Dose/Volume and Lines optimization templates generated plans with similar DVH metrics, with a slight preference for the Lines technique with reductions in heart V30Gy and spinal cord max dose. The gEUD model produced high target heterogeneity.ConclusionAutomated evaluation allowed for the exploration of multiple optimization templates in a larger validation cohort than would have been feasible using a manual approach. A final KBP model using line optimization objectives produced the highest quality plans without human intervention.

show abstract

Deep Learning–Based Dose Prediction for Automated, Individualized Quality Assurance of Head and Neck Radiation Therapy Plans

Cited by 20 publications

References 27 publications

Deep learning–based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers

Deep learning–based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers

Intentional deep overfit learning for patient‐specific dose predictions in adaptive radiotherapy

Automated evaluation for rapid implementation of knowledge‐based radiotherapy planning models

Contact Info

Product

Resources

About