Dataset Information

Deep Learning-Based Fluence Map Prediction for Pancreas Stereotactic Body Radiation Therapy With Simultaneous Integrated Boost.

ABSTRACT:

Purpose

Treatment planning for pancreas stereotactic body radiation therapy (SBRT) is a challenging task, especially with simultaneous integrated boost treatment approaches. We propose a deep learning (DL) framework to accurately predict fluence maps from patient anatomy and directly generate intensity modulated radiation therapy plans.

Methods and materials

The framework employs 2 convolutional neural networks (CNNs) to sequentially generate beam dose prediction and fluence map prediction, creating a deliverable 9-beam intensity modulated radiation therapy plan. Within the beam dose prediction CNN, axial slices of combined structure contour masks are used to predict 3-dimensional (3D) beam doses for each beam. Each 3D beam dose is projected along its beam's-eye-view to form a 2D beam dose map, which is subsequently used by the fluence map prediction CNN to predict its fluence map. Finally, the 9 predicted fluence maps are imported into the treatment planning system to finalize the plan by leaf sequencing and dose calculation. One hundred patients receiving pancreas SBRT were retrospectively collected for this study. Benchmark plans with unified simultaneous integrated boost prescription (25/33 Gy) were manually optimized for each case. The data set was split into 80/20 cases for training and testing. We evaluated the proposed DL framework by assessing both the fluence maps and the final predicted plans. Further, clinical acceptability of the plans was evaluated by a physician specializing in gastrointestinal cancer.

Results

The DL-based planning was, on average, completed in under 2 minutes. In testing, the predicted plans achieved similar dose distribution compared with the benchmark plans (-1.5% deviation for planning target volume 33 V_33Gy), with slightly higher planning target volume maximum (+1.03 Gy) and organ at risk maximum (+0.95 Gy) doses. After renormalization, the physician rated 19 cases clinically acceptable and 1 case requiring minor improvement.

Conclusions

The DL framework can effectively plan pancreas SBRT cases within 2 minutes. The predicted plans are clinically deliverable, with plan quality approaching that of manual planning.

SUBMITTER: Wang W

PROVIDER: S-EPMC8099762 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposePancreas stereotactic body radiation therapy (SBRT) treatment planning requires planners to make sequential, time-consuming interactions with the treatment planning system to reach the optimal dose distribution. We sought to develop a reinforcement learning (RL)-based planning bot to systematically address complex tradeoffs and achieve high plan quality consistently and efficiently.Methods and materialsThe focus of pancreas SBRT planning is finding a balance between organ-at-risk sparing and planning target volume (PTV) coverage. Planners evaluate dose distributions and make planning adjustments to optimize PTV coverage while adhering to organ-at-risk dose constraints. We formulated such interactions between the planner and treatment planning system into a finite-horizon RL model. First, planning status features were evaluated based on human planners' experience and defined as planning states. Second, planning actions were defined to represent steps that planners would commonly implement to address different planning needs. Finally, we derived a reward system based on an objective function guided by physician-assigned constraints. The planning bot trained itself with 48 plans augmented from 16 previously treated patients, and generated plans for 24 cases in a separate validation set.ResultsAll 24 bot-generated plans achieved similar PTV coverages compared with clinical plans while satisfying all clinical planning constraints. Moreover, the knowledge learned by the bot could be visualized and interpreted as consistent with human planning knowledge, and the knowledge maps learned in separate training sessions were consistent, indicating reproducibility of the learning process.ConclusionsWe developed a planning bot that generates high-quality treatment plans for pancreas SBRT. We demonstrated that the training phase of the bot is tractable and reproducible, and the knowledge acquired is interpretable. As a result, the RL planning bot can potentially be incorporated into the clinical workflow and reduce planning inefficiencies.

Project description:PurposeWe evaluate the feasibility of the elective nodal irradiation strategy in stereotactic body radiotherapy (SBRT) for pancreatic cancer.MethodsThree simultaneous integrated boost (SIB)-SBRT plans (Boost1, Boost2, and Boost3) were retrospectively generated for each of 20 different patients. Boost1 delivered 33 and 25 Gy to PTV1 and PTV2, respectively. Boost2 delivered 40, 33, and 25 Gy to boostCTV, PTV1, and PTV2, respectively. Boost3 delivered 33 and 25 Gy to PTV1 and PTV3, respectively. PTV1 covered the initial standard SBRT plan (InitPlan) gross tumor volume (GTV). PTV2 covered CTVgeom which was created by a 10-mm expansion (15 mm posterior) of GTV. PTV3 covered CTVprop which included elective nodal regions. The boostCTV included GTV as well as involved vasculature. The planning feasibility in each scenario and dose-volume histograms (DVHs) were analyzed and compared with the InitPlan (delivered 33 Gy only to PTV1) by paired t-test. Next, a novel DVH prediction model was developed and its performance was evaluated according to the prediction accuracy (AC) of planning violations. Then, the model was used to simulate the impacts of GTV-to-organs at risk (OAR) distance and gastrointestinal (GI) OAR volume variations on planning feasibility.ResultsSignificant dose increases were observed in GI-OARs in SIB-SBRT plans when compared with InitPlan. All dose constraints were met in 63% of cases in InitPlan, Boost1, and Boost2, whereas Boost3 developed DVH violations in all cases. Utilizing previous patient anatomy, the novel DVH prediction model achieved a high AC in the prediction of violations for GI-OARs; the positive predictive value, negative predictive value, and AC were 66%, 90%, and 84%, respectively. Experiments with the model demonstrated that the larger proximity volume of GI-OAR at the shorter distance substantially impacted on planning violations.ConclusionsSIB-SBRT plan with geometrically defined prophylactic areas can be dosimetrically feasible, but including all nodal areas with 25 Gy in five fractions appears to be unrealistic.

Project description:BackgroundRadiation therapy and chemoradiation therapy play a major role in the definitive management of esophageal cancer. Survival in esophageal cancer patients is still relatively poor, mostly due to high rates of local recurrence and distant metastases. It is hypothesized that dose escalation in radiotherapy could improve outcomes. Therefore, this retrospective analysis aimed to investigate the outcomes and toxicity in patients treated with local dose escalation by means of using simultaneous integrated boost concepts.MethodsBetween 2012 and 2018, 101 patients with esophageal carcinoma were analyzed in this monocentric, retrospective study. All patients received definitive chemoradiation or radiation therapy alone as intensity modulated radiotherapy. The prescribed dose was 50.4 Gy in 28 fractions to the primary tumor and the elective lymph nodes as well as a simultaneous integrated boost (SIB) with 58.8 Gy to macroscopic tumor and lymph node metastases. Endpoints were overall survival (OS), progression free survival (PFS), local control rate (LCR) and toxicity.Results60 patients (59.4%) received chemoradiation, 41 patients (40.6%) radiotherapy alone. The median follow up was 17 months (range 0-75 months). OS, PFS and LCR were at 63.9%, 53.9% and 59.9% after 1 year and 37.6%, 34.5% and 36.1%, respectively after 3 years. 16 patients (15.8%) in total developed a locoregional recurrence within the field of radiation. In 48 patients (47.5%) at least one grade III° (CTCAE) toxicity was documented during radiotherapy, mostly dysphagia (36 pat., 75%). One patient suffered from a grade IV° pneumonia.ConclusionThis retrospective analysis demonstrates that a SIB concept in definitive (chemo)radiation therapy is safe and feasible, showing acceptable outcomes in this patient cohort. Considering that this cohort mainly consists of elderly patients not eligible for chemotherapy in many cases, we emphasize the aspect of SIB radiation therapy as potential partial compensation for omitted simultaneous chemotherapy. Prospective studies are needed for validation.