Holmes, Jason

AbstractBackgroundAccurate and efficient dose calculation is essential for on‐line adaptive planning in proton therapy. Deep learning (DL) has shown promising dose prediction results in photon therapy. However, there is a scarcity of DL‐based dose prediction methods specifically designed for proton therapy. Successful dose prediction method for proton therapy should account for more challenging dose prediction problems in pencil beam scanning proton therapy (PBSPT) due to its sensitivity to heterogeneities.PurposeTo develop a DL‐based PBSPT dose prediction workflow with high accuracy and balanced complexity to support on‐line adaptive proton therapy clinical decision and subsequent replanning.MethodsPBSPT plans of 103 prostate cancer patients (93 for training and the other 10 for independent testing) and 83 lung cancer patients (73 for training and the other 10 for independent testing) previously treated at our institution were included in the study, each with computed tomography scans (CTs), structure sets, and plan doses calculated by the in‐house developed Monte‐Carlo dose engine (considered as the ground truth in the model training and testing). For the ablation study, we designed three experiments corresponding to the following three methods: (1) Experiment 1, the conventional region of interest (ROI) (composed of targets and organs‐at‐risk [OARs]) method. (2) Experiment 2, the beam mask (generated by raytracing of proton beams) method to improve proton dose prediction. (3) Experiment 3, the sliding window method for the model to focus on local details to further improve proton dose prediction. A fully connected 3D‐Unet was adopted as the backbone. Dose volume histogram (DVH) indices, 3D Gamma passing rates with a criterion of 3%/3 mm/10%, and dice coefficients for the structures enclosed by the iso‐dose lines between the predicted and the ground truth doses were used as the evaluation metrics. The calculation time for each proton dose prediction was recorded to evaluate the method's efficiency.ResultsCompared to the conventional ROI method, the beam mask method improved the agreement of DVH indices for both targets and OARs and the sliding window method further improved the agreement of the DVH indices (for lung cancer, CTV D98 absolute deviation: 0.74 ± 0.18 vs. 0.57 ± 0.21 vs. 0.54 ± 0.15 Gy[RBE], ROI vs. beam mask vs. sliding window methods, respectively). For the 3D Gamma passing rates in the target, OARs, and BODY (outside target and OARs), the beam mask method improved the passing rates in these regions and the sliding window method further improved them (for prostate cancer, targets: 96.93% ± 0.53% vs. 98.88% ± 0.49% vs. 99.97% ± 0.07%, BODY: 86.88% ± 0.74% vs. 93.21% ± 0.56% vs. 95.17% ± 0.59%). A similar trend was also observed for the dice coefficients. This trend was especially remarkable for relatively low prescription isodose lines (for lung cancer, 10% isodose line dice: 0.871 ± 0.027 vs. 0.911 ± 0.023 vs. 0.927 ± 0.017). The dose predictions for all the testing cases were completed within 0.25 s.ConclusionsAn accurate and efficient deep learning‐augmented proton dose prediction framework has been developed for PBSPT, which can predict accurate dose distributions not only inside but also outside ROI efficiently. The framework can potentially further reduce the initial planning and adaptive replanning workload in PBSPT.

AbstractBackgroundDeformable Image Registration (DIR) is an essential technique required in many applications of radiation oncology. However, conventional DIR approaches typically take several minutes to register one pair of 3D CT images and the resulting deformable vector fields (DVFs) are only specific to the pair of images used, making it less appealing for clinical application.PurposeA deep‐learning‐based DIR method using CT images is proposed for lung cancer patients to address the common drawbacks of the conventional DIR approaches and in turn can accelerate the speed of related applications, such as contour propagation, dose deformation, adaptive radiotherapy (ART), etc.MethodsA deep neural network based on VoxelMorph was developed to generate DVFs using CT images collected from 114 lung cancer patients. Two models were trained with the weighted mean absolute error (wMAE) loss and structural similarity index matrix (SSIM) loss (optional) (i.e., the MAE model and the M+S model). In total, 192 pairs of initial CT (iCT) and verification CT (vCT) were included as a training dataset and the other independent 10 pairs of CTs were included as a testing dataset. The vCTs usually were taken 2 weeks after the iCTs. The synthetic CTs (sCTs) were generated by warping the vCTs according to the DVFs generated by the pre‐trained model. The image quality of the synthetic CTs was evaluated by measuring the similarity between the iCTs and the sCTs generated by the proposed methods and the conventional DIR approaches, respectively. Per‐voxel absolute CT‐number‐difference volume histogram (CDVH) and MAE were used as the evaluation metrics. The time to generate the sCTs was also recorded and compared quantitatively. Contours were propagated using the derived DVFs and evaluated with SSIM. Forward dose calculations were done on the sCTs and the corresponding iCTs. Dose volume histograms (DVHs) were generated based on dose distributions on both iCTs and sCTs generated by two models, respectively. The clinically relevant DVH indices were derived for comparison. The resulted dose distributions were also compared using 3D Gamma analysis with thresholds of 3 mm/3%/10% and 2 mm/2%/10%, respectively.ResultsThe two models (wMAE and M+S) achieved a speed of 263.7±163 / 265.8±190 ms and a MAE of 13.15±3.8 / 17.52±5.8 HU for the testing dataset, respectively. The average SSIM scores of 0.987±0.006 and 0.988±0.004 were achieved by the two proposed models, respectively. For both models, CDVH of a typical patient showed that less than 5% of the voxels had a per‐voxel absolute CT‐number‐difference larger than 55 HU. The dose distribution calculated based on a typical sCT showed differences of ≤2cGy[RBE] for clinical target volume (CTV) D95 and D5, within ±0.06% for total lung V5, ≤1.5cGy[RBE] for heart and esophagus Dmean, and ≤6cGy[RBE] for cord Dmax compared to the dose distribution calculated based on the iCT. The good average 3D Gamma passing rates (> 96% for 3 mm/3%/10% and > 94% for 2 mm/2%/10%, respectively) were also observed.ConclusionA deep neural network‐based DIR approach was proposed and has been shown to be reasonably accurate and efficient to register the initial CTs and verification CTs in lung cancer.

Abstract Purpose To evaluate the accuracy of the RayStation Monte Carlo dose engine (RayStation MC) in modeling small‐field block apertures in proton pencil beam scanning. Furthermore, we evaluate the suitability of MCsquare as a second check for RayStation MC. Methods We have enhanced MCsquare to model block apertures. To test the accuracy of both RayStation MC and the newly enhanced MCsquare, we compare the dose predictions of each to in‐water dose measurements obtained using diode detectors and radiochromic film. Nine brass apertures with openings of 1, 2, 3, 4, and 5 cm and either 2 cm or 4 cm thickness were used in the irradiation of a water phantom. Two measurement setups were used, one with a range shifter and 119.7 MeV proton beam energy and the other with no range shifter and 147 MeV proton beam energy. To further test the validity of RayStation MC and MCsquare in modeling block apertures and to evaluate MCsquare as a second check tool, 10 small‐field (average target volume 8.3 cm 3 ) patient treatment plans were calculated by each dose engine followed by a statistical comparison. Results Comparing to the absolute dose measurements in water, RayStation MC differed by 1.2% ± 1.0% while MCsquare differed by −1.8% ± 3.7% in the plateau region of a pristine Bragg peak. Compared to the in‐water film measurements, RayStation MC and MCsquare both performed well with an average 2D‐3D gamma passing rate of 99.4% and 99.7% (3%/3 mm), respectively. A t ‐test comparing the agreement with the film measurements between RayStation MC and MCsquare suggested that the relative spatial dose distributions calculated by MCsquare and RayStation MC were statistically indistinguishable. Directly comparing the dose calculations between MCsquare and RayStation MC over 10 patients resulted in an average 3D‐3D gamma passing rates of 98.5% (3%/3 mm) and 94.1% (2%/2 mm), respectively. Conclusion The validity of RayStation MC algorithm for use with patient‐specific apertures has been expanded to include small apertures. MCsquare has been enhanced to model apertures and was found to be an adequate second check of RayStation MC in this scenario.

Particle detection instrumentation to address the in vivo verifications of proton dose and range is under development as part of a proton therapy research program focused on patient quality assurance. For in vivo proton range verification, a collimated gamma detector array is under construction to indirectly measure the position of the Bragg peak for each proton beam spot to within 1–2 mm precision. For dose flux verification, a proton fluence detector based on the technology of the Micromegas is under construction. This detector has an active area of about 100 cm2, coordinate resolution of better than 1 mm, and handling of incident proton beam fluxes of 109–1013 particles/s.