Wong, William W.

Abstract Background Accurate and efficient dose calculation is essential for online adaptive planning in proton therapy. Deep learning (DL) has shown promising dose prediction results for pencil beam scanning proton therapy (PBSPT) in recent years, but existing DL‐based dose prediction methods still suffer from limited generalizability and an inability to effectively handle outlier clinical cases. This may lead to inaccurate dose delivery to targets or excessive irradiation to organs at risk (OARs), thereby compromising the safety and efficacy of online adaptive proton therapy. Purpose To design a physics‐aware and generalizable AI‐based PBSPT dose prediction method that incorporates underlying physics to enhance generalizability, particularly in handling outlier clinical cases. Methods This study analyzed PBSPT plans of 103 prostate (93 for training and 10 for testing) and 78 lung cancer patients (68 for training and 10 for testing) from our institution, with each case comprising CT images and structure sets. Using the doses generated by our Monte Carlo‐based dose engine as the reference standard, we compared three methods: the region of interest (ROI)‐based method, the beam mask and sliding window method, and the proposed noisy probing dose method, which rapidly generates a low‐statistics dose via uniformly weighted spots on an expanded spot‐placement target volume without optimization. To evaluate the generalizability of these methods to rare treatment planning scenarios, 12 cases with uncommon beam angles or prescription doses were used to assess their performance, which was evaluated using dose‐volume histogram (DVH) indices, 3D Gamma passing rates (3%/2 mm/10%), and Dice coefficients for dose agreement, while prediction times were measured to gauge model efficiency. Results The proposed noisy probing dose method consistently outperformed the ROI‐based and beam mask baselines across all evaluated metrics, with more accurate dose agreement and superior generalizability. For DVH indices, the noisy probing dose method achieved the smallest deviation in clinical target volume (CTV) dose coverage: in prostate cancer, CTV D98 deviation was reduced by 45% (from 0.53 ± 0.22 Gy [RBE] for ROI‐based) and 29% (from 0.41 ± 0.28 Gy [RBE] for beam mask) to 0.29 ± 0.06 Gy [RBE]; in lung cancer, similar improvements were observed, with CTV D98 deviations reduced to 0.34 ± 0.12 Gy [RBE]. The 3D Gamma passing rates improved to 99.65% ± 1.15% for prostate targets and 97.04% ± 1.17% for lung targets. The dice coefficients of the 90% iso‐dose lines were also the highest with the noisy probing dose method (prostate: 0.983 ± 0.005; lung: 0.967 ± 0.01). For the 12 outlier cases, the noisy probing dose method maintained superior generalizability, yielding higher 3D Gamma passing rates (prostate targets: 96.79% ± 0.83%, OARs: 94.29% ± 1.01%; lung targets: 93.38% ± 1.34%, OARs: 93.95% ± 1.32%), demonstrating robust generalizability to rare clinical scenarios. The dose predictions for all testing cases were completed within 0.3 seconds. Conclusions A novel noisy probing dose method was proposed for PBSPT dose prediction in prostate and lung cancer patients. By embedding more proton‐specific physics, this method demonstrated an improvement in the generalizability of dose prediction.

Abstract In radiotherapy, 2D orthogonally projected kV images are used for patient alignment when 3D-on-board imaging(OBI) unavailable. But tumor visibility is constrained due to the projection of patient’s anatomy onto a 2D plane, potentially leading to substantial setup errors. In treatment room with 3D-OBI such as cone beam CT(CBCT), the field of view(FOV) of CBCT is limited with unnecessarily high imaging dose, thus unfavorable for pediatric patients. A solution to this dilemma is to reconstruct 3D CT from kV images obtained at the treatment position. Here, we propose a dual-models framework built with hierarchical ViT blocks. Unlike a proof-of-concept approach, our framework considers kV images as the solo input and can synthesize accurate, full-size 3D CT in real time(within milliseconds). We demonstrate the feasibility of the proposed approach on 10 patients with head and neck(H\&N) cancer using image quality(MAE:<45HU), dosimetric accuracy(Gamma passing rate(2%/2mm/10%):>97%) and patient position uncertainty(shift error:<0.4mm). The proposed framework can generate accurate 3D CT faithfully mirroring real-time patient position, thus significantly improving patient setup accuracy, keeping imaging dose minimum, and maintaining treatment veracity.

Abstract Background Efficient and accurate delineation of organs at risk (OARs) is a critical procedure for treatment planning and dose evaluation. Deep learning‐based auto‐segmentation of OARs has shown promising results and is increasingly being used in radiation therapy. However, existing deep learning‐based auto‐segmentation approaches face two challenges in clinical practice: generalizability and human‐AI interaction. A generalizable and promptable auto‐segmentation model, which segments OARs of multiple disease sites simultaneously and supports on‐the‐fly human‐AI interaction, can significantly enhance the efficiency of radiation therapy treatment planning. Purpose Meta's segment anything model (SAM) was proposed as a generalizable and promptable model for next‐generation natural image segmentation. We further evaluated the performance of SAM in radiotherapy segmentation. Methods Computed tomography (CT) images of clinical cases from four disease sites at our institute were collected: prostate, lung, gastrointestinal, and head & neck. For each case, we selected the OARs important in radiotherapy treatment planning. We then compared both the Dice coefficients and Jaccard indices derived from three distinct methods: manual delineation (ground truth), automatic segmentation using SAM's ’segment anything’ mode, and automatic segmentation using SAM's ‘box prompt’ mode that implements manual interaction via live prompts during segmentation. Results Our results indicate that SAM's segment anything mode can achieve clinically acceptable segmentation results in most OARs with Dice scores higher than 0.7. SAM's box prompt mode further improves Dice scores by 0.1∼0.5. Similar results were observed for Jaccard indices. The results show that SAM performs better for prostate and lung, but worse for gastrointestinal and head & neck. When considering the size of organs and the distinctiveness of their boundaries, SAM shows better performance for large organs with distinct boundaries, such as lung and liver, and worse for smaller organs with less distinct boundaries, like parotid and cochlea. Conclusions Our results demonstrate SAM's robust generalizability with consistent accuracy in automatic segmentation for radiotherapy. Furthermore, the advanced box‐prompt method enables the users to augment auto‐segmentation interactively and dynamically, leading to patient‐specific auto‐segmentation in radiation therapy. SAM's generalizability across different disease sites and different modalities makes it feasible to develop a generic auto‐segmentation model in radiotherapy.

Abstract Purpose . To enhance an in-house graphic-processing-unit accelerated virtual particle (VP)-based Monte Carlo (MC) proton dose engine (VPMC) to model aperture blocks in both dose calculation and optimization for pencil beam scanning proton therapy (PBSPT)-based stereotactic radiosurgery (SRS). Methods and materials . A module to simulate VPs passing through patient-specific aperture blocks was developed and integrated in VPMC based on simulation results of realistic particles (primary protons and their secondaries). To validate the aperture block module, VPMC was first validated by an opensource MC code, MCsquare, in eight water phantom simulations with 3 cm thick brass apertures: four were with aperture openings of 1, 2, 3, and 4 cm without a range shifter, while the other four were with same aperture opening configurations with a range shifter of 45 mm water equivalent thickness. Then, VPMC was benchmarked with MCsquare and RayStation MC for 10 patients with small targets (average volume 8.4 c.c. with range of 0.4–43.3 c.c.). Finally, 3 typical patients were selected for robust optimization with aperture blocks using VPMC. Results . In the water phantoms, 3D gamma passing rate (2%/2 mm/10%) between VPMC and MCsquare was 99.71 ± 0.23%. In the patient geometries, 3D gamma passing rates (3%/2 mm/10%) between VPMC/MCsquare and RayStation MC were 97.79 ± 2.21%/97.78 ± 1.97%, respectively. Meanwhile, the calculation time was drastically decreased from 112.45 ± 114.08 s (MCsquare) to 8.20 ± 6.42 s (VPMC) with the same statistical uncertainties of ~0.5%. The robustly optimized plans met all the dose–volume-constraints (DVCs) for the targets and OARs per our institutional protocols. The mean calculation time for 13 influence matrices in robust optimization by VPMC was 41.6 s and the subsequent on-the-fly ‘trial-and-error’ optimization procedure took only 71.4 s on average for the selected three patients. Conclusion . VPMC has been successfully enhanced to model aperture blocks in dose calculation and optimization for the PBSPT-based SRS.

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.

AbstractBackgroundDeep learning auto‐segmentation (DLAS) models have been adopted in the clinic; however, they suffer from performance deterioration owing to the clinical practice variability. Some commercial DLAS software provide an incremental retraining function that enables users to train a custom model using their institutional data to account for clinical practice variability.PurposeThis study was performed to evaluate and implement the commercial DLAS software with the incremental retraining function for definitive treatment of patients with prostate cancer in a multi‐user environment.MethodsCT‐based target organs and organs‐at‐risk (OAR) delineation of 215 prostate cancer patients were utilized. The performance of three commercial DLAS software built‐in models was validated with 20 patients. A retrained custom model was developed using 100 patients and evaluated on the remaining data (n = 115). Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), and surface DSC (SDSC) were utilized for quantitative evaluation. A multi‐rater qualitative evaluation was blindly performed with a five‐level scale. Visual inspection was performed in consensus and non‐consensus unacceptable cases to identify the failure modes.ResultsThree commercial DLAS vendor built‐in models achieved sub‐optimal performance in 20 patients. The retrained custom model had a mean DSC of 0.82 for prostate, 0.48 for seminal vesicles (SV), and 0.92 for rectum, respectively. This represents a significant improvement over the built‐in model with DSC of 0.73, 0.37, and 0.81 for the corresponding structures. Compared to the acceptance rate of 96.5% and consensus unacceptable rate (i.e., both reviewers rated as unacceptable) of 3.5% achieved by manual contours, the custom model achieved a 91.3% acceptance rate and 8.7% consensus unacceptable rate. The failure modes of retrained custom model were attributed to the following: cystogram (n = 2), hip prosthesis (n = 2), low dose rate brachytherapy seeds (n = 2), air in endorectal balloon(n = 1), non‐iodinated spacer (n = 2), and giant bladder(n = 1).ConclusionThe commercial DLAS software with the incremental retraining function was validated and clinically adopted for prostate patients in a multi‐user environment. AI‐based auto‐delineation of the prostate and OARs is shown to achieve improved physician acceptance, overall clinical utility, and accuracy.

AbstractBackgroundMechanical accuracy should be verified before implementing a proton stereotactic radiosurgery (SRS) program. Linear accelerator (Linac)‐based SRS systems often use electronic portal imaging devices (EPIDs) to verify beam isocentricity. Because proton therapy systems do not have EPID, beam isocentricity tests of proton SRS may still rely on films, which are not efficient.PurposeTo validate that our proton SRS system meets mechanical precision requirements and to present an efficient method to evaluate the couch and gantry's rotational isocentricity for our proton SRS system.MethodsA dedicated applicator to hold brass aperture for proton SRS system was designed. The mechanical precision of the system was tested using a metal ball and film for 11 combinations of gantry and couch angles. A more efficient quality assurance (QA) procedure was developed, which used a scintillator device to replace the film. The couch rotational isocentricity tests were performed using orthogonal kV x‐rays with the couch rotated isocentrically to five positions (0°, 315°, 270°, 225°, and 180°). At each couch position, the distance between the metal ball in kV images and the imaging isocenter was measured. The gantry isocentricity tests were performed using a cone‐shaped scintillator and proton beams at five gantry angles (0°, 45°, 90°, 135°, and 180°), and the isocenter position and the distance of each beam path to the isocenter were obtained. Daily QA procedure was performed for 1 month to test the robustness and reproducibility of the procedure.ResultsThe gantry and couch rotational isocentricity exhibited sub‐mm precision, with most measurements within ±0.5 mm. The 1‐month QA results showed that the procedure was robust and highly reproducible to within ±0.2 mm. The gantry isocentricity test using the cone‐shaped scintillator was accurate and sensitive to variations of ±0.2 mm. The QA procedure was efficient enough to be completed within 30 min. The 1‐month isocentricity position variations were within 0.5 mm, which demonstrating that the overall proton SRS system was stable and precise.ConclusionThe proton SRS Winston–Lutz QA procedure using a cone‐shaped scintillator was efficient and robust. We were able to verify radiation delivery could be performed with sub‐mm mechanical precision.

Purpose: Planning target volume (PTV) expansion for post-prostatectomy radiotherapy is typically ≥5 mm. Recent clinical trials have proved the feasibility of a reduced margin of 2–3 mm for treatments on MRI-linac. We aim to study the minimum PTV margin needed using iterative cone-beam CT (iCBCT) as image guidance on conventional linacs. Materials/Methods: Fourteen patients who received post-prostatectomy irradiation (8 with an endorectal balloon and 6 without a balloon) were included in this study. Treatment was delivered with volumetric modulated radiation therapy (VMAT). Fractional dose delivery was evaluated in 165 treatment fractions. The bladder, rectal wall, femoral heads, and prostate bed clinical tumor volume (CTV) were contoured and verified on daily iCBCT. PTV margins (0 mm, 2 mm, and 4 mm) were evaluated on daily iCBCT. CTV coverage and OAR dose parameters were assessed with each PTV margin. Results: CTV D100% was underdosed with a 0 mm margin in 32% of fractions in comparison with 2 mm (6%) and 4 mm (6%) PTV margin (p ≤ 0.001). CTV D95% > 95% was met in 93–94% fractions for all PTV expansions. CTV D95% > 95% was achieved in more patients with an endorectal balloon than those without: 0 mm—90/91 (99%) vs. 63/74 (85%); 2 mm—90/91 (99%) vs. 65/75 (87%); 4 mm—90/90 (100%) vs. 63/73 (86%). There was no difference in absolute median change in CTV D95% (0.32%) for 0-, 2-, and 4 mm margins. The maximum dose remained under 108% for 100% (0 mm), 97% (2 mm), and 98% (4 mm) of images. Rectal wall maximum dose remained under 108% for 100% (0 mm), 100% (2 mm), and 98% (4 mm) of images. Conclusions: With high-quality iCBCT image guidance, PTV margin accounting for inter-fractional uncertainties can be safely reduced for post-prostatectomy radiotherapy. For fractionated radiotherapy, an isotropic expansion of 2 mm and 4 mm may be considered for margin expansion with and without the endorectal balloon. Future application for margin reduction needs to be further evaluated and considered with the advent of shorter post-prostatectomy radiation courses.