Dose de-intensified 3-day photon, proton, or brachytherapy: a nonrandomized controlled partial breast irradiation trial.

BACKGROUND: The optimal approach for partial breast irradiation (PBI) is unknown. We investigated a novel de-intensified 3-fraction PBI regimen for photons, protons, and brachytherapy. METHODS: A multicenter nonrandomized controlled trial with primary outcome of adverse cosmesis at 3 years versus pre-PBI. Eligibility criteria were ≥ age 50 years treated with breast-conserving surgery for node-negative estrogen receptor positive (ER+) invasive breast cancer or any ductal carcinoma in-situ (DCIS) measuring ≤ 2.5 cm. Photon and proton PBI were prescribed 21.9 Gy (RBE) and brachytherapy 21 Gy in 3 fractions. Radiotherapy technique and use of adjuvant endocrine therapy was selected at physician and patient discretion. RESULTS: Between June 17, 2015 and July 13, 2017, 161 eligible patients were treated with photons (56), protons (49), or brachytherapy (56). Median patient age was 66.8 years. 126 (78.3%) had invasive breast cancer (all ER+) and 35 (21.7%) had DCIS (88.6% ER+). 54.0% of patients with invasive breast cancer and 25.8% of patients with ER+ DCIS initiated and adhered to prescribed endocrine therapy. The proportion of patients with adverse cosmesis (by trained nurse assessment) was 14.5% at baseline, 2.3% at 3 years (difference -12.2%, 95% CI (-100%, -6.4%)). Adverse cosmesis at last-follow-up, with median follow-up 5 years, was 5.7% by nurse assessment, 5.6% by panel assessment of digital photographs, and 5.2% by patient self-report. There were no observed clinically meaningful changes in other patient reported outcomes, and just two grade 2 or higher adverse events, both grade 2, in the brachytherapy cohort. 5-year local recurrence-free and progression-free survival were 98.0% and 95.5%, respectively. There were no local recurrences amongst 60 patients with invasive breast cancer and Ki67 ≤ 13.25%. CONCLUSIONS: De-intensified 3-day PBI provided favorable disease control, tolerability, and cosmetic outcomes, meeting the pre-specified criteria for acceptability. This approach is an attractive option for small node-negative ER+ BC and DCIS patients. TRIAL REGISTRATION: ClinicalTrials.gov identifier NCT02453737.

Online Adaptive Proton Therapy Facilitated by Artificial Intelligence-based Auto Segmentation in Pencil Beam Scanning Proton Therapy: Prostate oAPT in PBSPT.

PURPOSE: Online adaptive proton therapy (oAPT) is essential to address interfractional anatomical changes in patients receiving pencil beam scanning proton therapy (PBSPT). Artificial intelligence (AI)-based auto-segmentation can increase the efficiency and accuracy. Linear energy transfer (LET)-based biological effect evaluation can potentially mitigate possible adverse events caused by high LET. New spot arrangement based on the verification CT (vCT) can further improve the re-plan quality. We propose an oAPT workflow that incorporates all these functionalities and validate its clinical implementation feasibility with prostate patients. METHODS AND MATERIALS: AI-based auto-segmentation tool AccuContourTM (Manteia, Xiamen, China) was seamlessly integrated into oAPT. Initial spot arrangement tool on the vCT for re-optimization was implemented using raytracing. An LET-based biological effect evaluation tool was developed to assess the overlap region of high dose and high LET in selected OARs. Eleven prostate cancer patients were retrospectively selected to verify the efficacy and efficiency of the proposed oAPT workflow. The time cost of each component in the workflow was recorded for analysis. RESULTS: The verification plan showed significant degradation of the CTV coverage and rectum and bladder sparing due to the interfractional anatomical changes. Re-optimization on the vCT resulted in great improvement of the plan quality. No overlap regions of high dose and high LET distributions were observed in bladder or rectum in re-plans. 3D Gamma analyses in PSQA confirmed the accuracy of the re-plan doses before delivery (Gamma passing rate = 99.57 ± 0.46%), and after delivery (98.59 ± 1.29%). The robustness of the re-plans passed all clinical requirements. The average time for the complete execution of the workflow was 9.12 ± 0.85 minutes, excluding manual intervention time. CONCLUSION: The AI-facilitated oAPT workflow was demonstrated to be both efficient and effective by generating a re-plan that significantly improved the plan quality in prostate cancer treated with PBSPT.

Enhancing Activity and Stability of Pd-on-TiO2 Single-Atom Catalyst for Low-Temperature CO Oxidation through in Situ Local Environment Tailoring.

The development of efficient Pd single-atom catalysts for CO oxidation, crucial for environmental protection and fundamental studies, has been hindered by their limited reactivity and thermal stability. Here, we report a thermally stable TiO2-supported Pd single-atom catalyst that exhibits enhanced intrinsic CO oxidation activity by tunning the local coordination of Pd atoms via H2 treatment. Our comprehensive characterization reveals that H2-treated Pd single atoms have reduced nearest Pd-O coordination and form short-distanced Pd-Ti coordination, effectively stabilizing Pd as isolated atoms even at high temperatures. During CO oxidation, partial replacement of the Pd-Ti coordination by O or CO occurs. This unique Pd local environment facilitates CO adsorption and promotes the activity of the surrounding oxygen species, leading to superior catalytic performance. Remarkably, the turnover frequency of the H2-treated Pd single-atom catalyst at 120 °C surpasses that of the O2-treated Pd single-atom catalyst and the most effective Pd/Pt single-atom catalysts by an order of magnitude. These findings open up new possibilities for the design of high-performance single-atom catalysts for crucial industrial and environmental applications.

Stereotactic Body Proton Therapy Versus Conventionally Fractionated Proton Therapy for Early Prostate Cancer: A Randomized, Controlled, Phase 3 Trial.

PURPOSE: We aimed to determine if ultrahypofractionated proton therapy delivered via stereotactic body proton therapy (SBPT) is noninferior to conventionally fractionated proton therapy (CFPT) in patients with early prostate cancer. METHODS AND MATERIALS: This study was a multicenter, randomized, controlled, noninferiority phase 3 trial that included patients with histologically confirmed low-risk prostate adenocarcinoma defined by Gleason score grouping 1, Prostate-specific antigen <10 ng/mL, and clinical stage T1-T2a N0 M0 according to 7th edition of the American Joint Committee on Cancer tumor-node-metastasis cancer staging system. Eligible participants were randomly assigned initially at a 1:1 ratio and later at a 2:1 ratio to SBPT (38 Gy in 5 fractions) or CFPT (79.2 Gy in 44 fractions). The primary endpoint was freedom from failure (FFF) at 2 years from the date of randomization. Noninferiority for FFF was determined based on 1-sided confidence intervals. Toxicities were compared at different time points using Fisher's exact test. Health-related quality-of-life (HRQoL) was analyzed at different time points using a mixed-effects linear model. This trial is registered with ClinicalTrials.gov, NCT01230866, and is closed to accrual. RESULTS: Between December 10, 2010, and September 29, 2020, 144 patients were enrolled and 135 were randomly assigned (90 to the SBPT group and 45 to the CFPT group). The median follow-up was 5 years (IQR, 3.9-5.2). The 2-year FFF was 100% for both groups, with the 1-sided 5-year risk difference in FFF between groups reported as 2.63% (90% CI, -1.70% to 6.96%), favoring the SBRT arm, thus fulfilling the prespecified criteria for noninferiority of SBPT compared with CFPT. Rates of gastrointestinal and genitourinary G2 and G3 toxicities did not differ significantly between groups. Further, HRQoL metrics did not differ significantly between groups over the study's median follow-up. CONCLUSIONS: SBPT is noninferior to CFPT regarding FFF, with similar long-term genitourinary and gastrointestinal toxicity rates and minimal impact in patient-reported HRQoL over time.

Evaluation of knowledge-based planning models for male pelvic CBCT-based online adaptive radiotherapy on conventional linear accelerators.

PURPOSE: To assess the practicality of employing a commercial knowledge-based planning tool (RapidPlan) to generate adapted intact prostate and prostate bed volumetric modulated arc therapy (VMAT) plans on iterative cone-beam computed tomography (iCBCT) datasets. METHODS AND MATERIALS: Intact prostate and prostate bed RapidPlan models were trained utilizing planning data from 50 and 44 clinical cases, respectively. To ensure that refined models were capable of producing adequate clinical plans with a single optimization, models were tested with 50 clinical planning CT datasets by comparing dose-volume histogram (DVH) and plan quality metric (PQM) values between clinical and RapidPlan-generated plans. The RapidPlan tool was then used to retrospectively generate adapted VMAT plans on daily iCBCT images for 20 intact prostate and 15 prostate bed cases. As before, DVH and PQM metrics were utilized to dosimetrically compare scheduled (iCBCT Verify) and adapted (iCBCT RapidPlan) plans. Timing data was collected to further evaluate the feasibility of integrating this approach within an online adaptive radiotherapy workflow. RESULTS: Model testing results confirmed the models were capable of producing VMAT plans within a single optimization that were overall improved upon or dosimetrically comparable to original clinical plans. Direct application of RapidPlan on iCBCT datasets produced satisfactory intact prostate and prostate bed plans with generally improved target volume coverage/conformality and rectal sparing relative to iCBCT Verify plans as indicated by DVH values, though bladder metrics were marginally increased on average. Average PQM values for iCBCT RapidPlans were significantly improved compared to iCBCT Verify plans. The average time required [in mm:ss] to generate adapted plans was 06:09 ± 02:06 (intact) and 07:12 ± 01:04 (bed). CONCLUSION: This study demonstrated the feasibility of leveraging RapidPlan to expeditiously generate adapted VMAT intact prostate and prostate bed plans on iCBCT datasets. In general, adapted plans were dosimetrically improved relative to scheduled plans, emphasizing the practicality of the proposed approach.

The Status and Challenges for Prostate Stereotactic Body Radiation Therapy Treatments in United States Proton Therapy Centers: An NRG Oncology Practice Survey.

Purpose: To report the current practice pattern of the proton stereotactic body radiation therapy (SBRT) for prostate treatments. Materials and Methods: A survey was designed to inquire about the practice of proton SBRT treatment for prostate cancer. The survey was distributed to all 30 proton therapy centers in the United States that participate in the National Clinical Trial Network in February, 2023. The survey focused on usage, patient selection criteria, prescriptions, target contours, dose constraints, treatment plan optimization and evaluation methods, patient-specific QA, and image-guided radiation therapy (IGRT) methods. Results: We received responses from 25 centers (83% participation). Only 8 respondent proton centers (32%) reported performing SBRT of the prostate. The remaining 17 centers cited 3 primary reasons for not offering this treatment: no clinical need, lack of volumetric imaging, and/or lack of clinical evidence. Only 1 center cited the reduction in overall reimbursement as a concern for not offering prostate SBRT. Several common practices among the 8 centers offering SBRT for the prostate were noted, such as using Hydrogel spacers, fiducial markers, and magnetic resonance imaging (MRI) for target delineation. Most proton centers (87.5%) utilized pencil beam scanning (PBS) delivery and completed Imaging and Radiation Oncology Core (IROC) phantom credentialing. Treatment planning typically used parallel opposed lateral beams, and consistent parameters for setup and range uncertainties were used for plan optimization and robustness evaluation. Measurements-based patient-specific QA, beam delivery every other day, fiducial contours for IGRT, and total doses of 35 to 40 GyRBE were consistent across all centers. However, there was no consensus on the risk levels for patient selection. Conclusion: Prostate SBRT is used in about 1/3 of proton centers in the US. There was a significant consistency in practices among proton centers treating with proton SBRT. It is possible that the adoption of proton SBRT may become more common if proton SBRT is more commonly offered in clinical trials.

The status and challenges for prostate SBRT treatments in United States proton therapy centers: An NRG Oncology practice survey.

A survey was designed to inquire about the practice of proton SBRT treatment for prostate cancer. The survey was distributed to all 30 proton therapy centers in the United States that participate in the National Clinical Trial Network in Feb. 2023. The survey focused on usage, patient selection criteria, prescriptions, target contours, dose constraints, treatment plan optimization and evaluation methods, patient-specific QA, and IGRT methods. Results: We received responses from 25 centers (83% participation). Only 8 respondent proton centers (32%) reported performing SBRT of the prostate. The remaining 17 centers cited three primary reasons for not offering this treatment: no clinical need, lack of volumetric imaging, and/or lack of clinical evidence. Only 1 center cited the reduction in overall reimbursement as a concern for not offering prostate SBRT. Several common practices among the 8 centers offering SBRT for the prostate were noted, such as using Hydrogel spacers, fiducial markers, and MRI for target delineation. Most proton centers (87.5%) utilized pencil beam scanning (PBS) delivery and completed Imaging and Radiation Oncology Core (IROC) phantom credentialing. Treatment planning typically used parallel opposed lateral beams, and consistent parameters for setup and range uncertainties were used for plan optimization and robustness evaluation. Measurements-based patient-specific QA, beam delivery every other day, fiducial contours for IGRT, and total doses of 35-40 GyRBE were consistent across all centers. However, there was no consensus on the risk levels for patient selection. Conclusion: Prostate SBRT is used in about 1/3 of proton centers in the US. There was a significant consistency in practices among proton centers treating with proton SBRT. It is possible that the adoption of proton SBRT may become more common if proton SBRT is more commonly offered in clinical trials.

Beam mask and sliding window-facilitated deep learning-based accurate and efficient dose prediction for pencil beam scanning proton therapy.

BACKGROUND: Accurate 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. PURPOSE: To 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. METHODS: PBSPT 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. RESULTS: Compared 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. CONCLUSIONS: An 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.

Physician- and Patient-Reported Outcomes of the MC1635 Phase 3 Trial of Ultrahypofractionated Versus Moderately Hypofractionated Adjuvant Radiation Therapy After Breast-Conserving Surgery.

PURPOSE: Our aim was to report physician- and patient-reported outcomes of patients with localized breast cancer treated with moderate versus ultrahypofractionated whole breast irradiation (WBI) after breast-conserving surgery (BCS). METHODS AND MATERIALS: Between February 2018 and February 2020, patients with localized breast cancer (pT0-3 pN0-1 M0) were offered participation in a phase 3 randomized clinical trial assessing adjuvant moderate hypofractionation (MHF) to 40 Gy in 15 fractions versus ultrahypofractionation (UHF) to 25 Gy in 5 fractions after BCS, with an optional simultaneously integrated boost. Toxicities, cosmesis, and quality of life were assessed at baseline, end of treatment (EOT), and 3 months, 1 year, 2 years, and 3 years from irradiation using validated metric tools. RESULTS: One hundred seven patients were randomized to MHF (n = 54) or UHF (n = 53) adjuvant WBI. The median follow-up was 42.8 months. Grade 2 radiation dermatitis was experienced by 4 patients (7.4%) in the MHF arm and 2 patients (3.7%) in the UHF arm at EOT (P = .726). No grade 3 or higher toxicities were observed. Deterioration of cosmesis by physician assessment was observed in 2 (6.7%) patients treated in the UHF arm and 1 (1.9%) patient treated in the MHF arm at EOT (P = .534), whereas at 3 months, only 1 (1.8%) patient treated in the MHF arm demonstrated deterioration of cosmesis (P = .315). At EOT, 91% and 94% of patients reported excellent/good cosmesis among those treated with MHF and UHF regimens, respectively (P = .550). At 3 months, more patients within the MHF arm reported excellent/good cosmesis compared with those in the UHF arm (100% vs 91%; P = .030). However, the difference in patient-reported cosmesis disappeared at the 1-, 2-, and 3-year time points. CONCLUSIONS: UHF WBI showed similar treatment-related late toxicities and similar provider-scored cosmesis compared with MHF radiation in patients treated adjuvantly after BCS.

Predicting the Effect of Proton Beam Therapy Technology on Pulmonary Toxicities for Patients With Locally Advanced Lung Cancer Enrolled in the Proton Collaborative Group Prospective Clinical Trial.

PURPOSE: This study aimed to predict the probability of grade ≥2 pneumonitis or dyspnea within 12 months of receiving conventionally fractionated or mildly hypofractionated proton beam therapy for locally advanced lung cancer using machine learning. METHODS AND MATERIALS: Demographic and treatment characteristics were analyzed for 965 consecutive patients treated for lung cancer with conventionally fractionated or mildly hypofractionated (2.2-3 Gy/fraction) proton beam therapy across 12 institutions. Three machine learning models (gradient boosting, additive tree, and logistic regression with lasso regularization) were implemented to predict Common Terminology Criteria for Adverse Events version 4 grade ≥2 pulmonary toxicities using double 10-fold cross-validation for parameter hyper-tuning without leak of information. Balanced accuracy and area under the curve were calculated, and 95% confidence intervals were obtained using bootstrap sampling. RESULTS: The median age of the patients was 70 years (range, 20-97), and they had predominantly stage IIIA or IIIB disease. They received a median dose of 60 Gy in 2 Gy/fraction, and 46.4% received concurrent chemotherapy. In total, 250 (25.9%) had grade ≥2 pulmonary toxicity. The probability of pulmonary toxicity was 0.08 for patients treated with pencil beam scanning and 0.34 for those treated with other techniques (P = 8.97e-13). Use of abdominal compression and breath hold were highly significant predictors of less toxicity (P = 2.88e-08). Higher total radiation delivered dose (P = .0182) and higher average dose to the ipsilateral lung (P = .0035) increased the likelihood of pulmonary toxicities. The gradient boosting model performed the best of the models tested, and when demographic and dosimetric features were combined, the area under the curve and balanced accuracy were 0.75 ± 0.02 and 0.67 ± 0.02, respectively. After analyzing performance versus the number of data points used for training, we observed that accuracy was limited by the number of observations. CONCLUSIONS: In the largest analysis of prospectively enrolled patients with lung cancer assessing pulmonary toxicities from proton therapy to date, advanced machine learning methods revealed that pencil beam scanning, abdominal compression, and lower normal lung doses can lead to significantly lower probability of developing grade ≥2 pneumonitis or dyspnea.

Atrial Fibrillation: Rate Versus Rhythm Control.

Description Atrial fibrillation (AF) remains the most common arrhythmia worldwide and is expected to affect approximately 12 million individuals in the United States alone by 2030. Thromboembolic events remain a feared complication of AF and should be treated and risk-stratified utilizing the CHA2DS2-VASc scoring system. Other complications of AF span a wide spectrum from impaired quality of life (QoL) to an increase in all-cause mortality. Rate control strategies consist of controlling the ventricular rate and have been shown to be a safe and effective strategy for asymptomatic AF patients. In patients who are plagued with symptoms leading to impaired QoL or a decrease in exercise capacity, rhythm control with antiarrhythmic drugs or catheter ablation may be suitable options. Mortality benefits when comparing rate versus rhythm control remain equivocal when comparing multiple studies over the past decade.

Conventional versus hypofractionated postmastectomy proton radiotherapy in the USA (MC1631): a randomised phase 2 trial.

BACKGROUND: Proton therapy is under investigation in breast cancer as a strategy to reduce radiation exposure to the heart and lungs. So far, studies investigating proton postmastectomy radiotherapy (PMRT) have used conventional fractionation over 25-28 days, but whether hypofractionated proton PMRT is feasible is unclear. We aimed to compare conventional fractionation and hypofractionation in patients with indications for PMRT, including those with immediate breast reconstruction. METHODS: We did a randomised phase 2 trial (MC1631) at Mayo Clinic in Rochester (MN, USA) and Mayo Clinic in Arizona (Phoenix, AZ, USA) comparing conventional fractionated (50 Gy in 25 fractions of 2 Gy [relative biological effectiveness of 1·1]) and hypofractionated (40·05 Gy in 15 fractions of 2·67 Gy [relative biological effectiveness of 1·1]) proton PMRT. All patients were treated with pencil-beam scanning. Eligibility criteria included age 18 years or older, an Eastern Cooperative Oncology Group performance status of 0-2, and breast cancer resected by mastectomy with or without immediate reconstruction with indications for PMRT. Patients were randomly assigned (1:1) to either conventional fractionation or hypofractionation, with presence of immediate reconstruction (yes vs no) as a stratification factor, using a biased-coin minimisation algorithm. Any patient who received at least one fraction of protocol treatment was evaluable for the primary endpoint and safety analyses. The primary endpoint was 24-month complication rate from the date of first radiotherapy, defined as grade 3 or worse adverse events occurring from 90 days after last radiotherapy or unplanned surgical interventions in patients with immediate reconstruction. The inferiority of hypofractionation would not be ruled out if the upper bound of the one-sided 95% CI for the difference in 24-month complication rate between the two groups was greater than 10%. This trial is registered with ClinicalTrials.gov, NCT02783690, and is closed to accrual. FINDINGS: Between June 2, 2016, and Aug 23, 2018, 88 patients were randomly assigned (44 to each group), of whom 82 received protocol treatment (41 in the conventional fractionation group and 41 in the hypofractionation group; median age of 52 years [IQR 44-64], 79 [96%] patients were White, two [2%] were Black or African American, one [1%] was Asian, and 79 [96%] were not of Hispanic ethnicity). As of data cutoff (Jan 30, 2023), the median follow-up was 39·3 months (IQR 37·5-61·2). The median mean heart dose was 0·54 Gy (IQR 0·30-0·72) for the conventional fractionation group and 0·49 Gy (0·25-0·64) for the hypofractionation group. Within 24 months of first radiotherapy, 14 protocol-defined complications occurred in six (15%) patients in the conventional fractionation group and in eight (20%) patients in the hypofractionation group (absolute difference 4·9% [one-sided 95% CI 18·5], p=0·27). The complications in the conventionally fractionated group were contracture (five [12%] of 41 patients]) and fat necrosis (one [2%] patient) requiring surgical intervention. All eight protocol-defined complications in the hypofractionation group were due to infections, three of which were acute infections that required surgical intervention, and five were late infections, four of which required surgical intervention. All 14 complications were in patients with immediate expander or implant-based reconstruction. INTERPRETATION: After a median follow-up of 39·3 months, non-inferiority of the hypofractionation group could not be established. However, given similar tolerability, hypofractionated proton PMRT appears to be worthy of further study in patients with and without immediate reconstruction. FUNDING: The Department of Radiation Oncology, Mayo Clinic, Rochester, MN, the Department of Radiation Oncology, Mayo Clinic, Phoenix, AZ, USA, and the US National Cancer Institute.

Beam mask and sliding window-facilitated deep learning-based accurate and efficient dose prediction for pencil beam scanning proton therapy.

PURPOSE: To 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. METHODS: PBSPT plans of 103 prostate cancer patients and 83 lung cancer patients previously treated at our institution were included in the study, each with CTs, structure sets, and plan doses calculated by the in-house developed Monte-Carlo dose engine. For the ablation study, we designed three experiments corresponding to the following three methods: 1) Experiment 1, the conventional region of interest (ROI) 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, 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. RESULTS: Compared 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 the 3D Gamma passing rates in the target, OARs, and BODY (outside target and OARs), the beam mask method can improve the passing rates in these regions and the sliding window method further improved them. A similar trend was also observed for the dice coefficients. In fact, this trend was especially remarkable for relatively low prescription isodose lines. The dose predictions for all the testing cases were completed within 0.25s.

Incremental retraining, clinical implementation, and acceptance rate of deep learning auto-segmentation for male pelvis in a multiuser environment.

BACKGROUND: Deep 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. PURPOSE: This 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. METHODS: CT-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. RESULTS: Three 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). CONCLUSION: The 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.

First Report On Physician Assessment and Clinical Acceptability of Custom-Retrained Artificial Intelligence Models for Clinical Target Volume and Organs-at-Risk Auto-Delineation for Postprostatectomy Patients.

PURPOSE: To assess the clinical acceptability of a commercial deep-learning-based auto-segmentation (DLAS) prostate model that was retrained using institutional data for delineation of the clinical target volume (CTV) and organs-at-risk (OARs) for postprostatectomy patients, accounting for clinical and imaging protocol variations. METHODS AND MATERIALS: CTV and OARs of 109 prostate-bed patients were used to evaluate the performance of the vendor-trained model and custom retrained DLAS models using different training quantities. Two new models for OAR structures were retrained (n = 30, 60 data sets), while separate models were trained for a new CTV structure (n = 30, 60, 90 data sets), with the remaining data sets used for testing (n = 49, 19). The dice similarity coefficient (DSC), Hausdorff distance, and mean surface distance were evaluated. Six radiation oncologists performed a qualitative evaluation scoring both preference and clinical utility for blinded structure sets. Physician consensus data sets identified from the qualitative evaluation were used toward a separate CTV model. RESULTS: Both the 30- and 60-case retrained OAR models had median DSC values between 0.91 to 0.97, improving significantly over the vendor-trained model for all OARs except the penile bulb. The brand new 60-case CTV model had a median DSC of 0.70 improving significantly over the 30-case model. DLAS (60-case model) and manual contours were blinded and evaluated by physicians with contours deemed acceptable or precise for 87% and 94% of cases for DLAS and manual delineations, respectively. DLAS-generated CTVs were scored precise or acceptable in 54% of cases, compared with the manual delineation value of 73%. The 30-case physician consensus CTV model did not show a significant difference compared with the randomly selected models. CONCLUSIONS: Custom retraining using institutional data leads to performance improvement in the clinical utility and accuracy of DLAS for postprostatectomy patients. A small number of data sets are sufficient for building an institutional site-specific DLAS OAR model, as well as for training new structures. Data indicates the workload for identifying training data sets could be shared among groups for the male pelvic region, making it accessible to clinics of all sizes.

Initial Quality of Life and Toxicity Analysis of a Randomized Phase 3 Study of Moderately Hypofractionated Radiation Therapy With or Without Androgen Suppression for Intermediate-Risk Adenocarcinoma of the Prostate: PCG GU003.

Purpose: Our objective was to report the quality of life (QoL) analysis and toxicity in patients with intermediate-risk prostate cancer treated with or without androgen deprivation therapy (ADT) in Proton Collaborative Group (PCG) GU003. Methods and Materials: Between 2012 and 2019, patients with intermediate-risk prostate cancer were enrolled. Patients were randomized to receive moderately hypofractionated proton beam therapy (PBT) to 70 Gy relative biologic effectiveness in 28 fractions to the prostate with or without 6 months of ADT. Expanded Prostate Cancer Index Composite, Short-Form 12, and the American Urological Association Symptom Index instruments were given at baseline and 3, 6, 12, 18, and 24 months after PBT. Toxicities were assessed according to Common Terminology Criteria for Adverse Events (version 4). Results: One hundred ten patients were randomized to PBT either with 6 months of ADT (n = 55) or without ADT (n = 55). The median follow-up was 32.4 months (range, 5.5-84.6). On average, 101 out of 110 (92%) patients filled out baseline QoL and patient-reported outcome surveys. The compliance was 84%, 82%, 64%, and 42% at 3, 6, 12, and 24 months, respectively. Baseline median American Urological Association Symptom Index was comparable between arms (6 [11%] ADT vs 5 [9%] no ADT, P = .359). Acute and late grade 2+ genitourinary and gastrointestinal toxicity were similar between arms. The ADT arm experienced a QoL decline of mean scores in the sexual (-16.1, P < .001) and hormonal (-6.3, P < .001) domains, with the largest time-specific hormonal differences at 3 (-13.8, P < .001) and 6 (-11.2, P < .001) months. The hormonal QoL domain returned to baseline 6 months after therapy. There was a trend to baseline in sexual function 6 months after completion of ADT. Conclusions: After 6 months of ADT, sexual and hormonal domains returned to baseline 6 months after completion of treatment for men with intermediate-risk prostate cancer.

Clinical outcomes and toxicities of 100 patients treated with proton therapy for chordoma on the proton collaborative group prospective registry.

BACKGROUND: We present efficacy and toxicity outcomes among patients with chordoma treated on the Proton Collaborative Group prospective registry. METHODS: Consecutive chordoma patients treated between 2010-2018 were evaluated. One hundred fifty patients were identified, 100 had adequate follow-up information. Locations included base of skull (61%), spine (23%), and sacrum (16%). Patients had a performance status of ECOG 0-1 (82%) and median age of 58 years. Eighty-five percent of patients underwent surgical resection. The median proton RT dose was 74 Gy (RBE) (range 21-86 Gy (RBE)) using passive scatter proton RT (PS-PBT) (13%), uniform scanning proton RT (US-PBT) (54%) and pencil beam scanning proton RT (PBS-PBT) (33%). Rates of local control (LC), progression-free survival (PFS), overall survival (OS) and acute and late toxicities were assessed. RESULTS: 2/3-year LC, PFS, and OS rates are 97%/94%, 89%/74%, and 89%/83%, respectively. LC did not differ based on surgical resection (p = 0.61), though this is likely limited by most patients having undergone a prior resection. Eight patients experienced acute grade 3 toxicities, most commonly pain (n = 3), radiation dermatitis (n = 2), fatigue (n = 1), insomnia (n = 1) and dizziness (n = 1). No grade ≥ 4 acute toxicities were reported. No grade ≥ 3 late toxicities were reported, and most common grade 2 toxicities were fatigue (n = 5), headache (n = 2), CNS necrosis (n = 1), and pain (n = 1). CONCLUSIONS: In our series, PBT achieved excellent safety and efficacy outcomes with very low rates of treatment failure. CNS necrosis is exceedingly low (<1%) despite the high doses of PBT delivered. Further maturation of data and larger patient numbers are necessary to optimize therapy in chordoma.

Preliminary Analysis of a Phase II Trial of Stereotactic Body Radiation Therapy for Prostate Cancer With High-Risk Features After Radical Prostatectomy.

Purpose: There are limited data regarding using stereotactic body radiation therapy (SBRT) in the postprostatectomy setting. Here, we present a preliminary analysis of a prospective phase II trial that aimed to evaluate the safety and efficacy of postprostatectomy SBRT for adjuvant or early salvage therapy. Materials and Methods: Between May 2018 and May 2020, 41 patients fulfilled inclusion criteria and were stratified into 3 groups: group I (adjuvant), prostate-specific antigen (PSA) < 0.2 ng/mL with high-risk features including positive surgical margins, seminal vesicle invasion, or extracapsular extension; group II (salvage), with PSA ≥ 0.2 ng/mL but < 2 ng/mL; or group III (oligometastatic), with PSA ≥ 0.2 ng/mL but < 2 ng/mL and up to 3 sites of nodal or bone metastases. Androgen deprivation therapy was not offered to group I. Androgen deprivation therapy was offered for 6 months for group II and 18 months for group III patients. SBRT dose to the prostate bed was 30 to 32 Gy in 5 fractions. Baseline-adjusted physician reported toxicities (Common Terminology Criteria for Adverse Events), patient reported quality-of-life (Expanded Prostate Index Composite, Patient-Reported Outcome Measurement Information System), and American Urologic Association scores were evaluated for all patients. Results: The median follow-up was 23 months (range, 10-37). SBRT was adjuvant in 8 (20%) patients, salvage in 28 (68%), and salvage with the presence of oligometastases in 5 (12%) patients. Urinary, bowel, and sexual quality of life domains remained high after SBRT. Patients tolerated SBRT with no grade 3 or higher (3+) gastrointestinal or genitourinary toxicities. The baseline adjusted acute and late toxicity grade 2 genitourinary (urinary incontinence) rate was 2.4% (1/41) and 12.2% (5/41). At 2 years, clinical disease control was 95%, and biochemical control was 73%. Among the 2 clinical failures, 1 was a regional node and the other a bone metastasis. Oligometastatic sites were salvaged successfully with SBRT. There were no in-target failures. Conclusions: Postprostatectomy SBRT was very well tolerated in this prospective cohort, with no significant effect on quality of life metrics postirradiation, while providing excellent clinical disease control.