Associations Between Mean Lung Dose and Prevalence of Radiation Pneumonitis in Elderly Lung Cancer Patients.

BACKGROUND/AIM: Pneumonitis is a serious radiotherapy complication. This study, which is a prerequisite for a prospective trial, aimed to identify the prevalence of pneumonitis and risk factors in elderly patients with lung cancer. PATIENTS AND METHODS: Ninety-eight lung cancer patients aged ≥65 years were included. Seventeen factors were investigated regarding grade ≥2 pneumonitis at 24 weeks following radiotherapy. RESULTS: The prevalence of grade ≥2 pneumonitis at 24 weeks was 27.3%. On univariate analysis, a significant association was observed for mean (ipsilateral) lung dose (MLD; ≤13.0 vs. 13.1-20.0 vs. >20.0 Gy; 0% vs. 24.9% vs. 48.7%). Results were significant also for ≤13.0 vs. >13.0 Gy (0% vs. 37.1%) or ≤20.0 vs. >20.0 Gy (13.4% vs. 48.7%). MLD achieved significance on multivariate analysis. CONCLUSION: Elderly patients receiving MLDs >13.0 Gy, particularly >20.0 Gy, have a high risk of grade ≥2 pneumonitis. These results are important for designing a prospective trial.

The Role of Radiotherapy for Meningeal Melanocytomas - A 20 Year Update.

BACKGROUND/AIM: Meningeal melanocytomas are rare tumors of the central nervous system and optimal treatment needs further clarification. This study compared subtotal resection (STR), STR plus radiation therapy (RT), gross total resection (GTR), and GTR+RT to better define the role of postoperative RT. PATIENTS AND METHODS: All cases reported in the literature were reviewed. Patients (n=184) with complete data were analyzed for local control (LC) and overall survival (OS). RESULTS: On univariate analysis, GTR (vs. STR) was associated with improved LC (p=0.016). When comparing the treatment regimens, best and worst results were found after GTR+RT and STR alone, respectively (p<0.001). On univariate analysis, GTR resulted in better OS than STR (p=0.041). Moreover, the treatment regimen had a significant impact on OS (p=0.049). On multivariate analyses of LC and OS, extent of resection and treatment regimen were found to be significant factors. After STR, RT significantly improved LC but not OS. After GTR, RT did not significantly improve LC or OS. CONCLUSION: GTR was significantly superior to STR regarding LC and OS. STR+RT resulted in significantly better LC when compared to STR alone.

Clinically Significant Dermatitis During Adjuvant Radiotherapy for Invasive Breast Cancer.

BACKGROUND/AIM: Patients with breast cancer receiving adjuvant radiotherapy may experience grade ≥2 dermatitis. In the Interreg-project HeAT, a mobile application (app) reminding patients to perform skin care will be prospectively tested with the goal of decreasing clinically significant radiation dermatitis. This study aimed to identify the prevalence of grade ≥2 dermatitis and risk factors, required for designing the prospective trial. PATIENTS AND METHODS: In a retrospective study of 327 patients with breast cancer irradiated during 2022-2023, the prevalence of grade ≥2 dermatitis and 23 potential risk factors were investigated. RESULTS: The prevalence of grade ≥2 dermatitis was 31.2%. On multivariate analysis, it was significantly associated with chronic inflammatory disease (p=0.001), significant cardiovascular disease (p<0.001), smoking history >10 pack years (p<0.001), advanced T-stage (p=0.017), normo-fractionation (p<0.001), and radiation boost (p<0.001). CONCLUSION: The prevalence of grade ≥2 dermatitis and independent risk factors during adjuvant radiotherapy for invasive breast cancer were identified that contribute to improved patient care and the design of a prospective trial.

Proton Pencil-Beam Scanning Stereotactic Body Radiation Therapy and Hypofractionated Radiation Therapy for Thoracic Malignancies: Patterns of Practice Survey and Recommendations for Future Development from NRG Oncology and PTCOG.

Stereotactic body radiation therapy (SBRT) and hypofractionation using pencil-beam scanning (PBS) proton therapy (PBSPT) is an attractive option for thoracic malignancies. Combining the advantages of target coverage conformity and critical organ sparing from both PBSPT and SBRT, this new delivery technique has great potential to improve the therapeutic ratio, particularly for tumors near critical organs. Safe and effective implementation of PBSPT SBRT/hypofractionation to treat thoracic malignancies is more challenging than the conventionally-fractionated PBSPT due to concerns of amplified uncertainties at the larger dose per fraction. NRG Oncology and Particle Therapy Cooperative Group (PTCOG) Thoracic Subcommittee surveyed US proton centers to identify practice patterns of thoracic PBSPT SBRT/hypofractionation. From these patterns, we present recommendations for future technical development of proton SBRT/hypofractionation for thoracic treatment. Amongst other points, the recommendations highlight the need for volumetric image guidance and multiple CT-based robust optimization and robustness tools to minimize further the impact of uncertainties associated with respiratory motion. Advances in direct motion analysis techniques are urgently needed to supplement current motion management techniques.

NRG Oncology and PTCOG Patterns of Practice Survey and Consensus Recommendations on Pencil-Beam Scanning Proton Stereotactic Body Radiation Therapy and Hypofractionated Radiation Therapy for Thoracic Malignancies.

Stereotactic body radiation therapy (SBRT) and hypofractionation using pencil-beam scanning (PBS) proton therapy (PBSPT) is an attractive option for thoracic malignancies. Combining the advantages of target coverage conformity and critical organ sparing from both PBSPT and SBRT, this new delivery technique has great potential to improve the therapeutic ratio, particularly for tumors near critical organs. Safe and effective implementation of PBSPT SBRT/hypofractionation to treat thoracic malignancies is more challenging than the conventionally fractionated PBSPT because of concerns of amplified uncertainties at the larger dose per fraction. The NRG Oncology and Particle Therapy Cooperative Group Thoracic Subcommittee surveyed proton centers in the United States to identify practice patterns of thoracic PBSPT SBRT/hypofractionation. From these patterns, we present recommendations for future technical development of proton SBRT/hypofractionation for thoracic treatment. Among other points, the recommendations highlight the need for volumetric image guidance and multiple computed tomography-based robust optimization and robustness tools to minimize further the effect of uncertainties associated with respiratory motion. Advances in direct motion analysis techniques are urgently needed to supplement current motion management techniques.

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.

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.

Distress Scores in Elderly Cancer Patients During Radiotherapy.

BACKGROUND/AIM: When assigned to radiotherapy (RT), elderly patients may experience distress. We investigated distress during RT and potential risk factors in these patients. PATIENTS AND METHODS: Six-hundred-and-nineteen patients completed pre-RT and post-RT distress thermometers. Seven characteristics were investigated including age, sex, Karnofsky performance score (KPS), grouped KPS, tumor type, intent of RT, and previous RT. Additional analyses were performed in 358 patients with pre-RT scores ≤5. RESULTS: Mean change of distress was -0.5 (±2.7) points and associated with KPS (p=0.005) and grouped KPS (p<0.001). Male sex (p=0.035), KPS 90-100 (p=0.001), and curative intent (p=0.037) were associated with increased distress on univariable analyses, and KPS 90-100 (odds ratio=1.92, p=0.004) on multivariable analysis. In patients with baseline scores ≤5, mean change was +0.5 (±2.5) points and associated with KPS (p=0.040) and grouped KPS (p=0.025). CONCLUSION: Psychological assistance should be considered for all patients including those with baseline scores ≤5 and KPS 90-100. Patients with risk factors for increased distress would especially benefit.

Development of Distress During a Radiotherapy Course in Patients Irradiated for Breast Cancer.

BACKGROUND/AIM: Breast cancer patients receiving radiation therapy (RT) may experience considerable distress. We investigated the course of distress during an RT-course for breast cancer. PATIENTS AND METHODS: Three-hundred-and-thirty breast cancer patients completed Distress Thermometers before and directly after RT. Distress was evaluated in the entire cohort and different groups of age, sex, Karnofsky performance score (KPS), intent of RT, and previous RT. RESULTS: Mean change of distress scores was - 0.4 points, which was significantly associated with KPS. Decrease of distress was more pronounced in patients with KPS ≤80 or age <64 years. Deterioration (yes vs. no) was non-significantly associated with no previous RT. In patients with pre-RT distress scores ≤5 points, mean score increased by +0.5 points; no significant associations between characteristics and investigated endpoints were found. CONCLUSION: Psychological assistance should be offered to all patients irradiated for breast cancer, particularly to those with risk factors, regardless of the pre-RT distress score.

Radiation Dermatitis and Pneumonitis in Patients Irradiated for Breast Cancer.

BACKGROUND/AIM: Adjuvant radiotherapy (RT) for breast cancer can be associated with acute dermatitis (ARD) and pneumonitis (RP). Prevalence and risk factors were characterized. PATIENTS AND METHODS: This study included 489 breast cancer patients receiving adjuvant RT with conventional fractionation (CF) ± sequential or simultaneous integrated boost, or hypo-fractionation ± sequential boost. RT-regimen and 15 characteristics were investigated for grade ≥2 ARD and RP. RESULTS: Prevalence of grade ≥2 ARD and RP was 25.3% and 2.5%, respectively. On univariate analyses, ARD was significantly associated with CF and radiation boost (p<0.0001), age ≤60 years (p=0.008), Ki-67 ≥15% (p=0.012), and systemic treatment (p=0.002). On multivariate analysis, RT-regimen (p<0.0001) and age (p=0.009) were associated with ARD. Chronic inflammatory disease was significantly associated with RP on univariate (p=0.007) and multivariate (p=0.016) analyses. CONCLUSION: Risk factors for grade ≥2 ARD and RP were determined that may help identify patients who require closer monitoring during and after RT.

Whole-breast Radiotherapy With Boost for Node-negative Breast Cancer: Conventional vs. Hypo-fractionation.

BACKGROUND/AIM: Many breast cancer patients receive adjuvant radiotherapy. Tumor bed boost may reduce risk of local failure in high risk patients. We compared hypofractionated whole-breast irradiation (WBI) plus boost (HF+boost) and conventionally fractionated WBI plus boost (CF+boost). PATIENTS AND METHODS: One-hundred-and-twenty-eight patients receiving HF-WBI (40 Gy in 15 fractions) plus boost (group A) were matched to 127 patients receiving CF-WBI (50.4 Gy in 28 fractions) plus boost (group B), utilizing 10 characteristics. RESULTS: Grade ≥2 dermatitis rates were 16.4% in group A vs. 44.1% in group B (p<0.0001), and grade ≥2 pneumonitis rates were 1.6% vs. 2.4% (p=0.68). Four-year rates of local control, metastases-free survival, and overall survival were 100% vs. 99% (p=0.81), 98% vs. 100% (p=0.29), and 98% vs. 100% (p=0.17), respectively. CONCLUSION: HF+boost was associated with significantly less grade ≥2 dermatitis with similar disease control and survival.

Simultaneous vs. Sequential Boost for Adjuvant Breast Radiotherapy.

BACKGROUND/AIM: During the last 10-15 years, alternative regimens for adjuvant radiotherapy (RT) of breast cancer have become more popular, including simultaneous integrated (SIB) instead of sequential boosts (SEB). We present long-term outcomes after conventional fractionation (CF) plus SIB vs. CF+SEB. PATIENTS AND METHODS: Forty-eight patients receiving CF+SIB (treatment time=5.5 weeks) were matched to 72 patients (control group) receiving CF+SEB (6.5 weeks) considering twelve characteristics. Both groups were compared for radiation dermatitis, pneumonitis, local control (LC), metastases-free survival (MFS), cancer-specific survival (CSS), and overall survival (OS). RESULTS: Rates of grade ≥2 dermatitis were 35.4% (CF+SIB) and 45.8% (CF+SEB), respectively (p=0.26), and rates of grade ≥2 pneumonitis 0% and 4.2%, respectively (p=0.27). Six-year LC, MFS, CSS, and OS rates were 100% vs. 93% (p=0.11), 97% vs. 100% (p=0.29), 100% vs. 100% (p=1.00), and 98% vs. 100% (p=0.23), respectively. CONCLUSION: CF+SIB was similar to CF+SEB in terms of toxicities and outcomes but reduces total treatment time by one week.

Distress Scores During Radiotherapy for Lung Cancer: Course and Prognostic Factors.

Background/Aim: Cancer treatment can lead to significant distress. We investigated the course of distress during radiotherapy (RT) for lung cancer. Patients and Methods: Data of 159 patients receiving RT for lung cancer were investigated for change of distress scores during RT. Five characteristics were analyzed including age, sex, Karnofsky performance score, intent of RT, and receipt of previous RT. Additional analyses were performed in patients with pre-RT scores ≤5 points. Results: Mean pre-RT and post-RT distress scores were 5.5 (±2.6) and 4.7 (±2.6), respectively. No characteristic was significantly associated with mean change or increase of distress. In patients with pre-RT scores ≤5 points, non-significantly higher rates of increased distress were found for age ≤64 years, female sex, and Karnofsky performance score 90-100. Conclusion: Distress is reduced during a course of RT for lung cancer. This may reflect a reduction in anticipatory distress after first-hand experience.

Chemoimmunotherapy in patients with extensive-stage small cell lung cancer and a poor performance status.

BACKGROUND: Immune checkpoint inhibitor combined with platinum-etoposide is the standard first-line therapy for patients with extensive-stage small cell lung cancer (ES-SCLC). The phase 3 clinical trials that led to the approval of chemoimmunotherapy in ES-SCLC excluded patients who had an Eastern Cooperative Group (ECOG) performance status (PS) of 2-3. Therefore, data on the efficacy of chemoimmunotherapy in patients with an ECOG PS of 2-3 are limited. METHODS: A retrospective analysis was performed on patients diagnosed with ES-SCLC who received chemoimmunotherapy (atezolizumab or durvalumab) within the Mayo Clinic Health System between January 2016 and January 2021. The objective of this study was to compare the overall survival (OS), progression-free survival (PFS), and best clinical response to therapy in patients with an ECOG PS of 0-1 vs. patients with an ECOG PS of 2-3 who received chemoimmunotherapy for newly diagnosed ES-SCLC. RESULTS: In total, 82 patients were included in the study. The mean ± standard deviation age was 68.1 ± 8.3 years. Of these, 56 patients were identified with an ECOG PS of 0-1, and 26 patients were identified with an ECOG PS of 2-3. The median PFS was similar regardless of ECOG PS (5.8 months [95% CI, 4.3-6.0 months] in the ECOG PS 0-1 group vs. 4.1 months [95% CI, 3.8-6.9 months] in the ECOG PS 2-3; p = .2994). The median OS was also similar regardless of ECOG PS (10.6 months [95% CI, 8.4-13.4 months] in the ECOG PS 0-1 group vs. 9.3 months [95% CI, 4.9-12.8 months]; p = .2718) in the ECOG PS 2-3 group. CONCLUSIONS: The study results demonstrated no significant difference in PFS or OS among the ECOG PS 2-3 and ECOG PS 0-1 groups. Therefore, chemoimmunotherapy should be considered for patients who have ES-SCLC with an ECOG PS of 2-3.

Final Results of a Study Evaluating the Course of Distress Scores During Radiotherapy for Malignant Diseases.

BACKGROUND/AIM: Patients who receive radiotherapy (RT) may experience significant distress. This study investigated distress scores during RT for a variety of malignancies. PATIENTS AND METHODS: Distress thermometers (scores of 0-10 points) were completed by 927 patients at baseline and end of RT. Six characteristics were evaluated for changes of distress scores including age, sex, Karnofsky performance score (KPS), tumor type, intent of treatment, and previous RT. RESULTS: Mean distress scores were 4.9 (±2.7) at baseline and 4.6 (±2.7) at the end of RT; mean change was -0.3 (±2.8) points. On univariable analysis, increased distress (≥2 points) was significantly associated with KPS 90-100 (p<0.001) and curative intent (p=0.040). Trends were found for age ≤64 years (p=0.062), head-and-neck cancer (p=0.076), and no prior RT (p=0.055). In patients with baseline scores ≤5 points, deterioration rates were 30-47%. CONCLUSION: Psychological support should be offered to all patients undergoing RT. This would benefit particularly patients with risk factors for increased distress.

Development of Distress During a Radiotherapy Course for Head-and-neck Cancer.

BACKGROUND/AIM: Radiotherapy (RT) is a standard treatment for head-and-neck cancer, which can be associated with patient distress. This study provides data investigating distress during head-and-neck RT. PATIENTS AND METHODS: Fifty-six patients completed the Distress Thermometer before and on the last day of their RT-course. Mean changes of distress scores and increase of distress were evaluated. Age, sex, Karnofsky performance score (KPS), tumor type, intent of RT, and previous RT were analyzed for associations with course of distress. RESULTS: Mean pre-RT and post-RT distress scores were 5.1 (±2.6) and 5.0 (±2.7) points, respectively (mean change: ±0.0 points). Mean change of distress scores was significantly associated with age (p=0.042) and KPS (p<0.001). On multivariable analysis, increased distress (by ≥2 points) was associated with KPS 90-100 (p=0.011) and palliative intent of RT (p=0.036). CONCLUSION: Mean pre-RT and post-RT distress scores were almost identical. Patients with risk factors for increased distress during their RT-course should be offered immediate psychological support.

Comparison of Distress Scores Before and After Radiotherapy for Prostate Cancer.

BACKGROUND/AIM: Prostate cancer patients undergoing radiotherapy (RT) may experience distress. This study evaluated the course of distress during RT. PATIENTS AND METHODS: Four distress characteristics were analyzed for change of distress in 136 patients irradiated for prostate cancer, including age, Karnofsky performance score, intent of RT, and previous RT. RESULTS: Mean distress scores were 4.3 (±2.9) at baseline and 4.2 (±2.7) at the end of RT. Associations with increased distress were found for KPS >80 (p<0.001) and curative intent RT (p=0.072). When evaluating increased distress as binary variable (yes vs. no), KPS >80 was significant on univariable (p<0.001) and multivariable (p=0.016) analyses. In patients with baseline scores ≤5 points, KPS >80 was associated with mean change of distress (p=0.009) and increased distress (p=0.029). CONCLUSION: Many patients receiving RT for prostate cancer do not experience increased distress during their treatment course. Patients at higher risk of increased distress may require early psychological assistance.

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.