Purpose The study aimed to compare dosimetric, biological and efficiency differences between circular collimator (CC) and InCise multi-leaf collimator (MLC) of CyberKnife (CK) for various number of metastases, and to develop and validate a quantitative scoring method for collimator selection in stereotactic radiotherapy (SRT) of brain metastases. Methods For 57 patients with 1 to 5 intracranial metastases who received treatment with CK, two plans were designed for each patient using both MLC and CC. Dosimetric parameters, biological parameters, and treatment efficiency were analyzed using the paired t-test or the Wilcoxon signed-rank test after normality assessment with the Shapiro-Wilk test. These parameters included the minimum dose (PTV_Dmin), equivalent uniform dose (PTV_EUD), and tumor control probability (PTV_TCP) for the planning target volume (PTV), the conformity index (CI), gradient index (GI), homogeneity index (HI), maximum dose (Dmax) to organs at risk (OARs), normal brain volumes receiving 12 Gy, 6 Gy, and 3 Gy (V12Gy, V6Gy, V3Gy), normal tissue complication probability (NTCP), and the number of nodes, beams, total monitor units (MUs), and delivery time. A mathematical score was used to calculate the overall quality of both plans and was validated against a clinical score provided by radiation oncologists. Results For 1–2 metastases, CC provided significantly higher PTV_Dmin and PTV_EUD compared to MLC (p < 0.05), with no significant differences in CI, GI, or OAR doses. For ≥ 3 metastases, MLC significantly reduced treatment time (by 20–40%) and delivered more homogeneous target dose. (lower HI, p < 0.001), while increasing low-dose brain volumes (V6Gy and V3Gy, p < 0.05). No significant differences were observed in PTV_TCP or brain V12Gy (p > 0.05). The mathematical scoring method correlated well with clinical score (rs = 0.63, p < 0.001) and demonstrated robustness to weight adjustments. Conclusions The CC is considered for patients with 1–2 brain metastases, while the MLC is considered for patients with three or more metastases, and the validated scoring method supports objective collimator selection in clinical practice. These findings provide a quantitative treatment planning reference for collimator selection but require prospective clinical validation before routine implementation. Trial registration This study is retrospectively registered in the Clinical trial Center of Zhejiang Cancer Hospital in Jan 1st, 2024 (No. MR-33-24-005006)

Due to the limited number of studies on MR-only stereotactic radiotherapy (SRT) for brain metastases using CyberKnife in the literature, this study systematically evaluates the dose calculations and image guidance accuracy of synthetic CT (sCT) and sCT-derived digital reconstructed radiographs (sDRRs), to assess the feasibility of clinical MR-only workflow implementation in CyberKnife SRT for brain metastases. We developed a machine learning model trained on T1-weighted MR and corresponding CT images from 50 patients with brain metastases who had previously undergone CyberKnife treatment, with images from an additional 18 patients used to test the feasibility of the MR-only workflow. The Mean Absolute Error (MAE), Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR) and the Dice Similarity Coefficient (DSC) were used to evaluate the image quality of sCT and sDRR. For dosimetric evaluation, the sCT-based and transferred plans (namely, the original planning parameters were transferred to the sCT images for dose recalculation) was compared with the plans based on the real CT images (rCT) using DVH metrics. For image-guided positioning accuracy, the 2D errors generated by registering DRR with the digital radiography images (DRs) were converted into translational and rotational couch shifts using a geometric back-projection method, thereby assessing the consistency of positioning accuracy between the sDRRs with the rCT-derived DRRs (rDRRs). The sCT images had a mean MAE of 10.08 ± 2.14 HU, a SSIM of 0.98 ± 0.01, and a PSNR of 34.73 ± 1.27 dB, and the overall sDRRs maintained high image quality (MAE: 37.36 ± 9.31 HU; SSIM: 0.95 ± 0.03; PSNR: 31.41 ± 7.14 dB). Large OARs (brainstem/eyeballs) had high DSC (> 0.80), while small OARs (lenses/optic pathway) had lower DSC. The dosimetric parameters of PTV and OARs under both planning strategies showed no statistically significant difference from the rCT-based plans (p > 0.05). When using sDRRs for image guidance, the translational errors were submillimeter, and the rotational errors had a wider distribution but mean values within robotic correction range, there was no statistical difference compared with that of the rDRRs (p > 0.05). The proposed model can generate accurate sCT for brain metastases, and the feasibility of the MR-only in CyberKnife SRT has been verified. This study is retrospectively registered in the Clinical trial Center of Zhejiang Cancer Hospital in Jan 1th, 2024 (No. MR-33-24-003134).

Breast cancer (BC) is the most common malignancy with a poor prognosis. Radiotherapy is one of the leading traditional treatments for BC. However, radiotherapy-associated secondary diseases are severe issues for the treatment of BC. The present study integrated multi-omics data to investigate the molecular and epigenetic mechanisms involved in post-radiation BC. The differences in the expression of radiation-associated genes between post-radiation and pre-radiation BC samples were determined. Enrichment analysis revealed that these radiation-associated genes involved diverse biological functions and pathways in BC. Combining epigenetic data, we identified radiation-associated genes whose transcriptional changes might be associated with aberrant methylation. Then, we identified potential therapeutic targets and chemical drugs for post-radiation BC patient treatment by constructing a drug-target association network. Specifically, four radiation-associated genes (CD248, CCDC80, GADD45B, and MMP2) whose increased expression might be regulated by hypomethylation of the corresponding enhancer region were found to have excellent diagnostic effects and clinical prognostic value. Finally, we further used independent samples to verify CD248 expression and established a simple epigenetic regulatory model. In summary, this study provides novel insights for understanding the regulation of target genes mediated by DNA methylation and developing potential biomarkers for radiation-associated secondary diseases in BC.

PURPOSE:To assess the stability of dosiomic features in response to dose distribution variations caused by respiratory motion. METHODS AND MATERIALS:A total of 24 lung cancer patients who underwent 4DCT scanning and radiotherapy were included. For each patient, a 3D dose matrix and three 4D dose matrices generated using three distinct methods were calculated. Dosiomic features were extracted from dose distributions for four regions of interest: the gross tumor volume (GTV), the planning target volume (PTV), the heart, and the lung. The stability of each dosiomic feature was evaluated using the coefficient of variation (CV), while reproducibility was assessed using the intraclass correlation coefficient (ICC). The differences between 3D and 4D dose features were determined using the normalized difference (ND). RESULTS:5.0% of dosiomic features had a CV greater than or equal to 20%. The CVs were highest in the GTV region and lowest in the lung region. Additionally, 0.27% of features had an ICC less than 0.5, while 92.74% had an ICC greater than 0.9. 16.48% of features had an absolute value of the ND greater than 0.4. CONCLUSIONS:The stability of certain dosiomic features is strongly influenced by respiratory motion in radiotherapy. To ensure result reproducibility, dosiomic studies should fully consider the impact of respiratory motion during dose calculation or excluding unstable features to enhance model stability.

Background: Whole-brain radiotherapy(WBRT) can alleviate symptoms in patients with brain metastases. However, WBRT may damage the hippocampus.The helical tomotherapy (HT) presents a significant dosimetric advantage in the hippocampus avoidance WBRT(HA-WBRT). How to design linear accelerator radiation therapy plan for HA-WBRT is a challenge for medical physicists. Objective: The aim of this study is to investigate the dosimetric differences between noncoplanar VMAT(NCVMAT) and HT in HA-WBRT, exploring the feasibility of NC-VMAT for HA-WBRT. Methods: Fifteen patients with HA-WBRT were chosen randomly. For each patient, the Monaco TPS was used to design four distinct NC-VMAT plans based on the quantity of non-coplanar arcs (NC-VMATA, NC-VMATB,NC-VMATC,NC-VMATD) for HA-WBRT, totaling 60 plans. The HT TPS was used to generate HT plans, totaling 15 plans.The prescribed dose was 30 Gy in 10 fractions. Treatment plans were established based on the RTOG 0933 criteria.Under the premise that the 95% isodose curve covers the target area, dose-volume histogram(DVH) was applied to evaluate the WB-PTV, CI, HI, Dmax, Dmean, Dmin and doses of OARs in NC-VMAT and HT plans. Paired t-test was performed to compare the differences between each two radiation therapy plans, and p < 0.05 was considered statistically significant. Results: The RTOG0933 criteria could not be satisfied in NC-VMATA with 1 non-coplanar beam. NC-VMATB with 2 non-coplanar beams, the condition Dmax<16 Gy was not satisfied for 8 case in the hippocampus. NC-VMATC with 3 non-coplanar beams, the condition D98% > 25 Gy was not satisfied for 5 case in the WB-PTV. NC-VMATD with 4 non-coplanar beams and HT, all plans complied with the "Per protocol" requirements in the RTOG 0933 standard.We compared NC-VMATD with HT and found that there were no differences in the D98% and D2% of WB-PTV. However, the HT was significantly superior to NC-VMATD in terms of CI, HI, Dmean in HP, Dmax in Lens, Dmean in eyes (p < 0.05). The Dmax, D100% of HP and the dosimetry of other OARs had no significant difference (p > 0.05).In contrast, the average beam on time in NC-VMATD was greater advantage(506s Vs 687s, p < 0.05). NC-VMAT and HT planning templates were devised, which facilitated physicists in rapidly designing high-quality HA-WBRT plans. Conclusion: NC-VMAT proves to be effective in managing HA-WBRT.The plan quality improved along with the increase of non-coplanar arcs. NC-VMAT(one full arc and four noncoplanar partial arcs) with FFF irradiation mode is most recommended plan design pattern. NC-VMAT provides a practical clinical treatment option for HAWBRT based on linear accelerators.

Deep learning (DL) -based automated treatment planning (ATP) shows significant promise in streamlining radiotherapy workflow and reducing variability in plan quality. However, it often lacks the flexibility needed for achieving individualized trade-offs in real-world practice. Herein, we propose a hybrid strategy by integrating DL-based dose prediction with clinical-goal-guided inverse optimization to generate directly deliverable plans within five minutes. DL models for five disease sites were trained separately using datasets from a single institution and were tested retrospectively for clinical application among three institutions, with tailored prioritized clinical goals. We find that over 80% of the 250 auto-plans met clinical criteria, and 60% were preferred over manual plans in blinded reviews. Dosimetric analyses show that the auto-plans quantitatively matched or exceeded the quality of human-driven plans. This study highlights ATP's potential to transform radiotherapy practice, with ongoing efforts aimed at refining its versatility and adoption across diverse clinical settings.

Accurate and efficient automatic segmentation is essential for various clinical tasks such as radiotherapy treatment planning. However, atlas-based segmentation still faces challenges due to the lack of representative atlas dataset and the computational limitations of deformation algorithms. In this work, we have proposed an atlas selection procedure (subset atlas grouping approach, MAS-SAGA) which utilized both image similarity and volume features for selecting the best-fitting atlases for contour propagation. A dataset of anonymized female pelvic Computed Tomography (CT) images demonstrated that MAS-SAGA significantly outperforms conventional multi-atlas-based segmentation (cMAS) in terms of Dice Similarity Coefficient (DSC) and 95th Percentile Hausdorff Distance (95HD) for bladder and rectum segmentation using a three-fold cross-validation strategy. The proposed procedure also reduced computation time compared to cMAS, making it a promising tool for medical image analysis applications. In addition, we have evaluated two distinct atlas selection methods: the Feature-based Atlas Selection Approach (MAS-FASA) and the Similarity-based Atlas Selection Approach (MAS-SIM). We investigate the differences between these two methods in terms of their ability to select the best fitting atlases. The findings demonstrated that MAS-FASA selected different atlases than MAS-SIM, resulting in improved segmentation performance overall. It highlighted the potential of feature-based subgrouping techniques in enhancing the efficacy of MAS algorithms in the field of medical image segmentation.

Objective: A comparative analysis is conducted to examine dosimetric discrepancies between flattening filter-free (FFF) and flattened (FF) beam noncoplanar volumetric modulated arc therapy (NCVMAT) plans for whole brain radiotherapy (WBRT) with hippocampus avoidance. Methods: Fifteen patients who underwent WBRT with hippocampus avoidance were randomly selected. Individual treatment plans were created on the Infinity accelerator for FF-NCVMAT and FFF-NCVMAT, both with a prescribed dose of 30Gy/10F and identical plan parameters using the Monaco treatment planning system (TPS). The plans were designed to meet the dosimetric requirements specified in RTOG 0933. Both groups achieved a planning target volume (PTV) coverage rate of 95% for the prescribed dose. The dosimetric parameters, including machine units (MU), delivery time (DT), plan modulation factor (MF), and gamma pass rate(GPR) were compared between the two plans. Results: There were no significant differences in minimum dose (Dmin) and homogeneity index (HI) of the PTV between the FFF-NCVMAT group and the FF-NCVMAT group (P = 0.828, 0.453). However, utilization of the FFF mode effectively reduced maximum dose (Dmax) of the PTV and improved conformity index (CI), with statistical significance observed (P = 0.010, 0.006). The MF and GPR between both plans were similar (P = 0.599,0.130). Within the FFF-NCVMAT group, Dmax, D100%, and mean dose (Dmean) of the hippocampus were significantly smaller compared to those in the FF-NCVMAT group, demonstrating statistically significant differences(P < 0.001, P < 0.001, P < 0.001). In the FFF-NCVMAT group, the Dmax of the left and right optic nerves and optic chiasm were all smaller than those in the FF-NCVMAT group, and the differences were statistically significant (P = 0.027, 0.033, 0.043). The doses of other organs at risk (OARs) such as lens and eyes were all controlled within the clinically safe dose range, and there was no statistically significant difference between the two plans (P = 0.912, 0.179; P = 0.850, 0.855). The MU of the FFF-NCVMAT group was higher than that of the FF-NCVMAT group, but the DT was shorter than that of the FF-VMAT group, and the differences were statistically significant (P <0.001, P < 0.001). Conclusion: The FF-NCVMAT and FFF-NCVMAT plans both meet the clinical requirements of RTOG 0933, and their complexity is comparable. However, the FFF-NCVMAT plan offers an advantage in terms of hippocampus and lens protection. Despite having a higher MU, the FFF mode has a shorter DT, resulting in improved treatment efficiency. Therefore, it is recommended to consider using the FFF-NCVMAT plan for HA-WBRT.

Background: Cervical cancer radiotherapy in young patients risks premature ovarian failure. Ovarian-sparing techniques (OS-CRT) are critical for preserving fertility and endocrine function, yet optimal planning strategies remain underexplored. Objective: To compare dosimetric outcomes, efficiency, and plan quality between coplanar (C-VMAT) and non-coplanar VMAT (NC-VMAT) using two treatment planning systems (TPS): Monaco (Elekta Infinity) and uRTTPOIS (uRT-linac 506c). Methods: Four plans (MC-CVMAT, MC-NCVMAT, UT-CVMAT, UT-NCVMAT) were designed for 20 cervical cancer patients with bilateral ovarian transposition. Dosimetric parameters (PTV D0.03 cc, Dmean, HI, CI; ovarian Dmax/Dmean), plan complexity (modulation complexity score, MCS), delivery efficiency (beam-on time, BOT; monitor units, MU), and plan quality metrics (PQM) were evaluated. Statistical analysis included ANOVA and non-parametric tests. Results: All plans met clinical constraints. NC-VMAT showed marginally lower PTV D0.03 cc (48.45 f 0.48 Gy vs. 48.71 f 0.38 Gy, p = 0.063) and improved bowel bag Dmean (20.0 f 2.3 Gy vs. 24.1 f 3.5 Gy, p < 0.001) but increased BOT (114s vs. 86s for uRT-TPOIS; 233s vs. 193s for Monaco). C-VMAT demonstrated superior efficiency (optimization time: 15-40 min) and lower complexity (MCS = 0.335 vs. 0.222 for NC-VMAT). uRT-TPOIS achieved better CI (0.89 vs. 0.87, p < 0.001) and bowel sparing, while Monaco reduced bladder/rectal D2cc (47.27 f 0.39 Gy vs. 47.52 f 0.32 Gy, p < 0.05). No significant differences in PQM were observed. Conclusion: C-VMAT is preferred for OS-CRT due to balanced efficiency and dosimetry. uRT-TPOIS excels in rapid optimization and image guidance, whereas Monaco offers superior OAR protection. These findings provide clinically actionable insights for ovarian function preservation.

This study aims to explore the prognostic value of regionally modulated radiomics for patients with head and neck cancer (HNC) in positron emission tomography/computed tomography (PET/CT) imaging. The dataset included 224 HNC patients who underwent PET/CT imaging at five different centers. The primary tumor was manually contoured by experienced radiologists. For introducing regionally modulated radiomics, we developed four fuzzy masks by applying Gaussian filter, and four peritumor-included masks by applying morphological operations. For each patient, a total of 326 radiomic features were extracted from each of nine masks. Multivariate Cox proportional hazards model with ensemble strategy was adopted to construct classical, fuzzy, and peritumoral based prognostic models, respectively, for predicting progression-free survival. ComBat harmonization was applied to adjust for multicenter variability. A consistent modelling approach was employed to ensure the independence and comparability of these models. The models were evaluated by C-index, log-rank test, and the area under the time-dependent ROC curve (tAUC). The fuzzy radiomics model applied with 5 mm FWHM of Gaussian filter demonstrated superior performance compared to classical radiomics model (Testing C-index, 0.735 vs. 0.685; log-rank test, p < 0.007 vs. p < 0.035). Peritumoral radiomics models showed slightly improved performance compared to classical radiomics model (Testing C-index, 0.727 vs. 0.685; log-rank test, p < 0.014 vs. p < 0.035). The tAUC demonstrated consistent findings with the C-index. The harmonization strategy showed further improved performance for both fuzzy and peritumoral models. These results showed that regionally modulated radiomics analysis was superior for estimating prognosis in this multicenter HNC cohort when compared to classical radiomics. This demonstrated the potentially prognostic values by considering regional variations in radiomics analysis.

The purpose of this study is to develop an electronic portal imaging device‐based multi‐leaf collimator calibration procedure using log files. Picket fence fields with 2–14 mm nominal strip widths were performed and normalized by open field. Normalized pixel intensity profiles along the direction of leaf motion for each leaf pair were taken. Three independent algorithms and an integration method derived from them were developed according to the valley value, valley area, full‐width half‐maximum (FWHM) of the profile, and the abutment width of the leaf pairs obtained from the log files. Three data processing schemes (Scheme A, Scheme B, and Scheme C) were performed based on different data processing methods. To test the usefulness and robustness of the algorithm, the known leaf position errors along the direction of perpendicular leaf motion via the treatment planning system were introduced in the picket fence field with nominal 5, 8, and 11 mm. Algorithm tests were performed every 2 weeks over 4 months. According to the log files, about 17.628% and 1.060% of the leaves had position errors beyond ± 0.1 and ± 0.2 mm, respectively. The absolute position errors of the algorithm tests for different data schemes were 0.062 ± 0.067 (Scheme A), 0.041 ± 0.045 (Scheme B), and 0.037 ± 0.043 (Scheme C). The absolute position errors of the algorithms developed by Scheme C were 0.054 ± 0.063 (valley depth method), 0.040 ± 0.038 (valley area method), 0.031 ± 0.031 (FWHM method), and 0.021 ± 0.024 (integrated method). For the efficiency and robustness test of the algorithm, the absolute position errors of the integration method of Scheme C were 0.020 ± 0.024 (5 mm), 0.024 ± 0.026 (8 mm), and 0.018 ± 0.024 (11 mm). Different data processing schemes could affect the accuracy of the developed algorithms. The integration method could integrate the benefits of each algorithm, which improved the level of robustness and accuracy of the algorithm. The integration method can perform multi‐leaf collimator (MLC) quality assurance with an accuracy of 0.1 mm. This method is simple, effective, robust, quantitative, and can detect a wide range of MLC leaf position errors.

Background and Purpose Artificial intelligence (AI) is a technique which tries to think like humans and mimic human behaviors. It has been considered as an alternative in a lot of human-dependent steps in radiotherapy (RT), since the human participation is a principal uncertainty source in RT. The aim of this work is to provide a systematic summary of the current literature on AI application for RT, and to clarify its role for RT practice in terms of clinical views. Materials and Methods A systematic literature search of PubMed and Google Scholar was performed to identify original articles involving the AI applications in RT from the inception to 2022. Studies were included if they reported original data and explored the clinical applications of AI in RT. Results The selected studies were categorized into three aspects of RT: organ and lesion segmentation, treatment planning and quality assurance. For each aspect, this review discussed how these AI tools could be involved in the RT protocol. Conclusions Our study revealed that AI was a potential alternative for the human-dependent steps in the complex process of RT.

Radiation therapy (radiotherapy) is one of the important methods for comprehensive treatment of breast cancer. Radiotherapy after breast conserving surgery for early breast cancer can not only achieve local control rate and long-term survival rate similar to total mastectomy, but also meet patients' pursuit of higher quality of life. With the development of intensity modulated radiotherapy (IMRT), volumetric modulated arc therapy (VMAT), helical tomotherapy (HT), and other advanced radiotherapy technique, the consistency of patient position fixation during radiotherapy is the key to ensure the implementation of accurate radiotherapy. Due to the special and high activity of breast organs, there is no unified fixation method for breast conserving postoperative radiotherapy. This article reviews the clinical application and research progress of various accessible supine fixation techniques in early breast cancer postoperative radiotherapy in recent years. This paper analyzes the clinical application method and clinical application effect of various techniques, compares the advantages and disadvantages of each technology. It is found that breast bracket is the most widely used for classical breast cancer radiotherapy. In any fixation technique, it is still a practical problem for the clinic to solve the problem of the normal location of the breast activity and the consistency of the radiation. It is recommended that the position of the supposition fixation technique should be selected according to the patient's BMI, breast size and target area.

Medical physicists play an important role in the delivery of radiotherapy. Compared with China′s mainland, Hong Kong has established a more mature training mode and a more complete management system for medical physics talents. In this article, the authors introduced the current state of medical physics talent training, as well as the recruitment, certification and promotion of medical physicist in Hong Kong by querying the official websites of medical physics organizations, reviewing related literature and interviewing senior medical physicists in Hong Kong. The authors also analyzed the shortcomings in the construction of medical physics talent system in China′s mainland and made valuable suggestions.

Objective:To study the improvement of normal tissue region of interest (ROI) segmentation based on clustering-based multi-Atlas segmentation method, thereby achieving better delineation of organs at risk.Methods:CT images of 100 patients with cervical cancer who had completed treatment in Zhejiang Cancer Hospital during 2019-2020 were selected as the Atlas database. According to the volume characteristic parameters of the organs at risk (bladder, rectum and outer contour), the Atlas database was divided into several subsets by k-means clustering algorithm. The image to be segmented was matched to the corresponding Atlas library for multi-Atlas segmentation. The dice similarity coefficient (DSC) was used to evaluate the segmentation results.Results:Using 30 patients as the test set, the sub-Atlas generated by different clustering methods were compared for the improvement of image segmentation results. Compared with general multi-Atlas segmentation methods, clustering-based multi-Atlas segmentation method significantly improve the segmentation accuracy for the bladder (DSC=0.83±0.09 vs. 0.69±0.15, P<0.001) and the rectum (0.7±0.07 vs. 0.56±0.16, P<0.001), but no statistical significance was observed for left and right femoral head (0.92±0.04, 0.91±0.02) and bone marrow (0.91±0.06). The average segmentation time of clustering-based multi-Atlas segmentation method was shorter than that of the general multi-Atlas segmentation method (2.7 min vs. 6.3 min). Conclusion:The clustering-based multi-Atlas segmentation method can not only reduce the number of Atlas images registered with the image to be segmented, but also can be expected to improve the segmentation effect and obtain higher accuracy.

Objective:Topredict the three-dimensional dose distribution of regions of interest (ROI) with brachytherapy for cervical cancer based on U-Net fully convolutional network, and evaluate the accuracy of prediction model.Methods:First, 100 cases of cervical cancer intracavity combined with interstitial implantation were selected as the entire research data set, and divided into the training set ( n=72), validation set ( n=8), and test set ( n=20). Then the U-Net was used to construct two models based on whether the uterine tandem and the implantation needles were included as the distinguishing factors. Finally, dose distribution of 20 cases in the test set were predicted using the trained model, and comparative analysis was performed. The performance of the model was jointly evaluated by , and the mean absolute deviation (MAD). Results:Compared with the model without the uterine tandem and the implantation needles, the of the rectum was increased by (16.83±1.82) cGy ( P<0.05), and the or of the other ROI were not different significantly (all P>0.05). The MAD of the high-risk clinical target volume, rectum, sigmoid, small bowel, and bladder was increased by (11.96±3.78) cGy, (11.43±0.54) cGy, (24.08±1.65) cGy, (17.04±7.17) cGy and (9.52±4.35) cGy, respectively (all P<0.05). The MAD of the intermediate-risk clinical target volume was decreased by (120.85±29.78) cGy ( P<0.05). The mean value of MAD for all ROI was decreased by (7.8±53) cGy ( P<0.05), which was closer to the actual plan. Conclusions:U-Net fully convolutional network can be used to predict three-dimensional dose distribution of patients with cervical cancer undergoing brachytherapy. Combining the uterine tube with the implantation needles as the input parameters yields more accurate predictions than a single use of the ROI structure as the input.

Neural-network methods have been widely used for the prediction of dose distributions in radiotherapy. However, the prediction accuracy of existing methods may be degraded by the problem of dose imbalance. In this work, a new loss function is proposed to alleviate the dose imbalance and achieve more accurate prediction results. The U-Net architecture was employed to build a prediction model. Our study involved a total of 110 patients with left-breast cancer, who were previously treated by volumetric-modulated arc radiotherapy. The patient dataset was divided into training and test subsets of 100 and 10 cases, respectively. We proposed a novel ‘sharp loss’ function, and a parameter γ was used to adjust the loss properties. The mean square error (MSE) loss and the sharp loss with different γ values were tested and compared using the Wilcoxon signed-rank test. The sharp loss achieved superior dose prediction results compared to those of the MSE loss. The best performance with the MSE loss and the sharp loss was obtained when the parameter γ was set to 100. Specifically, the mean absolute difference values for the planning target volume were 318.87 ± 30.23 for the MSE loss versus 144.15 ± 16.27 for the sharp loss with γ = 100 (p < 0.05). The corresponding values for the ipsilateral lung, the heart, the contralateral lung, and the spinal cord were 278.99 ± 51.68 versus 198.75 ± 61.38 (p < 0.05), 216.99 ± 44.13 versus 144.86 ± 43.98 (p < 0.05), 125.96 ± 66.76 versus 111.86 ± 47.19 (p > 0.05), and 194.30 ± 14.51 versus 168.58 ± 25.97 (p < 0.05), respectively. The sharp loss function could significantly improve the accuracy of radiotherapy dose prediction.

随着国内TOMO技术的推广应用和相关质控指南的相继出台,目前还没有较为完善的质控指南解读和质控项目操作规范的研究发布,TOMO质控技术实施的同质化和推广受到了一定影响,更缺少适合国内临床需求的优化质控方案.本研究对《AAPM TG148号报告》、WS531-2017《螺旋断层治疗装置质量控制检测规范》和NCC/T-RT003-2019《螺旋断层放疗系统的质量保证》这3种TOMO质控相关指南进行分析及横向比较.文献搜集分析了近5年国内外有关常规直线加速器主流质控设备及新型质控设备在TOMO质控中的应用,从而提出一套操作性更强、效率更高的质控方案.完善的质控检测操作规范有利于相关从业人员对TOMO质控技术的学习和掌握,合理的质控项目设置更有利于质控的高效实施,三维及更新型质控设备的应用会节省质控费用并大幅度提升质控效率.

Fully convolutional networks were developed for predicting optimal dose distributions for patients with left-sided breast cancer and compared the prediction accuracy between two-dimensional and three-dimensional networks. Sixty cases treated with volumetric modulated arc radiotherapy were analyzed. Among them, 50 cases were randomly chosen to conform the training set, and the remaining 10 were to construct the test set. Two U-Net fully convolutional networks predicted the dose distributions, with two-dimensional and three-dimensional convolution kernels, respectively. Computed tomography images, delineated regions of interest, or their combination were considered as input data. The accuracy of predicted results was evaluated against the clinical dose. Most types of input data retrieved a similar dose to the ground truth for organs at risk ( p > 0.05). Overall, the two-dimensional model had higher performance than the three-dimensional model ( p < 0.05). Moreover, the two-dimensional region of interest input provided the best prediction results regarding the planning target volume mean percentage difference (2.40 ± 0.18%), heart mean percentage difference (4.28 ± 2.02%), and the gamma index at 80% of the prescription dose are with tolerances of 3 mm and 3% (0.85 ± 0.03), whereas the two-dimensional combined input provided the best prediction regarding ipsilateral lung mean percentage difference (4.16 ± 1.48%), lung mean percentage difference (2.41 ± 0.95%), spinal cord mean percentage difference (0.67 ± 0.40%), and 80% Dice similarity coefficient (0.94 ± 0.01). Statistically, the two-dimensional combined inputs achieved higher prediction accuracy regarding 80% Dice similarity coefficient than the two-dimensional region of interest input (0.94 ± 0.01 vs 0.92 ± 0.01, p < 0.05). The two-dimensional data model retrieves higher performance than its three-dimensional counterpart for dose prediction, especially when using region of interest and combined inputs.

BACKGROUND:Image-guided adaptive brachytherapy shows the ability to deliver high doses to tumors while sparing normal tissues. However, interfraction dose delivery introduces uncertainties to high dose estimation, which relates to normal tissue toxicity. The purpose of this study was to investigate the high-dose regions of two applicator approaches in brachytherapy.METHOD:For 32 cervical cancer patients, the CT images from each fraction were wrapped to a reference image, and the displacement vector field (DVF) was calculated with a hybrid intensity-based deformable registration algorithm. The fractional dose was then accumulated to calculate the position and the overlap of high dose (D2cc) during multiple fractions.RESULT:The overall Dice similarity coefficient (DSC) of the deformation algorithm for the bladder and the rectum was (0.97 and 0.91). No significant difference was observed between the two applicators. However, the location of the intracavitary brachytherapy (ICBT) high-dose region was relatively concentrated. The overlap volume of bladder and rectum D2cc was 0.42 and 0.71, respectively, which was higher than that of interstitial brachytherapy (ISBT) (0.26 and 0.31). The cumulative dose was overestimated in ISBT cases when using the GEC-recommended method. The ratio of bladder and rectum D2cc to the GEC method was 0.99 and 1, respectively, which was higher than that of the ISBT method (0.96 and 0.94).CONCLUSION:High-dose regions for brachytherapy based on different applicator types were different. The 3D-printed ICBT has better high-dose region consistency than freehand ISBT and hence is more predictable.