Objective To construct and investigate the multi-leaf collimator (MLC) fault prediction model of Varian NovalisTx medical linear accelerator based on BP neural network. Methods The MLC fault data applied in clinical trial for 18 months were collected and analyzed. The total use time of accelerator, the quantity of patients per month, average daily working hours of accelerator, volume of RapidArc plans and time interval between accelerator maintenance were used as the input factors and the prediction of MLC fault frequency was considered as the output result. The BP neural network model of MLC fault prediction was realized by AMORE package of R language and the simulation results were validated. Results The model contained 3 layers of network to realize the input-output switch. There were 5 nodes in the input layer,13 nodes in the hide layer and 1 node in the output layer, respectively. The transfer function from the input layer to the hide layer selected the tansig function and purelin function was used from the hide layer to the output layer. The maximum time of training was pre-set as 150 in the designed model. Actually, 111 times of training were performed. The pre-set error was 3% and the actual error was 2.7%, which indicated good convergence. The simulation results of MLC fault applied in clinical trial for 18 months were similar to the actual data. Conclusions The BP neural network model realized by R language of MLC fault prediction can describe the mapping relationship between fault factors and fault frequency, which provides references for the understanding of accelerator fault and management of spare parts inventory.

Objective To explore the importance of head fixation in chest wall field combined with supraclavicular field radiotherapy for breast cancer by comparing the displacement error and dosimetric differences caused by multi-functional body board and breast bracket. Methods Thirty patients with breast cancer were randomly divided into groups A and B. In group A, patients were fixed with multi-functional body board and head thermoplastic film. In group B, patients were fixed with traditional breast brackets. Each patient received CBCT scan before and after radiotherapy. Both setup errors and intra-fractional displacements in the x-,y-and z-axis, V100 and V95 were calculated. Statistical analyses were performed using the independent sample t-test. Results The displacement errors in groups A and B before and after radiotherapy were (1.24±0.42),(1.71±0.61) and (2.25±1.04) mm vs.(3.67±2.05),(3.78±1.74),(4.65±2.66) mm in the x-,y-and z-axis, respectively (P=0.033,0.027,0.020).The intra-fractional displacements in groups A and B were (1.10±0.66),(1.13±0.59),(1.11±0.62) mm vs.(2.48±0.88),(2.21±0.98),(3.53±2.01) mm in the x-,y-and z-axis, respectively (P=0.030,0.021,0.013).The V100 in groups A and B were (94.27±3.20)% and (99.08±0.60)%(P=0.065),and (89.48±4.70)% and (96.53±2.50)% for V95(P=0.002),respectively. Conclusion The risk of displacement error is significantly reduced using multi-functional body board, which enhances the accuracy of radiation dose in chest wall and supraclavicular fields of breast cancer patients.

Objective To analyze the correlation between treatment time and radiotherapy plan of deep inspiration breath-hold (DIBH) technique for the whole breast irradiation (WBI) in the left breast cancer after breast-conserving surgery,verify the inter-fractional reproducibility of radiotherapy,observe the heart location and dosimetric changes and calculate the effect of DIBH upon the WBI setup error after the surgery. Methods We prospectively enrolled 15 patients with left breast cancer undergoing WBI after breast-conserving surgery,who met the requirement of DIBH.Treatment time was recorded,its correlation with the number of field and monitor unit was analyzed. Inter-fractional setup errors and PTV delineation were calculated using cone beam CT (CBCT).The accuracy of the position and dose of the heart during radiotherapy was verified by the imaging fusion of CBCT and CT images. The variables among groups were analyzed by non-parametric Firedman test. Results The average treatment time of DIBH radiotherapy was 4.6 minutes. The treatment time was correlated with the maximal and total number of sub-fields and total monitor units. During DIBH treatment,the mean cardiac displacement volume was 19.1 cm³(3.8%).The mean cardiac dose difference between CBCT and planning CT was 5.1 cGy,and there was no significant difference in the heart V5-V30.The mean inter-fractional system setup error (Σ) and random setup error (σ) in the left-right (x),superior-inferior (y) and anterior-posterior (z) direction were Σ_x 1.9 mm,Σ_y 2.1 mm,Σ_z 2.0 mm,σ_x1.3 mm,σ_y 1.3 mm,σ_z 1.4 mm,respectively. The corresponding minimal margins for setup error were 5.7 mm,6.2 mm and 6.0 mm,respectively. Conclusion DIBH for WBI after breast-conserving surgery does not significantly prolong the treatment time. Treatment time is related to treatment plan. DIBH yields high inter-fractional reproducibility and protects the heart.

While emphasizing"Precision Medicine" nowadays, comprehending the specificity of patients and pathology is the key to achieving the precision diagnosis and treatment. Radiomics is a high-throughput quantitative analysis that combines the quantitative features from the region of interest on medical image and the biology and heterogeneity of tumor. It provides a non-invasive, convenient, dynamic, and quantitative method to collect the patient′s specific features of pathology and gene. Radiomics holds promise for the precision diagnosis and treatment of brain tumor. It can be used for molecular pathology diagnosis, definition of tumor boundaries, prognosis, prediction of complications, and so on. It helps to develop individualized measures for the prevention, diagnosis, treatment, and prognostic monitoring based on their disease features.

The development of a treatment plan is one of the critical steps in the three-dimensional (3D) brachytherapy for cervical cancer. This article reviews more than 40 papers on the treatment plan design of high-dose-rate brachytherapy for cervical cancer and summarizes the principles and methods for developing a treatment plan of 3D brachytherapy. There are many difficult points in 3D brachytherapy. The doses delivered to tumor and normal tissues need to be balanced by considering many different factors under different conditions. In addition, there are still some uncertain factors for developing the treatment plan of 3D brachytherapy, which needs further exploration and research in the future. It can provide some references for colleagues in 3D brachytherapy for cervical cancer.

The treatment guidelines based on evidence-based medical evidence provide appropriate treatment strategies for clinical oncologists. Currently, many treatment guidelines for primary liver cancer have been published and updated by many organizations from different countries, including Barcelona Clinic Liver Cancer (BCLC), European Association for the Study of the Liver and European Organization for Research and Treatment of Cancer (EASL-EORTC), American Association for the Study of Liver Diseases (AASLD), National Comprehensive Cancer Network (NCCN), Asia-Pacific Primary Liver Cancer Expert (APPLE), Korean Liver Cancer Study Group and National Cancer Center (KLCSG-NCC), and Chinese Society for Therapeutic Radiology and Oncology (CSTRO), Chinese Medical Association. Although radiotherapy is commonly used in clinical practice, some guidelines do not accept it as a standard treatment strategy. In this article, we review the current treatment guidelines and discuss the current status and future prospects of radiotherapy in the management of primary liver cancer.