scholarly journals Use of artificial neural network for pretreatment verification of intensity modulation radiation therapy fields

2019 ◽  
Vol 92 (1102) ◽  
pp. 20190355 ◽  
Author(s):  
Seied Rabie Mahdavi ◽  
Asieh Tavakol ◽  
Mastaneh Sanei ◽  
Seyed Hadi Molana ◽  
Farshid Arbabi ◽  
...  
Keyword(s):  
Neural Network ◽  
High Speed ◽  
Pass Rate ◽  
Planning System ◽  
Treatment Planning System ◽  
Two Dimensional ◽  
Dose Verification ◽  
Quality Assurance Procedure ◽  
Imaging Device ◽  
Artificial Neural

Objective: The accuracy of dose delivery for intensity modulated radiotherapy (IMRT) treatments should be determined by an accurate quality assurance procedure. In this work, we used artificial neural networks (ANNs) as an application for the pre-treatment dose verification of IMRT fields based two-dimensional-fluence maps acquired by an electronic portal imaging device (EPID). Methods: The ANN must be trained and validated before use for the pretreatment dose verification. Hence, 60 EPID fluence maps of the anteroposterior prostate and nasopharynx IMRT fields were used as an input for the ANN (feed forward type), and a dose map of those fluence maps that were acquired by two-dimensional Array Seven29TM as an output for the ANN. Results: After the training and validation of the neural network, the analysis of 20 IMRT anteroposterior fields showed excellent agreement between the ANN output and the dose map predicted by the treatment planning system. The average overall global and local γ field pass rate was greater than 90% for the prostate and nasopharynx fields, with the 2 mm/3% criteria. Conclusion: The results indicated that the ANN can be used as a fast and powerful tool for pretreatment dose verification, based on an EPID fluence map. Advances in knowledge: In this study, ANN is proposed for EPID based dose validation of IMRT fields. The proposed method has good accuracy and high speed in response to problems. Neural network show to be low price and precise method for IMRT fields verification

Temperature Rise Prediction of Oil-Air Lubricated Angular Contact Ball Bearings Using Artificial Neural Network

2019 ◽  
Vol 12 (3) ◽  
pp. 248-261
Author(s):  
Baomin Wang ◽  
Xiao Chang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Temperature Rise ◽  
High Speed ◽  
Ball Bearing ◽  
Influence Factors ◽  
Ball Bearings ◽  
Ann Model ◽  
Angular Contact Ball Bearing ◽  
Artificial Neural

Background: Angular contact ball bearing is an important component of many high-speed rotating mechanical systems. Oil-air lubrication makes it possible for angular contact ball bearing to operate at high speed. So the lubrication state of angular contact ball bearing directly affects the performance of the mechanical systems. However, as bearing rotation speed increases, the temperature rise is still the dominant limiting factor for improving the performance and service life of angular contact ball bearings. Therefore, it is very necessary to predict the temperature rise of angular contact ball bearings lubricated with oil-air. Objective: The purpose of this study is to provide an overview of temperature calculation of bearing from many studies and patents, and propose a new prediction method for temperature rise of angular contact ball bearing. Methods: Based on the artificial neural network and genetic algorithm, a new prediction methodology for bearings temperature rise was proposed which capitalizes on the notion that the temperature rise of oil-air lubricated angular contact ball bearing is generally coupling. The influence factors of temperature rise in high-speed angular contact ball bearings were analyzed through grey relational analysis, and the key influence factors are determined. Combined with Genetic Algorithm (GA), the Artificial Neural Network (ANN) model based on these key influence factors was built up, two groups of experimental data were used to train and validate the ANN model. Results: Compared with the ANN model, the ANN-GA model has shorter training time, higher accuracy and better stability, the output of ANN-GA model shows a good agreement with the experimental data, above 92% of bearing temperature rise under varying conditions can be predicted using the ANNGA model. Conclusion: A new method was proposed to predict the temperature rise of oil-air lubricated angular contact ball bearings based on the artificial neural network and genetic algorithm. The results show that the prediction model has good accuracy, stability and robustness.

Forecasting of Cutting Forces in Dental Adjustment of Ceramic Prostheses Using an Artificial Neural Network

2010 ◽  
Vol 152-153 ◽  
pp. 1687-1690
Author(s):  
Jian Hui Peng ◽  
Xiao Fei Song ◽  
Ling Yin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Cutting Forces ◽  
High Speed ◽  
Cutting Process ◽  
Computer Assisted ◽  
Ann Model ◽  
Operational Parameters ◽  
Artificial Neural

Intraoral adjustment of ceramic prostheses involving cutting process is a central procedure in restorative dentistry because the quality of ceramic prostheses depends on the cutting process. In this paper, an artificial neural network (ANN) model was developed for the first time to forecast the dynamic forces in dental cutting process as functions of clinical operational parameters. The predicted force values were compared with the measured values in in vitro dental cutting of porcelain prostheses obtained using a novel two-degrees-of-freedom computer-assisted testing apparatus with a high-speed dental handpiece and diamond burs. The results indicate that there existed nonlinear relationships between the cutting forces and clinical operational parameters. It is found that the ANN-forecasted forces were in good agreement with the experiment-measured values. This indicates that the established ANN model can provide insights into the force-related process assessment and forecast for clinical dental cutting of ceramic prostheses.

Quality assurance of linear accelerator: a comprehensive system using electronic portal imaging device

2018 ◽  
Vol 18 (02) ◽  
pp. 138-149
Author(s):  
P. Niyas ◽  
K. K. Abdullah ◽  
M. P. Noufal ◽  
R. Vysakh
Keyword(s):  
Quality Assurance ◽  
Linear Accelerator ◽  
Planning System ◽  
Treatment Planning System ◽  
Patient Specific ◽  
Array Detector ◽  
Electronic Portal Imaging Device ◽  
Imaging Device ◽  
Portal Imaging ◽  
Electronic Portal Imaging

AbstractAimThe Electronic Portal Imaging Device (EPID), primarily used for patient setup during radiotherapy sessions is also used for dosimetric measurements. In the present study, the feasibility of EPID in both machine and patient-specific quality assurance (QA) are investigated. We have developed a comprehensive software tool for effective utilisation of EPID in our institutional QA protocol.Materials and methodsPortal Vision aS1000, amorphous silicon portal detector attached to Clinac iX—Linear Accelerator (LINAC) was used to measure daily profile and output constancy, various Multi-Leaf Collimator (MLC) checks and patient plan verification. Different QA plans were generated with the help of Eclipse Treatment Planning System (TPS) and MLC shaper software. The indigenously developed MATLAB programs were used for image analysis. Flatness, symmetry, output constancy, Field Width at Half Maximum (FWHM) and fluence comparison were studied from images obtained from TPS and EPID dosimetry.ResultsThe 3 years institutional data of profile constancy and patient-specific QA measured using EPID were found within the acceptable limits. The daily output of photon beam correlated with the output obtained through solid phantom measurements. The Pearson correlation coefficients are 0.941 (p = 0.0001), 0.888 (p = 0.0188) and 0.917 (p = 0.0007) for the years of 2014, 2015 and 2016, respectively. The accuracy of MLC for shaping complex treatment fields was studied in terms of FWHM at different portions of various fields, showed good agreement between TPS-generated and EPID-measured MLC positions. The comparison of selected patient plans in EPID with an independent 2D array detector system showed statistically significant correlation between these two systems. Percentage difference between TPS computed and EPID measured fluence maps calculated for number of patients using MATLAB code also exhibited the validity of those plans for treatment.

An Object Detection Method for Sonar Image Using Fuzzy Artificial Neural Network

2011 ◽  
Vol 58-60 ◽  
pp. 1824-1829
Author(s):  
Xi Tao Zheng ◽  
Shi Ming Wang ◽  
Yong Wei Zhang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Grid Data ◽  
Imaging Device ◽  
Sonar Image ◽  
Additional Processing ◽  
Sonar Imaging ◽  
Multiple Levels ◽  
Artificial Neural ◽  
Matlab Programming

A method to efficiently identify object from its background noise for a sonar picture using fuzzy artificial neural network is introduced. The sonar images are from a high precision array sonar imaging device. The ability to set focus to a certain range of interest will produce a well lamented grayscale picture around the focus distance. The intelligent window over the digital picture based on neural network feedback is used to partition the picture into different levels of grid and the grid data is treated as the input for the network. Multiple levels of gridding are applied corresponding to the layers of neural network. Samples are provided for training to get the focus related threshold values. The method is faster and can be used for the pre-identification of object from sonar image so additional processing can be called for shape recognition. Matlab programming is used for data processing.

Sign in / Sign up

Export Citation Format

Share Document