Search

Introduction: Phantom is an object that can be used to investigate the accuracy of radiation dose delivered to patients. Phantom is usually produced from the combination of the silicone rubber as a matrix and glycerin as a filler to form a composite for the replacement of the human soft tissue. The composite is imaged using computed tomography (CT) simulator for the determination of the attenuation coefficient. Material and Methods: The Phantom in the current study has been synthesized from silicone rubber with and without the addition 10% and 20% of glycerin. The type of silicone rubber in this study was Room Temperature Vulcanized (RTV) 52 with blue catalyst by a ratio of 100:5 (wt%). Samples were scanned using CT simulator to obtain the images and then exported to the Eclipse treatment planning system for analysis. The region of interest (ROI) was at the center of an area of 50×50 pixels to determine the CT number. Results: The ROI results for the sample without and with the addition of glycerin 10% and 20% resulted in the CT values of 287.4, 280.5, and 225.2 HU, respectively, which were within the ROI range of the human soft tissue. The attenuation coefficients of the 3 samples were 0.239, 0.238±0.001, and 0.233±0.001 cm-1 for no glycerin, glycerin 10%, and glycerin 20%, respectively. The values of the half-value layer were 2.902±0.001, 2.911±0.001, and 2.980± 0.001 cm for phantom with no glycerin, glycerin 10%, and glycerin 20%, respectively. Conclusion: Phantoms in the current study were indicative of high potentials as an object of research for radiotherapy and educational purposes. Moreover, the composite with glycerin 20% could be the best surrogate of tissue in order to study human liver.

Introduction: Phantom is an object that can be used to investigate the accuracy of radiation dose delivered to patients. Phantom is usually produced from the combination of the silicone rubber as a matrix and glycerin as a filler to form a composite for the replacement of the human soft tissue. The composite is imaged using computed tomography (CT) simulator for the determination of the attenuation coefficient. Material and Methods: The Phantom in the current study has been synthesized from silicone rubber with and without the addition 10% and 20% of glycerin. The type of silicone rubber in this study was Room Temperature Vulcanized (RTV) 52 with blue catalyst by a ratio of 100:5 (wt%). Samples were scanned using CT simulator to obtain the images and then exported to the Eclipse treatment planning system for analysis. The region of interest (ROI) was at the center of an area of 50×50 pixels to determine the CT number. Results: The ROI results for the sample without and with the addition of glycerin 10% and 20% resulted in the CT values of 287.4, 280.5, and 225.2 HU, respectively, which were within the ROI range of the human soft tissue. The attenuation coefficients of the 3 samples were 0.239, 0.238-0.001, and 0.233-0.001 cm-1 for no glycerin, glycerin 10%, and glycerin 20%, respectively. The values of the half-value layer were 2.902-0.001, 2.911-0.001, and 2.980-0.001 cm for phantom with no glycerin, glycerin 10%, and glycerin 20%, respectively. Conclusion: Phantoms in the current study were indicative of high potentials as an object of research for radiotherapy and educational purposes. Moreover, the composite with glycerin 20% could be the best surrogate of tissue in order to study human liver. [ABSTRACT FROM AUTHOR]

The segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions, and non-rigid geometrical features. To address these difficulties, we introduce a deep Q network (DQN) driven approach with deformable U-Net to accurately segment the pancreas by explicitly interacting with contextual information and extract anisotropic features from pancreas. The DQN-based model learns a context-adaptive localization policy to produce a visually tightened and precise localization bounding box of the pancreas. Furthermore, deformable U-Net captures geometry-aware information of pancreas by learning geometrically deformable filters for feature extraction. The experiments on NIH dataset validate the effectiveness of the proposed framework in pancreas segmentation. [ABSTRACT FROM AUTHOR]

This paper refers to the cases of the use of Artificial Neural Networks and Convolutional Neural Networks in impedance tomography. Machine Learning methods can be used to teach computers different technical problems. The efficient use of conventional artificial neural networks in tomography is possible able to effectively visualize objects. The first step of implementation Deep Learning methods in Electrical Impedance Tomography was performed in this work.

The paper presents considerations on motion of a group of air bubbles. Special attention has been paid to interactions between them. The author presents the test stand structure and the idea of image tomograph used for measurements of bubble motion trajectories. The results of measurements have been presented in a three-dimensional space, and next characteristic behaviours of the moving bubbles were analyzed. Some basic mechanisms of the gas bubble division have been classified. [ABSTRACT FROM AUTHOR]