• Journal of Industrial Technology
• /
• v.26 no.B
• /
• pp.221-226
• /
• 2006

Electrical impedance tomography (EIT) is a technique for determining the electrical conductivity and permittivity distribution within the interior of a body from measurements made on its surface. One recent application area of the EIT is the detection of breast cancer by imaging the conductivity and permittivity distribution inside the breast. The present "gold standard" for breast cancer detection is X-ray mammography, and it is desirable that EIT and X-ray mammography use the same geometry. This paper presents a forward model of a simplified mammography geometry for EIT imaging. The mammography geometry is modeled as a rectangular box with electrode arrays on the top and bottom planes. A forward model for the electrical impedance imaging problem is derived for a homogeneous conductivity distribution and Validated by experiment using a phantom tank.

• Journal of Industrial Technology
• /
• v.27 no.B
• /
• pp.91-96
• /
• 2007

Electrical impedance tomography (EIT) is a technique for determining the electrical conductivity and permittivity distribution within the interior of a body from measurements made on its surface. One recent application area of the EIT is the detection of breast cancer by imaging the conductivity and permittivity distribution inside the breast. The present standard for breast cancer detection is X-ray mammography, and it is desirable that EIT and X-ray mammography use the same geometry. A forward model of a simplified mammography geometry for EIT imaging was proposed earlier. In this paper, we propose an iterative algorithm for computing the current pattern that will be applied to the electrodes. The current pattern applied to the electrodes influences the voltages measured on the electrodes. Since the measured voltage data is going to be used in the impedance imaging computation, it is desirable to apply currents that result in the largest possible voltage signal. We compute the eigenfunctions for a homogenous medium that will be applied as current patterns to the electrodes. The algorithm for the computation of the eigenfunctions is presented. The convergence of the algorithm is shown by computing the eigencurrent of the simplified mammography geometry.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.39-48
• /
• 2023

Breast cancer screening makes extensive utilization of mammography. Even so, there has been a lot of debate with regards to this application's starting age as well as screening interval. The deep learning technique of transfer learning is employed for transferring the knowledge learnt from the source tasks to the target tasks. For the resolution of real-world problems, deep neural networks have demonstrated superior performance in comparison with the standard machine learning algorithms. The architecture of the deep neural networks has to be defined by taking into account the problem domain knowledge. Normally, this technique will consume a lot of time as well as computational resources. This work evaluated the efficacy of the deep learning neural network like Visual Geometry Group Network (VGG Net) Residual Network (Res Net), as well as inception network for classifying the mammograms. This work proposed optimization of ResNet with Teaching Learning Based Optimization (TLBO) algorithm's in order to predict breast cancers by means of mammogram images. The proposed TLBO-ResNet, an optimized ResNet with faster convergence ability when compared with other evolutionary methods for mammogram classification.

• Journal of radiological science and technology
• /
• v.35 no.4
• /
• pp.345-352
• /
• 2012

As the breast cancer rate is increasing fast in Korean women, people pay more attention to mammography and number of mammography have been increasing dramatically over the last few years. Mammography is the only means to diagnose breast cancer early, but harms caused by radiation exposure shouldn't be overlooked. Therefore, it is important to calculate the radiation dose being absorbed into the breast tissue during the process of mammography for a protective measure against radiation exposure. Because it is impossible to directly measure the radiation dose being absorbed into the human body, statistical calculation methods are commonly used, and most of them are supposed to simulate the interaction between radiation and matter by describing the human body internal structure with anthropomorphic phantoms. However, a simulation using Geant4 Code of Monte Carlo Method, which is well-known as most accurate in calculating the absorbed dose inside the human body, helps calculate exact dose by recreating the anatomical human body structure as it is through the DICOM file of CT. To calculate the absorbed dose in the breast tissue, therefore, this study carried out a simulation using Geant4 Code, and by using the DICOM converted file provided by Geant4, this study changed the human body structure expressed on the CT image data into geometry needed for this simulation. Besides, this study attempted to verify if the dose calculation of Geant4 interlocking with the DICOM file is useful, by comparing the calculated dose provided by this simulation and the measured dose provided by the PTW ion chamber. As a result, under the condition of 28kVp/190mAs, the Difference(%) between the measured dose and the calculated dose was found to be 0.08 %~0.33 %, and at 28 kVp/70 mAs, the Difference(%) of dose was 0.01 %~0.16 %, both of which showed results within 2%, the effective difference range. Therefore, this study found out that calculation of the absorbed dose using Geant4 Simulation is useful in measuring the absorbed dose in the breast tissue for mammography.

• Journal of radiological science and technology
• /
• v.39 no.1
• /
• pp.35-42
• /
• 2016

Room-temperature operating CdZnTe(CZT) material is an innovative radiation detector which could reduce the patient dose to one-tenth level of conventional CT (Computed Tomography) and mammography system. The pixel and pixel pitch in the imaging device determine the conversion efficiency of incident X-or gamma-ray and the cross-talk of signal, that is, image quality of detector system. The weighting potential is the virtual potential determined by the position and geometry of electrode. The weighting potential obtained by computer-based simulation in solving Poisson equation with proper boundaries condition. The pixel was optimized by considering the CIE (charge induced efficiency) and the signal cross-talk in CT detector system. The pixel pitch was 1-mm and the detector thickness was 2-mm in the simulation. The optimized pixel size and inter-pixel distance for maximizing the CIE and minimizing the signal cross-talk is about $750{\mu}m$ and $125{\mu}m$, respectively.