ﻻ يوجد ملخص باللغة العربية
It has been shown that with the use of ultra-wideband (UWB) electromagnetic signal and time of arrival (ToA) principle, it is possible to locate medical implants given the permittivity distribution of the body. We propose a new imaging modality using the reverse process to acquire permittivity distributions as a surrogate of human anatomy. In the proposed systems, the locations of the signal source, receiver, and signal shapes are assumed to be known exactly. The measured data is recorded as the time it takes for the signal to travel from the signal source to the signal receiver. The finite-difference-time-domain (FDTD) method is used for the modeling of signal propagation within the phantom, which is used for both simulation and image reconstruction. Image reconstruction is achieved using linear regression on the training pairs, which includes randomly generated images and its corresponding arrival times generated using the FDTD approach. The linear weights of the training images are generated to minimize the difference between the arrival time of the reconstruction image and the measured arrival time. A simulation study using UWB signal with the central frequency of 300 MHz and the Shepp-Logan phantom was carried out. Ten-picosecond timing resolution is used for the simulation and image reconstruction. The quantitative difference between the arrival times of the phantom and the reconstructed image reduced with an increased iteration number. The quantitative error of the reconstructed image reached below 10% after 900 iterations, and 8.4% after 1200 iterations. With additional post-smoothing to suppress the introduced noise pattern through reconstruction, 6.5% error was achieved. In this paper, an approach that utilizes the ToA principle to achieve transmission imaging with radio waves is proposed and validated using a simulation study.
Motion imaging phantoms are expensive, bulky and difficult to transport and set-up. The purpose of this paper is to demonstrate a simple approach to the design of multi-modality motion imaging phantoms that use mechanically stored energy to produce m
Medical image processing is one of the most important topics in the field of the Internet of Medical Things (IoMT). Recently, deep learning methods have carried out state-of-the-art performances on medical image tasks. However, conventional deep lear
This article discusses how the language of causality can shed new light on the major challenges in machine learning for medical imaging: 1) data scarcity, which is the limited availability of high-quality annotations, and 2) data mismatch, whereby a
Advances in computing power, deep learning architectures, and expert labelled datasets have spurred the development of medical imaging artificial intelligence systems that rival clinical experts in a variety of scenarios. The National Institutes of H
Image denoising is of great importance for medical imaging system, since it can improve image quality for disease diagnosis and downstream image analyses. In a variety of applications, dynamic imaging techniques are utilized to capture the time-varyi