1,721,035 research outputs found
Hyperthermia Treatment Monitoring via Deep Learning Enhanced Microwave Imaging: A Numerical Assessment
Full text linkSimple Summary Non-invasive temperature monitoring during hyperthermia cancer treatment is of paramount importance. It allows physicians to verify the therapeutic temperature is reached in the treated area. Currently, only superficial or invasive thermometry is performed on a clinical level. Magnetic resonance thermometry has been proposed as a a non-invasive alternative but its applicability is limited. Conversely, microwave imaging based thermometry is a potential low cost candidate for non-invasive temperature monitoring. This works presents a computational study in which the use of deep learning is proposed to face the challenges related to the use of microwave imaging in hyperthermia monitoring. The paper deals with the problem of monitoring temperature during hyperthermia treatments in the whole domain of interest. In particular, a physics-assisted deep learning computational framework is proposed to provide an objective assessment of the temperature in the target tissue to be treated and in the healthy one to be preserved, based on the measurements performed by a microwave imaging device. The proposed concept is assessed in-silico for the case of neck tumors achieving an accuracy above 90%. The paper results show the potential of the proposed approach and support further studies aimed at its experimental validation
An Effective Framework for Deep-Learning-Enhanced Quantitative Microwave Imaging and Its Potential for Medical Applications
Full text linkMicrowave imaging is emerging as an alternative modality to conventional medical diagnostics technologies. However, its adoption is hindered by the intrinsic difficulties faced in the solution of the underlying inverse scattering problem, namely non-linearity and ill-posedness. In this paper, an innovative approach for a reliable and automated solution of the inverse scattering problem is presented, which combines a qualitative imaging technique and deep learning in a two-step framework. In the first step, the orthogonality sampling method is employed to process measurements of the scattered field into an image, which explicitly provides an estimate of the targets shapes and implicitly encodes information in their contrast values. In the second step, the images obtained in the previous step are fed into a neural network (U-Net), whose duty is retrieving the exact shape of the target and its contrast value. This task is cast as an image segmentation one, where each pixel is classified into a discrete set of permittivity values within a given range. The use of a reduced number of possible permittivities facilitates the training stage by limiting its scope. The approach was tested with synthetic data and validated with experimental data taken from the Fresnel database to allow a fair comparison with the literature. Finally, its potential for biomedical imaging is demonstrated with a numerical example related to microwave brain stroke diagnosis
On the Design of Phased Arrays for Medical Applications
No full textThis paper deals with the optimal design of phased arrays for medical applications of microwaves, such as hyperthermia treatments and cancer imaging. To address this problem, microwave engineers have to face peculiar and novel challenges, since the region of interest is a 3-D domain in the near field of the array and consists of a highly heterogeneous and lossy medium, whose characteristics change from patient to patient. For this reason, we have to reconsider basic fundamentals about phased array design, in order to devise proper tools and criteria. In particular, we address the design of the system layout, i.e., the choice of the number and locations of the array elements, as this represents the preliminary fundamental problem to face. To this end, we first formulate the two general problems relevant to biomedical applications-the design of an array for therapeutic purposes and of an array for diagnostic/imaging goals. We then address the proper theoretical and analytic tools and methods that enable pursuit of an optimal design with respect to given constraints. Finally, we provide some examples to show how the design procedure can be carried out in practice
Microwave Imaging System for In-Line Security Assessment
Full text linkThe accidental foreign bodies contamination is still a major issue for food manufacturing industries. The continuous growth of automation along production lines together with the increasing attention of the customers towards food products quality, improved the industries care aiming to avoid complaints and ensure the best possible quality. As a matter of fact, several technologies are employed, but they lack in detecting certain class of contaminants, such as low-density plastics or small glass fragments that could turn into a severe threat, in particular for children. This work proposes a microwave imaging system in order to overcome these limitation in employed technologies.
The design and characterization are reported in this paper; the simulations are addressed to the realization of a system prototype
A Simple Differential Microwave Imaging Approach for In-Line Inspection of Food Products
Full text linkMicrowave imaging has been recently proposed as alternative technology for in-line inspection of packaged products in the food industry, thanks to its non-invasiveness and the low-cost of the equipment. In this framework, simple and effective detection/imaging strategies, able to reveal the presence of foreign bodies that may have contaminated the product during the packaging stage, are needed to allow real-time and reliable detection, thus avoiding delays along the production line and limiting occurrence of false detections (either negative or positive). In this work, a novel detection/imaging approach meeting these requirements is presented. The approach performs the detection/imaging of the contaminant by exploiting the symmetries usually characterizing the food items. Such symmetries are broken by the presence of foreign bodies, thereby determining a differential signal that can be processed to reveal their presence. In so doing, the approach does not require the prior measurement of a reference, defect-free, item. With respect to the quite common case of homogeneous food packaged in circular plastic/glass jars, numerical analyses are provided to show the effectiveness of the proposed approach
Simplified Multi-Channel Calibration for Microwave Imaging Systems
Full text linkThis work proposes and validates a simplified
n-channel calibration for microwave imaging systems that reduces the complexity of a standard full-port calibration from a
minimum of 4n − 1 measurements to 4(2) − 1 ones, respectively.
The method consists of a joined 2-port standard calibration
with a multi-port extrapolation. It compensates for systematic
errors and mitigates the effects of losses and phase shifting
caused by the multiplexing stage of a microwave imaging system.
The conditioning and limitations of the technique are studied,
including the switching matrix’s dynamic range, insertion loss,
and the error path extrapolation analysis. Finally, the calibration
is validated by employing a brain stroke monitoring system using
either an electromechanical switching matrix or a solid-statebased one, and repeatability and stability tests that demonstrate
the calibration’s effectiveness and robustness are performed
Early Detection of Alzheimer’s Disease via Microwave Sensing Technique Applied to the Neck
No full textThis paper aims to assess the capability in detecting the Alzheimer's disease via the investigation of the dielectric properties in the human neck, exploiting the microwave sensing technique. In particular, after the creation of a simplified 2-D synthetic neck phantom, four different stages of the pathology are generated by changing the permittivity of the cerebrospinal fluid. The discretization and the solution of the problem is obtained through a finite element method solver. The results show that the different considered stages of the disease cause changing in the cerebrospinal fluid permittivity, detectable by the microwaves technique
Brick Shaped Antenna Module for Microwave Brain Imaging Systems
Full text linkIn this letter, we describe and validate a microwave antenna designed for an imaging device for the diagnosis and monitoring of cerebrovascular pathologies. The antenna consists of a printed monopole immersed in a parallelepipedic block of semiflexible material with custom-permittivity, which allows to avoid the use of liquid coupling media and enables a simple array arrangement. The “brick” is built with a mixture of urethane rubber and graphite powder. The -10 dB frequency band of the antenna is 800 MHz-1.2 GHz, in agreement with the device requirements. The designed brick antenna is assessed in terms of power penetration, reflection, and transmission coefficients. To show the performance of the antenna in the relevant application scenario, an experiment has been carried out on an anthropomorphic head phantom, measuring the differential signals between healthy state and hemorrhagic stroke mimicking condition for different antennas positions
High Fidelity Modelling of a Microwave Imaging Device for Brain Stroke Monitoring
Full text linkIn this paper, we present the validation of novel microwave imaging device able to monitor cerebrovascular diseases through a 3-D anatomically realistic full-wave simulation and a reconstruction algorithm based on Truncated Singular Value Decomposition (TSVD)
- …
