Magnetic induction tomography (MIT) is a technique for imaging the internal conductivity distribution of an object. In MIT current-carrying coils are used to induce eddy currents in the object and the induced voltages are sensed with other coils. From these measurements, the internal conductivity distribution of the object can be reconstructed. In this paper, we introduce a 16-channel MIT measurement system that is capable of parallel readout of 16 receiver channels. The parallel measurements are carried out using high-quality audio sampling devices. Furthermore, approaches for reconstructing MIT images developed for the 16-channel MIT system are introduced. We consider low conductivity applications, conductivity less than 5 S m(-1), and we use a frequency of 10 MHz. In the image reconstruction, we use time-harmonic Maxwell's equation for the electric field. This equation is solved with the finite element method using edge elements and the images are reconstructed using a generalized Tikhonov regularization approach. Both difference and static image reconstruction approaches are considered. Results from simulations and real measurements collected with the Philips 16-channel MIT system are shown.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1088/0967-3334/29/6/S37 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Retrospective evaluation of a novel ultrasound-based imaging analysis software for predicting radiofrequency ablation areas.
PLoS One
January 2025
Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
Objective: This study aimed to introduce and evaluate a novel software-based system, BioTrace, designed for real-time monitoring of thermal ablation tissue damage during image-guided radiofrequency ablation for hepatocellular carcinoma (HCC).
Methods: BioTrace utilizes a proprietary algorithm to analyze the temporo-spatial behavior of thermal gas bubble activity during ablation, as seen in conventional B-mode ultrasound imaging. Its predictive accuracy was assessed by comparing the ablation zones it predicted with those annotated by radiologists using contrast-enhanced computed tomography (CECT) 24 hours post-treatment, considered the gold standard.
Convolutional neural network (CNN) configuration using a learning automaton model for neonatal brain image segmentation.
PLoS One
January 2025
Department of Electrical Engineering, Shiraz Branch, Islamic Azad University, Shiraz, Iran.
CNN is considered an efficient tool in brain image segmentation. However, neonatal brain images require specific methods due to their nature and structural differences from adult brain images. Hence, it is necessary to determine the optimal structure and parameters for these models to achieve the desired results.
View Article and Find Full Text PDFField-scale detection of Bacterial Leaf Blight in rice based on UAV multispectral imaging and deep learning frameworks.
PLoS One
January 2025
Rice Department, Bangkok, Thailand.
Bacterial Leaf Blight (BLB) usually attacks rice in the flowering stage and can cause yield losses of up to 50% in severely infected fields. The resulting yield losses severely impact farmers, necessitating compensation from the regulatory authorities. This study introduces a new pipeline specifically designed for detecting BLB in rice fields using unmanned aerial vehicle (UAV) imagery.
View Article and Find Full Text PDFArtificial intelligence applied in identifying left ventricular walls in myocardial perfusion scintigraphy images: Pilot study.
PLoS One
January 2025
Electrical, Mechanical & Computer Engineering School, Federal University of Goias, Goiania, Brazil.
This paper proposes the use of artificial intelligence techniques, specifically the nnU-Net convolutional neural network, to improve the identification of left ventricular walls in images of myocardial perfusion scintigraphy, with the objective of improving the diagnosis and treatment of coronary artery disease. The methodology included data collection in a clinical environment, followed by data preparation and analysis using the 3D Slicer Platform for manual segmentation, and subsequently, the application of artificial intelligence models for automated segmentation, focusing on the efficiency of identifying the walls of the left ventricular. A total of 83 clinical routine exams were collected, each exam containing 50 slices, which is 4,150 images.
View Article and Find Full Text PDFGenome-wide association study on color-image-based convolutional neural networks.
PeerJ
January 2025
School of Mathematics and Computer Science, Gannan Normal University, Ganzhou, China.
Background: Convolutional neural networks have excellent modeling abilities to complex large-scale datasets and have been applied to genomics. It requires converting genotype data to image format when employing convolutional neural networks to genome-wide association studies. Existing studies converting the data into grayscale images have shown promising.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!