Adaptive Clustering Distorted Born Iterative Method for Microwave Brain Tomography With Stroke Detection and Classification

Khosravi-Farsani, Mojtaba; Stancombe, Anthony E.; Bialkowski, Konstanty; Abbosh, Amin

doi:10.1109/tbme.2021.3122113

Cited by 35 publications

(10 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some recent works on brain microwave imaging through quantitative reconstruction are [ 10 , 11 ], where the distorted Born iterative algorithm is used for the reconstruction of the head dielectric properties. Our results are comparable with those, especially for the focusing and positioning of the reconstructed target.…”

Section: Numerical Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Discretization Procedure in the CSI-FEM Algorithm for Brain Stroke Microwave Imaging

Mariano

Vasquez

Vipiana

2022

Sensors

View full text Add to dashboard Cite

In this work, the contrast source inversion method is combined with a finite element method to solve microwave imaging problems. The paper’s major contribution is the development of a novel contrast source variable discretization that leads to simplify the algorithm implementation and, at the same time, to improve the accuracy of the discretized quantities. Moreover, the imaging problem is recreated in a synthetic environment, where the antennas, and their corresponding coaxial port, are modeled. The implemented algorithm is applied to reconstruct the tissues’ dielectric properties inside the head for brain stroke microwave imaging. The proposed implementation is compared with the standard one to evaluate the impact of the variables’ discretization on the algorithm’s accuracy. Furthermore, the paper shows the obtained performances with the proposed and the standard implementations of the contrast source inversion method in the same realistic 3D scenario. The exploited numerical example shows that the proposed discretization can reach a better focus on the stroke region in comparison with the standard one. However, the variation is within a limited range of permittivity values, which is reflected in similar averages.

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

“…The CSI method is an iterative nonlinear algorithm widely exploited in MWI technology, thanks to its capability to reconstruct the dielectric properties distribution quantitatively inside the DoI. Another quantitative algorithm used in the literature for brain microwave imaging is the distorted Born iterative method, as in [ 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Discretization Procedure in the CSI-FEM Algorithm for Brain Stroke Microwave Imaging

Mariano

Vasquez

Vipiana

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…They designed an adaptive clustering DBIM (AC-DBIM), which obtains advancements in the reconstruction of size and shape and results in significant reductions in errors compared to other conventional algorithms. [52] Although microwave imaging technology has made significant advances in diagnosing stroke patients, several limitations should be considered. For example, there is substantial leakage into the space between the sensor and head, reducing the radiofrequency transmission through the skull.…”

Section: Microwave Technologymentioning

confidence: 99%

“…They designed an adaptive clustering DBIM (AC‐DBIM), which obtains advancements in the reconstruction of size and shape and results in significant reductions in errors compared to other conventional algorithms. [ 52 ]…”

Section: Microwave Technologymentioning

confidence: 99%

Modern Prehospital Screening Technology for Emergent Neurovascular Disorders

Guo

Dye

2023

Advanced Biology

View full text Add to dashboard Cite

Stroke is a serious neurological disease and a significant contributor to disability worldwide. Traditional in‐hospital imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI) remain the standard modalities for diagnosing stroke. The development of prehospital stroke detection devices may facilitate earlier diagnosis, initiation of stroke care, and ultimately better patient outcomes. In this review, the authors summarize the features of eight stroke detection devices using noninvasive brain scanning technology. The review summarizes the features of stroke detection devices including portable CT, MRI, transcranial Doppler ultrasound , microwave tomographic imaging, electroencephalography, near‐infrared spectroscopy, volumetric impedance phaseshift spectroscopy, and cranial accelerometry. The technologies utilized, the indications for application, the environments indicated for application, the physical features of the eight stroke detection devices, and current commercial products are discussed. As technology advances, multiple portable stroke detection instruments exhibit the promising potential to expedite the diagnosis of stroke and enhance the time taken for treatment, ultimately aiding in prehospital stroke triage.

show abstract

“…9 Guo et al proposed an adaptive clustering Distorted Born iterative method (DBIM) for brain imaging, significantly improving size and shape reconstruction. 10 However, traditional microwave tomography is computationally complex and has many iterations. 11 Deep learning has made significant progress in the field of medical image processing, including brain anomaly detection 12 and automatic diagnosis of COVID-19 lung images, 13 and has also been applied to other fields.…”

Section: Introductionmentioning

confidence: 99%

An encoder–decoder and modified U‐Net network for microwave imaging of stroke

Liu,

Chen,

Xiong

2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Microwave imaging has been widely used in stroke diagnosis as a non‐invasive, ionizing radiation‐free imaging method. However, the electromagnetic inverse scattering problems of microwave imaging are nonlinear and ill‐posed. To further improve the accuracy of microwave imaging algorithms to identify and reconstruct stroke regions. A novel Encoder‐Decoder and Modified U‐Net (ED‐MUNET) network for microwave imaging of stroke is proposed. The newly proposed ED‐MUNET method accomplishes the initial imaging from scattered data to stroke images through an encoder–decoder in the first step. In the second step, the feature information of the reconstructed image is extracted through the modified U‐Net network, and the reconstruction from the rough stroke image to the high‐resolution image is realized. The second step avoids black‐box operations and improves image accuracy. ED‐MUNET has fewer artifacts, the relative reconstruction error is less than 0.05, and the reconstructed images are clearer, according to the comparative experiments with other networks. The experimental results showed the superiority of the proposed method for reconstructing stroke images.

show abstract

Adaptive Clustering Distorted Born Iterative Method for Microwave Brain Tomography With Stroke Detection and Classification

Cited by 35 publications

References 50 publications

A Novel Discretization Procedure in the CSI-FEM Algorithm for Brain Stroke Microwave Imaging

A Novel Discretization Procedure in the CSI-FEM Algorithm for Brain Stroke Microwave Imaging

Modern Prehospital Screening Technology for Emergent Neurovascular Disorders

An encoder–decoder and modified U‐Net network for microwave imaging of stroke

Contact Info

Product

Resources

About