Integration of Image Segmentation Method in Inverse Scattering for Brain Tumour Detection

Joseph, Eustacius Jude; Ping, Kismet Anak Hong; Kipli, Kuryati; Mat, Dayang Azra Awang; Sahrani, Shafrida; Zaidel, D. N. A.; Sariphn, Mohd Iqbal; Marhaban, Mohamad Hamiruce

doi:10.2528/pierm17070603

Cited by 5 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As in the frequency domain case, the relative permittivity at the j th grid cell was changed 10% to ensure linearity. The Jacobian matrix was calculated using (48) and repeating the simulations for M grid cells. Then, the functional derivative was obtained using (51).…”

Section: Time Domain Simulationsmentioning

confidence: 99%

“…It has found widespread use in many fields, including seismology, 18 ultrasound imaging, 19 blood flow and clotting, 20,21 diffuse optical tomography, [22][23][24] geophysics, 25 photonics, 26 and high-frequency structure analysis. 27 Microwave imaging also takes advantage of the adjoint method, which is frequently favored in both frequency domain [28][29][30][31][32][33][34][35][36][37][38][39][40][41] and time domain [42][43][44][45][46][47][48][49][50] imaging algorithms resulting in diverse formulations.…”

mentioning

confidence: 99%

See 1 more Smart Citation

On the utilization of the adjoint method in microwave tomography

Soydan,

Top,

Gençer

2024

Numer Methods Biomed Eng

View full text Add to dashboard Cite

In microwave imaging, the adjoint method is widely used for the efficient calculation of the update direction, which is then used to update the unknown model parameter. However, the utilization and the formulation of the adjoint method differ significantly depending on the imaging scenario and the applied optimization algorithm. Because of the problem‐specific nature of the adjoint formulations, the dissimilarities between the adjoint calculations may be overlooked. Here, we have classified the adjoint method formulations into two groups: the direct and indirect methods. The direct method involves calculating the derivative of the cost function, whereas, in the indirect method, the derivative of the predicted data is calculated. In this review, the direct and indirect adjoint methods are presented, compared, and discussed. The formulations are explicitly derived using the two‐dimensional wave equation in frequency and time domains. Finite‐difference time‐domain simulations are conducted to show the different uses of the adjoint methods for both single source‐multiple receiver, and multiple transceiver scenarios. This study demonstrated that an appropriate adjoint method selection is significant to achieve improved computational efficiency for the applied optimization algorithm.

show abstract

Section: Time Domain Simulationsmentioning

confidence: 99%

mentioning

confidence: 99%

On the utilization of the adjoint method in microwave tomography

Soydan,

Top,

Gençer

2024

Numer Methods Biomed Eng

View full text Add to dashboard Cite

show abstract

“…Another concrete comparative study was presented by Mahmood et al [5], who demonstrated that MWT image segmentation is even capable of ameliorating the accuracy of image reconstruction using several automated segmentation methods. Joseph et al [24] integrated image segmentation with their inverse scattering algorithm called Forward-Backward Time-Stepping (FBTS) to apply on microwave imaging for brain tumors. From the retrospective work, we determine to deploy two well-known approaches as pre-study to support our methodology.…”

Section: Related Workmentioning

confidence: 99%

Automated Microwave Tomography (MWT) Image Segmentation: State-of-the-Art Implementation and Evaluation

Zhang¹,

Ma²,

Omrani³

et al. 2020

Computer Science Research Notes

View full text Add to dashboard Cite

Inspired by the high performance in image-based medical analysis, this paper explores the use of advanced segmentation techniques for industrial Microwave Tomography (MWT). Our context is the visual analysis of moisture levels in porous foams undergoing microwave drying. We propose an automatic segmentation technique-MWT Segmentation based on K-means (MWTS-KM) and demonstrate its efficiency and accuracy for industrial use. MWTS-KM consists of three stages: image augmentation, grayscale conversion, and K-means implementation. To estimate the performance of this technique, we empirically benchmark its efficiency and accuracy against two well-established alternatives: Otsu and K-means. To elicit performance data, three metrics (Jaccard index, Dice coefficient and false positive) are used. Our results indicate that MWTS-KM outperforms the well-established Otsu and K-means, both in visually observable and objectively quantitative evaluation.

show abstract

“…The time domain technique has the ability to reconstruct an accurate profile of electrical properties as in the FBTS technique, compared to frequency domain based technique. Thus, the FBTS technique has been used for the detection of breast cancer [6,7,35], tumors in the lung [36], and tumors in the brain [37]. Following the advancement of FBTS, filters such as Elliptic filter [38] and Chebyshev filter [39] are incorporated to solve the non-linearity problem.…”

Section: Introductionmentioning

confidence: 99%

Detection and Localization of an Object Behind Wall Using an Inverse Scattering Technique With Wall Direct Subtraction Method

Mahsen¹,

Ping²,

Sahrani³

2019

PIER C

Self Cite

View full text Add to dashboard Cite

Through-wall imaging (TWI) is one of the useful applications nowadays in microwave tomography field. Reconstructing image of an object becomes more challenging when it is obscured by walls. In practice, the inclusions of noise worsen the reconstruction results. In this paper, Forward-Backward Time-Stepping (FBTS) in time inversion technique is utilized and integrated with Wall Direct Subtraction (WDS) method to reconstruct unknown object behind walls. The investigation includes two types of walls that are homogeneous and heterogeneous. The object is surrounded by closed walls. With noise added in the setup, Singular Value Decomposition (SVD) and Savitzky-Golay (SG) filtering method are used to eliminate the noise and enhance the reconstructed image of an object. The results show that WDS integrated with FBTS has successfully mitigating wall clutter from both homogeneous and heterogeneous walls, and also improves image reconstruction of a hidden object. Further, by using the proposed noise reduction method, lower MSE values can be achieved.

show abstract

Integration of Image Segmentation Method in Inverse Scattering for Brain Tumour Detection

Cited by 5 publications

References 22 publications

On the utilization of the adjoint method in microwave tomography

On the utilization of the adjoint method in microwave tomography

Automated Microwave Tomography (MWT) Image Segmentation: State-of-the-Art Implementation and Evaluation

Detection and Localization of an Object Behind Wall Using an Inverse Scattering Technique With Wall Direct Subtraction Method

Contact Info

Product

Resources

About