Breast Tumor Detection System Based on a Compact Uwb Antenna Design

Amdaouch, Ibtisam; Aghzout, Otman; Naghar, Azzeddin; Alejos, Ana Vázquez; Falcone, and Francisco J.

doi:10.2528/pierm17102404

Cited by 48 publications

(29 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig 3 shows the experimental set-up for the breast cancer sampling [ 18 , 21 – 24 ]. A pair of antennae is placed facing each other with the breast phantom located at the middle of the antennae as shown in Fig 4 .…”

Section: Data Collectionmentioning

confidence: 99%

Multi-stage feature selection (MSFS) algorithm for UWB-based early breast cancer size prediction

et al. 2020

View full text Add to dashboard Cite

Breast cancer is the most common cancer among women and it is one of the main causes of death for women worldwide. To attain an optimum medical treatment for breast cancer, an early breast cancer detection is crucial. This paper proposes a multi- stage feature selection method that extracts statistically significant features for breast cancer size detection using proposed data normalization techniques. Ultra-wideband (UWB) signals, controlled using microcontroller are transmitted via an antenna from one end of the breast phantom and are received on the other end. These ultra-wideband analogue signals are represented in both time and frequency domain. The preprocessed digital data is passed to the proposed multi- stage feature selection algorithm. This algorithm has four selection stages. It comprises of data normalization methods, feature extraction, data dimensional reduction and feature fusion. The output data is fused together to form the proposed datasets, namely, 8-HybridFeature, 9-HybridFeature and 10-HybridFeature datasets. The classification performance of these datasets is tested using the Support Vector Machine, Probabilistic Neural Network and Naïve Bayes classifiers for breast cancer size classification. The research findings indicate that the 8-HybridFeature dataset performs better in comparison to the other two datasets. For the 8-HybridFeature dataset, the Naïve Bayes classifier (91.98%) outperformed the Support Vector Machine (90.44%) and Probabilistic Neural Network (80.05%) classifiers in terms of classification accuracy. The finalized method is tested and visualized in the MATLAB based 2D and 3D environment.

show abstract

Section: Data Collectionmentioning

confidence: 99%

Multi-stage feature selection (MSFS) algorithm for UWB-based early breast cancer size prediction

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The microwave imaging technique uses UWB antenna [14,15] which covers a band of frequencies from 2.4 to 4.7 GHz as shown in Figure 3. The low frequency range is required to make sure of deep penetration [16] which is favourable for identifying the tumors at deep location, whereas high-frequency band is essential in order to obtain acceptable spatial resolution which is also favourable for identifying tumors neighbouring to the skin level.…”

Section: Ultra Wideband Antennamentioning

confidence: 99%

Detection of Depth of the Tumor in Microwave Imaging Using Ground Penetrating Radar Algorithm

Selvaraj¹,

Sheela²,

Krishnan³

et al. 2020

PIER M

View full text Add to dashboard Cite

Microwave Imaging (MI) is a new technique for detecting breast cancer using electrical property difference between the non-malignant and malignant tissues present in the breast. Numerous studies show that detecting the depth of the tumor is the essential measure in determining additional management. Developing evidence in many of the literature surveys illustrate that detecting tumor depth is a precise parameter for identifying the affected area. Thus, Ground Penetrating Radar (GPR) algorithm is applied successfully to detect the exact depth of the malignant tissue. Generally, GPR is originally conceived for archaeological investigations, building condition assessment, detection of buried mines, etc. But here an effort has been made to apply GPR to Radar-based breast cancer detection. The simulated bandwidth of the proposed UWB antenna starts at 2.4 GHz and ends at 4.7 GHz. The electromagnetic wave reflected due to dielectric property variation is used by GPR algorithm to identify the depth of the tumor. Before applying a depth migration technique, preprocessing steps like Cartesian form transformation, Hermitian Signal Processing, and Inverse Fast Fourier Transform (IFFT) have to be followed in the backscattered signal to convert positive frequency data into time-domain data. Depth details can be noticed in the migrated image, after applying the migration procedure. Results show that GPR algorithm can be effectively used for detecting the tumor embedded in the depth of the breast tissue. To understand the effectiveness of this imaging scheme, an experimental analysis is done using a combination of wheat flour and water-petroleum jelly. The measured impedance bandwidth of the UWB antenna ranges from 2.8 GHz to 4.48 GHz. The observation is done for a known spherical tumor of diameter 13 mm which is placed at different depths from the skin layer. While applying the algorithm in the received backscattered signal, we were able to detect correctly the tumor at a depth of 45 mm embedded in the breast tissue. The experimental results are compared with simulation ones to validate the aptness of a microwave imaging approach for detecting the depth of the tumor.

show abstract

“…Fig 2 shows the developed breast phantom and tumor for the experiments. Fig 3 shows the experimental set-up for the breast cancer sampling [12][13][14][15][16]. A pair of antennae is placed facing each other with the breast phantom located at the middle of the antennae.…”

Section: Data Collectionmentioning

confidence: 99%

Multi-Stage Feature Selection (MSFS) Algorithm for UWB-Based Early Breast Cancer Size Prediction

Vijayasarveswari

Andrew

Jusoh

et al. 2020

Preprint

View full text Add to dashboard Cite

Breast cancer is the most common cancer among women and it is one of the main causes of death for women worldwide. To attain an optimum medical treatment for breast cancer, an early breast cancer detection is crucial. This paper proposes a multistage feature selection method that extracts statistically significant features for breast cancer size detection using proposed data normalization techniques. Ultrawideband (UWB) signals, controlled using microcontroller are transmitted via an antenna from one end of the breast phantom and are received on the other end. These ultra-wideband analogue signals are represented in both time and frequency domain. The preprocessed digital data is passed to the proposed multi-stage feature selection algorithm. This algorithm has four selection stages. It comprises of data normalization methods, feature extraction, data dimensional reduction and feature fusion. The output data is fused together to form the proposed datasets, namely, 8-HybridFeature, 9-HybridFeature and 10-HybridFeature datasets. The classification performance of these datasets is tested using the Support Vector Machine, Probabilistic Neural Network and Naïve Bayes classifiers for breast cancer size classification. The research findings indicate that the 8-HybridFeature dataset performs better in comparison to the other two datasets. For the 8-HybridFeature dataset, the Naïve Bayes classifier (91.98%) outperformed the Support Vector Machine (90.44%) and Probabilistic Neural Network (80.05%) classifiers in terms of classification accuracy. The finalized method is tested and visualized in the MATLAB based 2D and 3D environment.

show abstract

Breast Tumor Detection System Based on a Compact Uwb Antenna Design

Cited by 48 publications

References 7 publications

Multi-stage feature selection (MSFS) algorithm for UWB-based early breast cancer size prediction

Multi-stage feature selection (MSFS) algorithm for UWB-based early breast cancer size prediction

Detection of Depth of the Tumor in Microwave Imaging Using Ground Penetrating Radar Algorithm

Multi-Stage Feature Selection (MSFS) Algorithm for UWB-Based Early Breast Cancer Size Prediction

Contact Info

Product

Resources

About