Review of Microwaves Techniques for Breast Cancer Detection

Aldhaeebi, Maged A.; Alzoubi, Khawla; Almoneef, Thamer S.; Bamatraf, Saeed; Attia, Hussein; Ramahi, Omar M.

doi:10.3390/s20082390

Cited by 126 publications

(86 citation statements)

References 178 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Out of the remaining features, ten features with highest F - values (highlighted in the table) are selected for Stage 4. Table 5 shows the ranking of the selected features in Stage 3 based on the F - values (in descending order) for the respective normalization methods [ 38 ].…”

Section: Multi- Stage Feature Selection Methodsmentioning

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: Multi- Stage Feature Selection Methodsmentioning

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

“…With breast tissue the performance of the proposed array worsens by about 2 dB, which is due to tissue absorption, and its response dips at a slightly lower frequency of 7.8 GHz. Compared to the reference array the proposed array in situ with the breast tissue exhibits an excellent impedance match over a very wide bandwidth (2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12). This demonstrates it is highly sensitive and receptive to weak signals over this frequency range.…”

Section: Figure 2 a Typical Microwave Imaging System In Which The Prmentioning

confidence: 95%

“…Techniques based on electromagnetic (EM) energy in the microwave region have been investigated for image reconstruction [7,8]. Compared to existing imaging systems, microwave imaging can be safely repeated more frequently because it is free from ionizing radiation [9][10][11]. In fact, investigations show that microwaves allow dielectric properties of healthy and malignant tissues to be contrasted which enables medical images to be created relatively easily due to the interaction of EM waves with matter [12].…”

Section: Introductionmentioning

confidence: 99%

Metamaterial-Inspired Antenna Array for Application in Microwave Breast Imaging Systems for Tumor Detection

et al. 2020

View full text Add to dashboard Cite

This paper presents a study of a planar antenna-array inspired by the metamaterial concept where the resonant elements have sub-wavelength dimensions for application in microwave medical imaging systems for detecting tumors in biological tissues. The proposed antenna consists of square-shaped concentric-rings which are connected to a central patch through a common feedline. The array structure comprises several antennas that are arranged to surround the sample breast model. One antenna at a time in the array is used in transmission-mode while others are in receive-mode. The antenna array operates over 2-12 GHz amply covering the frequency range of existing microwave imaging systems. Measured results show that compared to a standard patch antenna array the proposed array with identical dimensions exhibits an average radiation gain and efficiency improvement of 4.8 dBi and 18%, respectively. The average reflection-coefficient of the array over its operating range is better than S 11 ≤-20 dB making it highly receptive to weak signals and minimizing the distortion encountered with the transmission of short duration pulse-trains. Moreover, the proposed antenna-array exhibits high-isolation on average of 30dB between radiators. This means that antennas in the array (i) can be closely spaced to accommodate more radiators to achieve higher-resolution imaging scans, and (ii) the imagining scans can be done over a wider frequency range to ascertain better contrast in electrical parameters between malignant tumor-tissue and the surrounding normal breast-tissue to facilitate the detection of breast-tumor. It is found that short wavelength gives better resolution. In this experimental study a standard biomedical breast model that mimics a realhuman breast in terms of dielectric and optical properties was used to demonstrate the viability of the proposed antenna over a standard patch antenna in the detection and the localization of tumor. These results are encouraging for clinical trials and further refinement of the antenna-array.

show abstract

“…Breast cancer is reported as one of the most leading cause in deaths of women by the International Agency for Research on Cancer (IARC) [ 1 , 2 , 3 ]. The clinical diagnosis of breast cancer includes inspection of medical images including mammograms, MRI, ultrasound, and histopathology images obtained from a biopsy [ 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

Spectral–Spatial Features Integrated Convolution Neural Network for Breast Cancer Classification

Mewada

Patel

Hassaballah

et al. 2020

Sensors

View full text Add to dashboard Cite

Cancer identification and classification from histopathological images of the breast depends greatly on experts, and computer-aided diagnosis can play an important role in disagreement of experts. This automatic process has increased the accuracy of the classification at a reduced cost. The advancement in Convolution Neural Network (CNN) structure has outperformed the traditional approaches in biomedical imaging applications. One of the limiting factors of CNN is it uses spatial image features only for classification. The spectral features from the transform domain have equivalent importance in the complex image classification algorithm. This paper proposes a new CNN structure to classify the histopathological cancer images based on integrating the spectral features obtained using a multi-resolution wavelet transform with the spatial features of CNN. In addition, batch normalization process is used after every layer in the convolution network to improve the poor convergence problem of CNN and the deep layers of CNN are trained with spectral–spatial features. The proposed structure is tested on malignant histology images of the breast for both binary and multi-class classification of tissue using the BreaKHis Dataset and the Breast Cancer Classification Challenge 2015 Datasest. Experimental results show that the combination of spectral–spatial features improves classification accuracy of the CNN network and requires less training parameters in comparison with the well known models (i.e., VGG16 and ALEXNET). The proposed structure achieves an average accuracy of 97.58% and 97.45% with 7.6 million training parameters on both datasets, respectively.

show abstract

Review of Microwaves Techniques for Breast Cancer Detection

Cited by 126 publications

References 178 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

Metamaterial-Inspired Antenna Array for Application in Microwave Breast Imaging Systems for Tumor Detection

Spectral–Spatial Features Integrated Convolution Neural Network for Breast Cancer Classification

Contact Info

Product

Resources

About