Microwave breast cancer detection using time-frequency representations

Song, Hongchao; Li, Yunpeng; Men, Aidong

doi:10.1007/s11517-017-1712-0

Cited by 15 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, other authors have implemented comparable machine-learning approaches for detection, i.e., to determine whether a tumour is present in the breast [ 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 ]. While an in-depth review of the detection studies based on machine learning performed to date is beyond the scope of this work, their main findings are summarised here for completeness.…”

Section: Introductionmentioning

confidence: 99%

“…Artefact removal algorithms have been proposed, which deal with large skin reflections and decrease the glandular tissue influence on the backscattered signals, for example [ 50 , 51 ]. As mentioned in Section 1.2 , previous studies have also suggested that: pre-processing signals by means of windowing could highlight and time-align the tumour signature [ 38 ]; extracting features based on time-frequency representations of the data could further capture the essence of the tumour signature while disregarding the background noise [ 48 , 49 ]; and classifying a dataset according to tumour size before attempting at classification based on the level of malignancy [ 29 , 30 , 31 , 33 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosing Breast Cancer with Microwave Technology: Remaining Challenges and Potential Solutions with Machine Learning

et al. 2018

View full text Add to dashboard Cite

Currently, breast cancer often requires invasive biopsies for diagnosis, motivating researchers to design and develop non-invasive and automated diagnosis systems. Recent microwave breast imaging studies have shown how backscattered signals carry relevant information about the shape of a tumour, and tumour shape is often used with current imaging modalities to assess malignancy. This paper presents a comprehensive analysis of microwave breast diagnosis systems which use machine learning to learn characteristics of benign and malignant tumours. The state-of-the-art, the main challenges still to overcome and potential solutions are outlined. Specifically, this work investigates the benefit of signal pre-processing on diagnostic performance, and proposes a new set of extracted features that capture the tumour shape information embedded in a signal. This work also investigates if a relationship exists between the antenna topology in a microwave system and diagnostic performance. Finally, a careful machine learning validation methodology is implemented to guarantee the robustness of the results and the accuracy of performance evaluation.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Diagnosing Breast Cancer with Microwave Technology: Remaining Challenges and Potential Solutions with Machine Learning

et al. 2018

View full text Add to dashboard Cite

show abstract

“…It is easier to visualize the signal characteristics in time domain. However, analyzing the signal characterization in frequency domain is equally important because it helps to observe the characteristics of the signal which are unable to be visualized in the time domain [ 27 , 29 , 30 ]. Thus, the time domain signals obtained from the UWB transceivers are transformed to the frequency domain signals using the commonly used Fast Fourier Transform (FFT).…”

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

“…To remove/reduce these early time clutters, several signal processing algorithms were used such as Averaging [5], Weiner Filter [7], Entropy Filter [16], Hybrid approaches [17], Pole Removal [15], and Independent Component Analysis [18].…”

Section: Signal Calibrationmentioning

confidence: 99%

“…To apply a Wiener filter in multistatic, we need to find similar channels to allow the Wiener filter to find common information among them. We choose highly similar signals and a condition for the channels as one group as in [18]. The filter coefficients h(n) are:…”

Section: Wiener Filtermentioning

confidence: 99%

Poles Isolation via Esprit for Ultra-Wide Band Breast Cancer Imaging

Abed¹,

Al-Zuhairi²,

Quboa³

et al. 2019

PIER C

View full text Add to dashboard Cite

In this paper, microwave breast cancer detection is investigated using the Ultra-Wide Band (UWB) radar imaging technique. A novel calibration approach based on the Estimation of Signal Parameters via Rotational Invariance Technique (ESPRIT) is used and adapted to work in this field. Using this method, many high amplitude undesired responses can be removed like early time clutter, late time clutter, and the mutual coupling between antennas. Using an electromagnetic simulation tool, a numerical phantom with a heterogeneous structure and dispersive dielectric properties is made for simulating the interactions of the electromagnetic fields with various breast tissues and investigating the proposed approach. The calibrated signals show the capability of the proposed algorithm in separating the tumor/glandular responses from the clutter. Also, the results of the proposed algorithm are compared with the Wiener algorithm results which are considered one of the best techniques to remove clutter, reduce late time clutters in the multistatic, and enhance the beamformer algorithm performance. Moreover, we propose the use of Transmitting-Receiving Antenna Separation Distance (TRASD) to limit the reflection angles from the voxel under the calculations of DAS and IDAS beamforming algorithms.

show abstract

Microwave breast cancer detection using time-frequency representations

Cited by 15 publications

References 34 publications

Diagnosing Breast Cancer with Microwave Technology: Remaining Challenges and Potential Solutions with Machine Learning

Diagnosing Breast Cancer with Microwave Technology: Remaining Challenges and Potential Solutions with Machine Learning

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

Poles Isolation via Esprit for Ultra-Wide Band Breast Cancer Imaging

Contact Info

Product

Resources

About