Investigation of classification algorithms for a prototype microwave breast cancer monitor

Santorelli, Adam; Liu, Yunpeng; Porter, Emily; Popović, Milica; Coates, Mark

doi:10.1109/eucap.2014.6901757

Cited by 5 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technology has been used extensively in the detection of breast cancer, stroke, and most recently, neurodegenerative diseases [10]- [12]. Recently, ML has been utilised to efficiently process the captured RF signals from such devices and classify different diseases in the heart and breast using received RF signals [13], [14]. Although there are no studies that investigate ML with RF data for AD detection, there have been recent studies that utilised this approach to classify stroke in the brain [15]- [17].…”

Section: Progressionmentioning

confidence: 99%

Classification of Alzheimer's Disease Using RF Signals and Machine Learning

Saied

Arslan

Chandran

2022

IEEE J. Electromagn. RF Microw. Med. Biol.

View full text Add to dashboard Cite

Objectives: Alzheimer's disease is one of the most fastest growing and costly diseases in the world today. It affects the livelihood of not just patients, but those who take care of them, including care givers, nurses, and close family members. Current progression monitoring techniques are based on MRI and PET scans which are inconvenient for patients to use. In addition, more intelligent and efficient methods are needed to predict what the current stage of the disease is and strategies on how to slow down its progress over time. Technology or Method: In this paper, machine learning was used with S-parameter data obtained from 6 antennas that were placed around the head to noninvasively capture changes in the brain in the presence of Alzheimer's disease pathology. Measurements were conducted for 9 different human models that varied in head sizes. The data was processed in several machine learning algorithms. Each algorithm's prediction and accuracy score were generated and the results were compared to determine which machine learning algorithm could be used to efficiently classify different stages of Alzheimer's disease. Results: Results from the study showed that overall, the logistic regression model had the best accuracy of 98.97% and efficiency in differentiating between 4 different stages of Alzheimer's disease. Clinical or Biological Impact: The results obtained here provide a transformative approach to clinics and monitoring systems where machine learning can be integrated with noninvasive microwave medical sensors and systems to intelligently predict the stage of Alzheimer's disease in the brain.

show abstract

Section: Progressionmentioning

confidence: 99%

Classification of Alzheimer's Disease Using RF Signals and Machine Learning

Saied

Arslan

Chandran

2022

IEEE J. Electromagn. RF Microw. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…Feature extraction is used to reduce the dimensionality of a large dataset, and ensures that only the key information that more specifically describes the observations in the dataset is retained (Santorelli et al 2014a). This process can reduce training and testing computational time and saves storage space due to the reduced number of features.…”

Section: Feature Extractionmentioning

confidence: 99%

Image-based classification of bladder state using electrical impedance tomography

et al. 2018

Self Cite

View full text Add to dashboard Cite

Objective: In this study, we examine the potential of using machine learning classification to determine the bladder state (‘not full’, ‘full’) with electrical impedance tomography (EIT) images of the pelvic region. Accurate classification of these states would enable urinary incontinence (UI) monitoring to alert the patient, before involuntary voiding occurs, in a low-cost and discrete manner. Approach: Using both numerical and experimental data, we form datasets that contain diverse observations with varying clinical parameters such as bladder volume, urine conductivity, and the reference used for time-difference imaging. We then classify the bladder state using both pixel-wise and feature extraction-based classification techniques. We employ principal component analysis, wavelets, and image segmentation to help create features. Main results: The performance was compared across several classifier algorithms. The minimum accuracy was 77.50%. The highest accuracy observed was 100%, and was found by combining principal component analysis and the Gaussian radial based function kernel support vector machine. This combination also offered the best trade-off between classification performance and the costs of training time and memory space. The biggest challenge in bladder state classification is classifying volumes near the separation volume of not full and full, in which choosing the most suitable classifier combination can minimize this error. Significance: We performed the first machine learning classification of bladder EIT images, achieving high classification accuracies with both numerical and experimental data. This work highlights the potential of using image-based machine learning with an EIT device to support bladder monitoring for those suffering from UI.

show abstract

“…8, we present photographs of the assembled system, as well as comparison photographs of the previous version of this system in [25]. Significant size reduction was achieved in this iteration by removing the electromechanical switch assembly and integrating the switching into the board.…”

Section: E System Size and Applicationmentioning

confidence: 99%

“…While there have already been a few demonstrations of a microwave system with a solid-state switching matrix [9], [16], we show for the first time in microwave imaging the integration of the switching matrix and antennas on a single-circuit board, removing the need for dedicated RF cables for each antenna. Our original system [25] required 50 RF cables for the switching matrix and antennas (one for each antenna, and then two for each switch). By integrating this circuit into our system, we have reduced this number to two RF cables and some dc control lines in ribbon cabling.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Time-Domain Microwave System for Breast Cancer Detection Using a Flexible Circuit Board

Santorelli

Porter

Kang

et al. 2015

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

We present the design of a flexible multilayer circuit board for use in a custom-built microwave system for breast health monitoring. The flexible circuit features both an integrated solid-state switching network and 16 wideband antennas, which transmit short-duration pulses into the breast tissues and receive the backscattered responses. By integrating the switching matrix and the antenna array on the same substrate, we reduce the overall cost and size of the system in comparison with previously demonstrated systems in the literature. We characterize the performance of the flexible circuit board using our clinically tested experimental system and demonstrate its functionality through successful imaging of dielectrically realistic breast phantoms that simulate the presence of a tumor. This represents a step toward a more patient-friendly, compact, cost-effective, and wearable design in contrast to previous systems in the literature that required a clinical table or used bulky rigid antenna housings and electromechanical switching networks. Emily Porter (S'11) received the B.Eng. and M.Eng. degrees in electrical engineering from McGill University, Montreal, QC, Canada, in 2009 and 2010, respectively, where she is currently pursuing the Ph.D. degree in electrical engineering.She is involved in research on applied and computational electromagnetics. Her current research interests include the medical applications of microwaves, flexible antennas, the design of realistic breast phantoms and models, and the development of a wearable prototype for breast health monitoring using microwave radar.

show abstract

Investigation of classification algorithms for a prototype microwave breast cancer monitor

Cited by 5 publications

References 9 publications

Classification of Alzheimer's Disease Using RF Signals and Machine Learning

Classification of Alzheimer's Disease Using RF Signals and Machine Learning

Image-based classification of bladder state using electrical impedance tomography

A Time-Domain Microwave System for Breast Cancer Detection Using a Flexible Circuit Board

Contact Info

Product

Resources

About