Evaluation of Features and Classifiers for Classification of Early-stage Breast Cancer

Conceição, Raquel C.; O’Halloran, Martin; Glavin, Martin; Jones, Edward

doi:10.1163/156939311793898350

Cited by 25 publications

(43 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applying feature extraction to the recorded data allows us to reduce the dimensionality of the data, thus we can minimize the processing of the input data by extracting only the essential components, and using these components for analysis with the classifier. In [28] it was shown that PCA was the best feature extraction method on average; additionally, when combined with the SVM classifier, it yielded the best results compared to the combination of other classifier and feature extraction methods. Thus, we adopt a similar methodology in this paper.…”

Section: Feature Extractionmentioning

confidence: 99%

Investigation of Classifiers for Tumor Detection With an Experimental Time-Domain Breast Screening System

Santorelli¹,

Porter²,

Kirshin³

et al. 2014

PIER

View full text Add to dashboard Cite

Abstract-In this work we examine, for the first time, the use of classification algorithms for earlystage tumor detection with an experimental time-domain microwave breast screening system. The experimental system contains a 16-element antenna array, and testing is done on breast phantoms that mimic breast tissue dielectric properties. We obtain experimental data from multiple breast phantoms with two possible tumor locations. In this work, we investigate a method for detecting the tumors within the breast but without the usual complexity inherent to image-generation methods, and confirm its feasibility on experimental data. The proposed method uses machine learning techniques, namely Support Vector Machines (SVM) and Linear Discriminant Analysis (LDA), to determine whether the current breast being scanned is tumor-free. Our results show that both SVM and LDA methods have promise as algorithms supporting early breast cancer microwave screening.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Investigation of Classifiers for Tumor Detection With an Experimental Time-Domain Breast Screening System

Santorelli¹,

Porter²,

Kirshin³

et al. 2014

PIER

View full text Add to dashboard Cite

show abstract

“…Two methods have principally been used for tumour modelling in 2D and in 3D studies: polygonal approximation using an elliptical baseline [44][45][46][47][48][49] and Gaussian Random Spheres [30,35,[50][51][52][53][54][55][56][57]. The basis for these methods is described in the following subsections.…”

Section: Tumour Modellingmentioning

confidence: 99%

“…UWB tumour classification was examined by Chen et al [44][45][46][47][48] and Teo et al [49] using tumours located in 2D breast models, while studies by Davis et al [30] and Conceição [51][52][53][54][55], McGinley et al [56], O'Halloran et al [57] and Alshehri et al [64] considered tumours in 3D breast models. The latter will not be further discussed in this study since discrimination between benign and malignant tumours is only assessed in terms of dielectric differences between the two types of tumours and does not address resulting tumour signatures due to different shapes, which is the scope of this paper.…”

Section: Combining Breast and Tumour Modelsmentioning

confidence: 99%

“…In studies by Conceição et al [51][52][53]55] and McGinley et al [56] a similar approach to that of Davis et al [30] is used. The main differences are the dimensions of the TF and SF regions, as illustrated in Figure 13.…”

Section: Combining Breast and Tumour Modelsmentioning

confidence: 99%

“…In the latest studies by Conceição et al [52,54] and O'Halloran et al [57], dielectric heterogeneity is introduced by inclusion of fibroglandular clusters in the TF, around the tumour models. Four different breast model scenarios were considered.…”

Section: Combining Breast and Tumour Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Numerical Modelling for Ultra Wideband Radar Breast Cancer Detection and Classification

ConceiÃ§Ã£o¹,

O’Halloran²,

Glavin³

et al. 2011

PIER B

View full text Add to dashboard Cite

Abstract-Microwave Imaging is one of the most promising emerging imaging technologies for breast cancer detection, and exploits the dielectric contrast between normal and malignant breast tissue at microwave frequencies. The development of many UWB Radar imaging approaches requires the use of accurate numerical models for the propagation and scattering of microwave signals within the breast. The Finite-Difference Time-Domain (FDTD) method is the most commonly used numerical modelling technique used to model the propagation of Electromagnetic (EM) waves in biological tissue. However, it is critical that an FDTD model accurately represents the dielectric properties of the constituent tissues, including tumour tissues, and the highly correlated distribution of these tissues within the breast. This paper presents a comprehensive review of the latest findings regarding dielectric properties of normal and cancerous breast tissue, and the heterogeneity of normal breast tissue. Furthermore, existing FDTD models of the breast described in the literature are examined.

show abstract

Classification of breast tumor models with a prototype microwave imaging system

et al. 2020

View full text Add to dashboard Cite

Purpose: The assessment of the size and shape of breast tumors is of utter importance to the correct diagnosis and staging of breast cancer. In this paper, we classify breast tumor models of varying sizes and shapes using signals collected with a monostatic ultra-wideband radar microwave imaging prototype system with machine learning algorithms specifically tailored to the collected data. Methods: A database comprising 13 benign and 13 malignant tumor models with sizes between 13 and 40 mm was created using dielectrically representative tissue mimicking materials. These tumor models were placed inside two breast phantoms: a homogeneous breast phantom and a breast phantom with clusters of fibroglandular mimicking tissue, accounting for breast heterogeneity. The breast phantoms with tumors were imaged with a monostatic microwave imaging prototype system, over a 1-6 GHz frequency range. The classification of benign and malignant tumors embedded in the two breast phantoms was completed, and tumor classification was evaluated with Principal Component Analysis as a feature extraction method, and tuned Na€ ıve Bayes (NB), decision trees (DT), and knearest neighbours (kNN) as classifiers. We further study which antenna positions are better placed to classify tumors, discuss the feature extraction method and optimize classification algorithms, by tuning their hyperparameters, to improve sensitivity, specificity and the receiver operating characteristic curve, while ensuring maximum generalization and avoiding overfitting and data contamination. We also added a realistic synthetic skin response to the collected signals and examined its global effect on classification of benign vs malignant tumors. Results: In terms of global classification performance, kNN outperformed DT and NB machine learning classifiers, achieving a classification accuracy of 96.2% when classifying between benign and malignant tumor phantoms in a homogeneous breast phantom (both when the skin artifact is and is not considered). Conclusions:We experimentally classified tumor models as benign or malignant with a microwave imaging system, and we showed a methodology that can potentially assess the shape of breast tumors, which will give further insight into the correct diagnosis and staging of breast cancer.

show abstract

Evaluation of Features and Classifiers for Classification of Early-stage Breast Cancer

Abstract: Microwave Imaging (MI) has been extensively investigated for a number of years to develop a technique to detect breast cancer at the earliest stages of development.

Cited by 25 publications

References 29 publications

Investigation of Classifiers for Tumor Detection With an Experimental Time-Domain Breast Screening System

Investigation of Classifiers for Tumor Detection With an Experimental Time-Domain Breast Screening System

Numerical Modelling for Ultra Wideband Radar Breast Cancer Detection and Classification

Classification of breast tumor models with a prototype microwave imaging system

Contact Info

Product

Resources

About