A new ensemble of features for breast cancer diagnosis

Abstract

In this paper, an automatic Computer Aided Diagnosis (CAD) system is completely designed for breast cancer diagnosis and it is verified on a publicly available mammogram dataset constructed during Image Retrieval in Medical Applications (IRMA) project. This database comprises three different patch types indicating the health status of a person. These types are normal, benign cancer, and malignant cancer and they are labeled by the radiologists for the IRMA project. In the realization of CAD system, all mammogram patches are firstly preprocessed performing a histogram equalization followed by Non-Local Means (NLM) filtering. Then, the Local Configuration Pattern (LCP) algorithm is performed for feature extraction. Besides, some statistical and frequencydomain features are concatenated to LCP-based feature vectors. The obtained new feature ensemble is used with four well-known classifiers which are Fisher's Linear Discriminant Analysis (FLDA), Support Vector Machines (SVM), Decision Tree, and k-Nearest Neighbors (k-NN). A maximum of 94.67% recognition accuracy is attained utilizing the new feature ensemble whereas 90.60% was found if only LCP-based feature vectors are used. This consequence obviously reveals that the new feature ensemble is more representative than an LCP-based feature vector by itself.

A New Feature Ensemble with a Multistage Classification Scheme for Breast Cancer Diagnosis

“…It is very important to work on images with their ground truths for medical imaging applications [48]. In this study, a publicly available mammogram dataset constructed during the IRMA project is used [49].…”

“…In the preprocessing stage, a histogram equalization followed by the NLM filtering is applied on the mammogram parts [48]. The NLM filter is an adaptive smoothing filter that changes the window size according to the similarity between neighborhoods of any two pixels as well as preserves the fine details by computing a weighting function according to the derivatives in the corresponding search window [46, 48].…”

“…The NLM filter is an adaptive smoothing filter that changes the window size according to the similarity between neighborhoods of any two pixels as well as preserves the fine details by computing a weighting function according to the derivatives in the corresponding search window [46, 48]. Given a discrete noisy image v = { v ( i )| i ∈ I }, the filtered value NL[ v ( i )] of any pixel is computed as $\begin{array}{c}\mathrm{N}\mathrm{L}\left[v\left(i\right)\right]=\sum _{j\in I}w\left(i,j\right)·v\left(j\right),\end{array}$where w ( i , j ) refers to the weight coefficient computed utilizing the similarity between pixels i and j and satisfies the conditions 0 ≤ w ( i , j ) ≤ 1 and ∑ j w ( i , j ) = 1.…”

“…The similarity between pixels i and j is measured as the Gaussian weighted Euclidean distance, ‖ v ( N i ) − v ( N j )‖ 2, σ 2 , where σ   ( σ > 0) is the standard deviation of the Gaussian kernel, whereas v ( N i ) and v ( N j ) are the neighborhoods of pixels i and j in the similarity window [48]. The pixels with larger weights indicate a similar neighborhood as it can be understood by analyzing (2).…”

Machine learning based detection of age-related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images

“…They ranked the features individually and achieved 97.8% in accuracy for the binary classifier, which focused on disease and control samples. The LCP-based features were also utilized on image-based biomedical problems, such as mammogram-based breast cancer diagnosis [25], CT-based lung nodule segmentation and identification [26], and ultrasound-based myocardial infarction staging [27], etc. LCP was demonstrated to work well on describing both the microscopic configurations and the local structural features [28].…”