Automated Breast Cancer Diagnosis Based on GVF-Snake Segmentation, Wavelet Features Extraction and Fuzzy Classification

Abstract

The automatic diagnosis of breast cancer (BC) is an important, real-world medical problem. This paper proposes a design of automated detection, segmentation, and classification of breast cancer nuclei using a fuzzy logic. The first step is based on segmentation using an active contour for cell tracking and isolating of the nucleus in the cytological image. Then from this nucleus, have been extracted some textural features using the wavelet transforms to characterize image using its texture, so that malign texture can be differentiated from benign one with the assumption that tumoral texture is different from the texture of other kinds of tissues. Finally, the obtained features will be introduced as the input vector of a fuzzy C-means (FCM) clustering algorithm to classify the images into malign and benign ones. The implementation of such algorithm has been done using a methodology based on very high speed integrated circuit, hardware description language (VHDL). The design of the circuit is performed by using a CMOS 0.35 μm technology.

Automatic Diagnosing of Suspicious Lesions in Digital Mammograms

“…L.Jelen et al [19] developed a method for Classification of breast cancer malignancy using cytological images of fine needle aspiration biopsies. J. Malek et al [20] proposed a system to Automatic Breast Cancer Diagnosis Based on GVFSnake Segmentation, Wavelet Features Extraction and Fuzzy Classification. Nra Szkely et al [21] used A Hybrid System for Detecting Masses in Mammographic Images.…”

Multiscale Convolutional Neural Networks for Vision–Based Classification of Cells

“…We manually acquire a database of annotated cells (samples shown at the first row of Figure 1 This database (and the segmentation of each cell) is made available for research purposes 1 . It contains some difficulties and maybe some annotation errors.…”

“…Computer-Aided Diagnosis (CAD) through image processing [1] [2] is a domain of ever increasing interest. Indeed, automatic salient feature extraction by a computer can save time to a pathologist, and with the ever-increasing amount of virtual biomedical data, CAD has now become a crucial point for enabling safer and faster diagnosis.…”

Nuclei segmentation for computer-aided diagnosis of breast cancer

“…Many researchers have studied the segmentation of cytological images of breast tumors, proposed new features or tested the classification algorithms (Muniandy and Stanslas, 2008;Yasmeen et al, 2013;Mat-Isa et al, 2007;Cruz-Ramirez et al, 2009;Ubeyli, 2007;Polat and Gunes, 2007;Jeleń et al, 2010;Niwas et al, 2013;Malek et al, 2009;Xiong et al, 2005). However, a few of these researchers have tested the efficiency of their methodology in a comprehensive computerized breast cancer classification system.…”

“…Classification efficiency with the k-nearest neighbor algorithm on 645 (311 malignant, 334 benign) images reached 93.9%. Another approach was presented by Malek et al (2009). They used active contours to segment nuclei and classified 200 (80 malignant, 120 benign) images using the fuzzy c-means algorithm, achieving 95% efficiency.…”