Breast masses in mammography classification with local contour features

Abstract

BackgroundMammography is one of the most popular tools for early detection of breast cancer. Contour of breast mass in mammography is very important information to distinguish benign and malignant mass. Contour of benign mass is smooth and round or oval, while malignant mass has irregular shape and spiculated contour. Several studies have shown that 1D signature translated from 2D contour can describe the contour features well.MethodsIn this paper, we propose a new method to translate 2D contour of breast mass in mammography into 1D signature. The method can describe not only the contour features but also the regularity of breast mass. Then we segment the whole 1D signature into different subsections. We extract four local features including a new contour descriptor from the subsections. The new contour descriptor is root mean square (RMS) slope. It can describe the roughness of the contour. KNN, SVM and ANN classifier are used to classify benign breast mass and malignant mass.ResultsThe proposed method is tested on a set with 323 contours including 143 benign masses and 180 malignant ones from digital database of screening mammography (DDSM). The best accuracy of classification is 99.66% using the feature of root mean square slope with SVM classifier.ConclusionThe performance of the proposed method is better than traditional method. In addition, RMS slope is an effective feature comparable to most of the existing features.Electronic supplementary materialThe online version of this article (doi:10.1186/s12938-017-0332-0) contains supplementary material, which is available to authorized users.

Establishment and Verification of a Bagged-Trees-Based Model for Prediction of Sentinel Lymph Node Metastasis for Early Breast Cancer Patients

“…Breast malignant tumor has its special form; for example, ultrasound is typically classified through the morphology, boundaries, activity, and other conditions of the tumor; molybdenum target will be classified according to the shape of the tumor and calcification (31). In retrospect, the morphology of the tumor was not analyzed as a factor in previous studies.…”

Efficient Breast Cancer Classification Using Tumor Area and Boundaries Calculation

“…Belal A. Elmonem 1 , Taha M. Mohamed 2 , and Sherif Kholeif 3 , 1 Belal_1111@hotmail.com, 2 tahamahdy3000@yahoo.com, 3 sherifkholeif@yahoo.com 1,2,3 Faculty of Computers and Information, Helwan University, Egypt. Most of the research in breast cancer classification is oriented to detect the regularity of the cell boundaries in order to correctly classify the cell to either benign or malignant.…”

“…In [5], the Cmax algorithm is proposed to classify the tumor images to either benign or malignant. In [2], the Contour method is proposed by converting the tumor image from 2D to 1D signature. In [6], the region of interest is extracted by using the spherical wavelet transform.…”

“…Early detection and diagnosis is essential to control breast cancer, which increases the success of treatment, saves lives, and reduces costs. Researchers make great efforts to find solutions to this problem [2].…”

“…Mammography is one of the diagnostic tools, used by doctors, to detect the tumors [2]. In some cases, the available mammograms are of low quality due to mammography limitation factors.…”