Characterization of mammographic masses based on local photometric attributes
- PDF / 2,734,298 Bytes
- 19 Pages / 439.642 x 666.49 pts Page_size
- 4 Downloads / 179 Views
Characterization of mammographic masses based on local photometric attributes Rinku Rabidas1 · Wasim Arif2 Received: 3 June 2019 / Revised: 13 March 2020 / Accepted: 22 April 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract This paper proposes Local Photometric Attributes (LPA) for the characterization of mammographic masses as benign or malignant. LPA measures the local information over the optical density image which suppresses the background region and provides more details about the mass lesion. The evaluation of the proposed approach is conducted by incorporating the mammograms of two benchmark databases—mini-MIAS and DDSM where a ten-fold cross validation technique is employed with different classifiers—Fishers Linear Discriminant Analysis, Random forest, and Support vector machine after filtering the optimal set of features by utilizing stepwise logistic regression method. The best performance achieved by the introduced approach in terms of an area under the receiver operating characteristic (ROC) curve (Az value) and accuracy (Acc ) are 0.94 and 86.90%, respectively for the mini-MIAS dataset while the same for the DDSM dataset are 0.89 and 80.76%, respectively. The competitive nature of the proposed scheme is evident by comparing the obtained results with schemes in the state-of-the-arts. Keywords Breast cancer · Mammography · Mass classification · ODCM · Local attributes
1 Introduction Globally, cancer is a severe threat to the humankind but among different kind of cancers, though rare in male, breast cancer is the most dominant type in women, especially. Breast cancer has an estimate of 1,676,600 new cases registered with an approximate of 521,900 deaths as reported by the American Cancer Society [1]. Although the mortality rate due to breast cancer has gone down in the last decade, but is still a prominent type of cancer affecting the women life. Early detection and diagnosis of breast cancer is the only way to reduce the mortality rate. Due to the high radiation of Computed tomography (CT) and expensive Rinku Rabidas
[email protected] 1
Department of Electronics and Communication Engineering, Assam University Silchar, Assam, India, 788011
2
Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Assam, 788010, India
Multimedia Tools and Applications
nature of Magnetic resonance imaging (MRI) screening, the infrared thermal imaging based Thermograms can be explored as another alternative to screening techniques for detection of breast cancer.[23–25] but mammography, an effective and low energy X-rays screening technique, is generally preferred for the detection of abnormalities in breast [1]. Moreover, the efficient interpretation of mammograms is a challenging job due to the subtle nature of the anomalies as a result it requires skilled radiologists which are less in number. The fatigue caused after examining large volume of mammograms may lead to human errors even by the skilled radiologists. Therefore, Comp
Data Loading...
