Detection and classification of masses in mammographic images in a multi-kernel approach

A R T I C L E I N F O Article history:
Received 00 December 00 Received in revised form 00 January 00 Accepted 00 February 00

Keywords: Breast cancer Mammography Multi-resolution wavelets Extreme learning machines Support vector machines

A B S T R A C T According to the World Health Organization, breast cancer is the main cause of cancer death among adult women in the world. Although breast cancer occurs indiscriminately in countries with several degrees of social and economic development, among developing and underdevelopment countries mortality rates are still high, due to low availability of early detection technologies. From the clinical point of view, mammography is still the most effective diagnostic technology, given the wide diffusion of the use and interpretation of these images. Herein this work we propose a method to detect and classify mammographic lesions using the regions of interest of images. Our proposal consists in decomposing each image using multi-resolution wavelets. Zernike moments are extracted from each wavelet component. Using this approach we can combine both texture and shape features, which can be applied both to the detection and classification of mammary lesions. We used 355 images of fatty breast tissue of IRMA database, with 233 normal instances (no lesion), 72 benign, and 83 malignant cases. Classification was performed by using SVM and ELM networks with modified kernels, in order to optimize accuracy rates, reaching 94.11%. Considering both accuracy rates and training times, we defined the ration between average percentage accuracy and average training time in a reverse order. Our proposal was 50 times higher than the ratio obtained using the best method of the state-of-the-art. As our proposed model can combine high accuracy rate with low learning time, whenever a new data is received, our work will be able to save a lot of time, hours, in learning process in relation to the best method of the state-of-the-art.
© 2013 xxxxxxxx. Hosting by Elsevier B.V. All rights reserved.

1. Introduction Breast cancer is the leading cause of death of women around the world, both in developed and underdevelopment countries [1]. According to the World Health organization (WHO), in 2012, about 1.7 million new cases of breast cancer emerged in the world [1]. Additionally, breast cancer is the most common type of cancer in 140 countries of a total of 182 evaluated nations [1]. The incidence of breast cancer increased 20% between the years 2008 and 2012, as well as mortality rates augmented by around 14% [1]. According to Brazil’s National Institute of Cancer, approximately 30% of cases of breast cancer could be prevented with simple measures such as the adoption of a balanced diet, regular physical activity, and maintenance of the ideal weight [2]. However, the industrial way of life has been contributing for unhealthy lifestyles and obesity increasing, especially in urban and industrialized countries, which is intrinsically related to increasing breast cancer incidence rates in the next decades [1]. Although the amount of breast cancer cases in economically developed regions is increasing, mortality is decreasing due to the availability of early detection technologies, from self-examination campaigns to image-based diagnostic technologies, especially mammography [1]. In underdevelopment countries, however, the increasing incidence of breast cancer has been accompanied by the augment of the mortality rates. In East Africa, the incidence is 30 new cases per 100.00 women per year, whilst in Western Europe and industrialized, economically developed regions of the world, the incidence of breast cancer has reached more than 90 new cases for each group of 100.00 women per year [1]. The mortality rates, however, are almost identical in these two regions, about 15 per 100.00 women [1]. One of the causes is that patients from East Africa do not have easy access to image diagnosis. Therefore, breast cancer is usually detected in advanced stages. Additionally, this fact may lead to the need of mastectomies, mutilating surgeries in which the suspicious mammary tissue is completely remove

…(Full text truncated)…