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

•We propose a method to detect and classify mammographic lesions using the regions of interest of images.•We use multi-resolution wavelets and Zernike moments as extract feature extractor image stage.•We can combine both texture and shape features, which can be applied both to the detection and classification of mammary lesions.•Considering the ratio between accuracy and training time, our proposal proved to be 50 times superior to state-of-the-art approaches.•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 approaches.

Background and ObjectiveAccording 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.MethodsHerein 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.ResultsClassification 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 state-of-the-art approaches.ConclusionsAs 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.