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

TL;DR

This paper presents a multi-kernel approach combining wavelet decomposition and Zernike moments for effective detection and classification of mammographic masses, achieving high accuracy with reduced training time.

Contribution

The study introduces a novel method integrating multi-resolution wavelets and shape-texture features with modified kernels in SVM and ELM, significantly improving accuracy and efficiency over existing techniques.

Findings

Achieved 94.11% classification accuracy.

Outperformed state-of-the-art methods by 50 times in accuracy-to-training-time ratio.

Reduced training time while maintaining high detection accuracy.

Abstract

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.