Venue: N/A
Year: 2020
Abstract
Breast cancer is one of the deadliest forms of cancer for women. The disease has a good prognosis when diagnosed early. The gold standard for the diagnosis of breast cancer is mammography imaging analysis. However, the acquisition of mammograms involves a painful and embarrassing procedure, with breast compression. Alternative methods have been investigated in the last years, including breast thermographs, which do not involve ionizing radiation, pain or contact with the breast. However, the performance of these modern techniques still needs to be improved to allow widespread use in practical applications. Machine learning techniques have contributed to increase accuracy and reduce false positives and false negatives in the analysis of breast thermograms. We propose a methodology for the detection and classification of breast lesions using a database of real images of Brazilian patients. We divide our methodology into three steps. In the first step, shape and texture characteristics of breast thermograms are extracted using the moments of Zernike and Haralick. The second step is the feature selection process using multi-objective binary optimization algorithms based on swarm intelligence. The third step is the analysis of the classification of the best vectors using Convolutive Neural Networks, Extreme Learning Machines and Support Vector Machines. Finally, we discuss the computational time and performance of various techniques based on swarm intelligence, artificial neural networks and statistical models to improve the time and accuracy of the breast cancer diagnosis. We perform additional analysis of shape and texture characteristics. We discuss the use of multi-objective fish school search algorithms to select characteristics extracted from thermography images. From the results, we observe the feature selection process has helped us to decrease computational time, with a high potential to improve diagnostic accuracy.
Additional information
Mariana Macedo, Carmelo Bastos-Filho, and Ronaldo Menezes. Improved Multi-Objective Binary Fish School for Feature Selection, in Florida Artificial Intelligence Research Society Conference, 2018