Optimized Extreme Learning Machine for Breast Tumor Classification Using Mammograms

Breast cancer is the most invasive cancer type for women, being the second leading cause of cancer-related deaths after lung cancer. Recently, many intelligent approaches have emerged for the effective classification of such deadly diseases; however, optimistic light of research is needed for improved diagnosis. Thus, the work proposed a novel methodology of combining the effective classification ability of extreme learning machine (ELM) with the efficient searching behavior of crowsearch optimization algorithm (CSOA). In this way, an improved crow-search optimization algorithm-based extreme learning machine (ImCSOA-ELM) is proposed for addressing the severity classification of breast tumors. Here, the novelty of the work lies in enhancing the generalization ability of the ELM by using the CSOA with chaotic-based controlled randomness for improved convergence. For the evaluation of the proposed algorithm, two different benchmark datasets namely MIAS and DDSM are used. Further, the proposed framework is validated using a larger FFDM dataset, VinDr-Mammo. The performance comparison of the proposed algorithm with existing classification models (SVM-RBF, ELM, particle swarm optimization-based ELM, and CSOA-based ELM) is done, in which the highest classification accuracy is obtained for the proposed algorithm is 90% (MIAS), 95.4% (DDSM), and 86.04% (VinDr-Mammo) respectively.