Boosted Nutcracker optimizer and Chaos Game Optimization with Cross Vision Transformer for medical image classification

Abstract

This paper presents an alternative breast cancer classification method based on enhancing the efficiency of the Nutcracker optimizer (NO) algorithm using Chaos Game Optimization (CGO). In addition, we use the Cross Vision Transformer to extract features from breast images. After that, the relevant features are allocated using the modified version of NO based on CGO. This modification aims to enhance the exploration ability of the NO algorithm to discover the region of a feasible solution (an optimal subset of features). The performance of the developed model is validated by using twelve functions from the CEC2022 benchmark and comparing the results with traditional CGO and NO algorithms. In addition, to assess the applicability of the developed technique, a set of three datasets, and the results were compared with other techniques. The results illustrate the high ability of the developed method to enhance the detection of breast cancer and find the optimal solution of CEC2022 functions according to different performance measures.