What question did this study set out to answer?

This research aims to enhance breast cancer image classification through feature optimization using a modified ResNet-50.

February 11, 2026Open Access

Breast cancer inter-image dissimilarity by feature optimization: An application of novel flea optimization algorithm

PRP.P. Fathimathul RajeenaKing Faisal University MYMuhammad YasirHITEC University MAMona Al AliKing Faisal University

Key Points

This research aims to enhance breast cancer image classification through feature optimization using a modified ResNet-50.
Utilized a modified ResNet-50 model for feature extraction from breast tissue biopsy slides.
Reduced the model layers from 177 to 146 by minimizing activation and number of convolutional filters.
Applied a novel Flea optimization algorithm for extracting global image features.
Conducted inter-image dissimilarity evaluation for class compactness and separation.
Measured performance using metrics such as accuracy, precision, recall, F1 score, and statistical analysis.
Achieved accuracy rates of 99.20%, 99.62%, 99.50%, and 99.34% at different magnifications of 40×, 100×, 200×, and 400× respectively.
Showed superior performance compared to other models like DenseNet, VGG, and Multi-task CNN.
Reported improved classification metrics including precision and recall, indicating enhanced reliability of the diagnostic framework.

Abstract

Background/Objective: Breast cancer is a serious disease that has caused thousands of deaths around the world. According to the American Cancer Society, more than 40,000 women and about 600 men lost their lives due to breast cancer in 2021, and it increased to 43,700 women and 530 men until 2023. Method : In this paper, a modified version of ResNet-50 has been exploited to extract features from breast tissue biopsy slides, contained in the BreakHis public dataset. The standard 177 layer model is amended upto 146 layers by reducing redundant activation, normalization operations and number of convolutional filters without compromising representational capacity. As a result the computational efficiency is achieved along with reduction in learnable parameters from 23.7M to 16.8M. The features vector is extracted using novel Flea optimization Algorithm that performs exploration from a d-dimensional search space to get global features. An inter-image dissimilarity evaluation has been performed to find out class compactness and separation, demonstrating its crucial role in achieving better classification performance. The results of the proposed framework are obtained on various performance indicators including average accuracy, precision, recall, F1 score etc while the statistical analysis is made to see the reliability of the framework based on MCC, Cohen’s Kappa and t-test. Results: The results of the proposed method are compared with DenseNet, VGG, CNN with LSTM, Primal Dual Multi-instance SVM, Single Task CNN and Multi Task CNN and shown dominance on various performance measures. An accuracy of 99.20% was achieved at 40× magnification, 99.62% at 100× magnification, 99.50% at 200× magnification, 99.34% at 400× magnification, respectively. Conclusions: The proposed approach, implemented on the real hardware, can provide an alternate to health experts in diagnosing breast cancer in the early stages.

AI에게 질문

Bookmark

View Full Paper