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, 2026PLoS ONEOpen Access

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

View Full Paper

Ask AI

Bookmark

Authors

Analysis demonstrates improved classification performance in breast cancer images, suggesting effective diagnosis support for health experts.

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.

Rajeena et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

February 11, 2026PLoS ONEOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Analysis demonstrates improved classification performance in breast cancer images, suggesting effective diagnosis support for health experts.

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.

Rajeena et al. (2026) studied this question.

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark