Fuzzy Residual-ShuffleNet Detects Breast Cancer on Mammography

A Fuzzy Residual-ShuffleNet deep learning model achieved 94.999% accuracy, 95.899% sensitivity, and 93.889% specificity for breast cancer detection on mammograms in a retrospective study.

• The Fuzzy RS-Net model combines Deep Residual Network, Fuzzy logic, and ShuffleNet for feature extraction and classification.
• On a retrospective dataset of mammogram images, the model achieved accuracy of 94.999%, sensitivity of 95.899%, and specificity of 93.889%.
• Preprocessing included wavelet domain filtering, O-SegNet segmentation, and data augmentation via rotation, shifting, and erasing.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.