Document Type : Review
Authors
1
1.Department of Computer Engineering, Kerman Branch, Islamic Azad University, Kerman, Iran. B.rezai@kmu.ac.ir
2
Department of Computer Engineering, Kerman Branch, Islamic Azad University, Kerman, Iran
3
Department of Computer Engineering, Graduate University of Advanced Technology, Kerman, Iran
10.30476/jhmi.2024.103601.1232
Abstract
Background: Breast cancer detection is critical for timely intervention and treatment. This study proposes a novel hybrid deep learning approach that integrates Convolutional Neural Networks (CNNs) and Residual Number Systems (RNS) to enhance breast cancer detection performance.
Methods: The hybrid model was evaluated on two distinct datasets: INBREAST and MINI-DDSM. Performance metrics such as accuracy, precision, recall, and F1-score were analyzed to assess the model’s effectiveness compared to traditional methods.
Results: The hybrid approach achieved a training accuracy of 99% and validation accuracy of 91.5% on the INBREAST dataset, while the MINI-DDSM dataset yielded training and validation accuracies of 98% and 95.02%, respectively. The model demonstrated superior performance on the MINI-DDSM dataset, outperforming established models like ZFNET and ResNet18 in accuracy, recall, and precision. However, the INBREAST dataset presented challenges due to its complexity, resulting in lower precision and recall despite high overall accuracy.
Conclusion: This study highlights the potential of the proposed hybrid deep learning approach for breast cancer detection, especially in simpler datasets. Future research should focus on techniques such as data augmentation, transfer learning, and ensemble methods to improve robustness and generalizability across diverse imaging scenarios. The findings contribute to the integration of deep learning in medical diagnostics, aiming for more accurate and efficient breast cancer detection systems.
Keywords: breast cancer detection, deep learning, convolutional neural networks, residual number systems, hybrid model
Keywords
Main Subjects
)