Efficient and Precise CNN Based Machine Learning Method for Microwave Medical Imaging in Cancer Detection

Cancer detection is critical for early diagnosis and treatment, and non-invasive imaging methods like microwave imaging have shown promise in this domain. This research presents a CNN-based machine learning model to improve the speed and accuracy of microwave medical imaging for cancer detection. Leveraging large datasets, advanced preprocessing techniques such as noise removal, normalization, and data augmentation were applied. The proposed model includes a multi-layer CNN architecture, optimized using stochastic gradient descent (SGD) and categorical cross-entropy loss functions. Evaluation metrics, including accuracy, sensitivity, and specificity, were calculated from a confusion matrix. The system achieved 95.6% accuracy, 94% sensitivity, and 96% specificity, outperforming traditional models both in terms of accuracy and computational efficiency. The results suggest that the proposed model is well-suited for real-time clinical applications. Future work will focus on expanding the dataset and integrating multimodal imaging to enhance diagnostic precision.