Customized MobileNet with Transfer Learning for Enhanced Early Breast Cancer Detection: A Deep Learning Approach
Nihar Ranjan Panda, Debendra Muduli, Santosh Kumar Sharma · 2024
Breast cancer remains a significant global health issue, and early detection is crucial for improving treatment outcomes. This research introduces a deep learning method for breast cancer detection using histopathological images, utilizing the MobileNet architecture alongside transfer learning techniques. By leveraging a robust dataset, we refined the model's hyperparameters and integrated interpretability features to boost its clinical applicability. Rigorous testing and evaluation showed that our model excels at differentiating between benign and malignant tumors with high precision. Future work will focus on expanding dataset diversity, further optimizing model performance, and performing real-world validation studies to improve early detection and patient outcomes in the diagnosis and treatment of breast cancer. The model achieved a classification accuracy of 92.92%, outperforming other existing models.