Agoes Santika Hyperastuty, Anik Nur Handayani, Heru Wahyu Herwanto
Breast cancer remains one of the most prevalent causes of mortality among women worldwide. Histopathological grading is crucial for assessing tumor aggressiveness and determining appropriate treatment strategies. However, manual grading performed by pathologists is time-consuming and prone to inter-observer variability. This study proposes an automated grading approach using the AlexNet convolutional neural network (CNN) to classify histopathological images of breast cancer into Grade I, II, and III. Preprocessing steps, including augmentation, resizing, and normalization, were applied before training and testing. The model achieved 97% training accuracy and 94% validation accuracy, with balanced precision and recall, demonstrating robust feature extraction and generalization capability. The findings indicate that the proposed approach can support pathologists by providing objective and efficient grading results for breast cancer diagnosis. © 2025 IEEE.
Universitas Negeri, Malang, Indonesia; Universitas Negeri Malang, Malang, Indonesia
