Advancing Breast Cancer Detection with Convolutional Neural Networks: A Comparative Analysis of MIAS and DDSM Datasets

• Published in: 2024 IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP) Vol. 1; pp. 194 - 199
• Main Authors: Alhsnony, Farag H., Sellami, Lamia
• Format: Conference Proceeding
• Language: English
• Published: IEEE 11-07-2024
• Subjects: Accuracy; Adaptation models; Breast cancer; Breast Cancer Detection; CNN; Deep learning; Delta-sigma modulation; Image processing; Mammographic Imaging; Refining
• ISSN: 2687-878X
• DOI: 10.1109/ATSIP62566.2024.10638886

In this research, we present a Convolutional Neural Network (CNN) model designed to improve the detection and classification of breast cancer from mammographic images. By categorizing images as normal, benign, or malignant, our simplified CNN model aims to increase the precision and speed of breast cancer screenings. The effectiveness of the model was validated using established MIAS and DDSM datasets, where it achieved impressive precision rates of 94.23% and 95.53%, respectively. Moreover, the model's performance further improved, reaching an accuracy of 96.67%, when assessed on a combined dataset. These results demonstrate the considerable potential of leveraging CNN-based deep learning techniques to enhance early detection practices in breast cancer care, offering new prospects for clinical application and advancements in medical imaging technologies.