CNN - Based Breast Cancer detection using Noninvasive methods

• Published in: 2024 Tenth International Conference on Bio Signals, Images, and Instrumentation (ICBSII) pp. 1 - 5
• Main Authors: Harish, M. Neela, Sathish, S., K, Dharun, R, Keerthivasan, V, Rudhresh
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.03.2024
• Subjects: Benign; Breast cancer; CNN; Computed tomography; Convolutional neural networks; Deep learning; Image Processing; Instruments; Location awareness; Malignant; Mammography
• ISSN: 2768-6450
• DOI: 10.1109/ICBSII61384.2024.10564089

One of the foremost reason for the maximum number of female deaths in world is due to the breast cancer. According to WHO, one among eight women is affected by breast cancer worldwide. This study introduces an advanced non-invasive method for detecting and classifying breast cancer using deep learning. Utilizing CT mammogram images, the research aims to implement a Convolutional neural network (CNN) along with a Region Proposal Network (RPN) for precise localization. The model first pinpoints potential cancerous regions and then classifies them into specific types. Tested on diverse datasets, our approach outperforms traditional methods. By accurately identifying cancer and its subtypes, our model promises to enhance early diagnosis and aid in personalized treatment. This research marks a significant step toward improving breast cancer detection, paving the way for more effective healthcare interventions and better patient outcomes. The proposed framework stands as a promising advancement in the realm of medical diagnostics, contributing to improved patient outcomes and more efficient healthcare interventions.