Transfer Learning Based Breast Cancer Detection for Telemedicine Systems in Healthare Environment
Ansh Bhavsar, Vansh Patel, Yogi Patel, Rebakah Geddam, Rajesh Gupta, Sudeep Tanwar, Melika Mohammad-Hosseini, Hossein Shahinzadeh · 2024
Breast cancer continues to be a serious challenge all over the world with many lives of women affected globally due to changing societal lifestyle dynamics. Timely detection and accurate diagnosis are crucial for easing its impact as well as guiding treatment towards favorable outcomes. This study proposes a framework to meet these necessities i.e. integration of ResNet-101 model with telemedicine technology making use of transfer learning techniques in detecting and classifying breast cancers. The proposed model signifies a change in the way healthcare services are delivered, where telehealth is utilized to overcome geographical barriers and provide access to medical expertise remotely. The aim of this study is to change how breast cancer care works, by enabling timely diagnosis and intervention irrespective of one’s physical location. Through robust validation and experimentation, impressive accuracy rate of 95.16% was achieved. Apart from new technology, telemedicine can change special health services, especially in places where there is a lack of doctors or hospitals nearby. This methodology combines the power of ResNet-101 model, transfer learning, and telemedicine that facilitate not only early detection of breast cancer but also creates a path in future of healthcare systems.