Next-Gen Breast Cancer Prediction Through Adaptive Deep Learning
Pandarinath Potluri, Kavyashree Nagarajaiah, K. Packia Lakshmi, Manjula Moolbharathi, Nagaratnamma, Allam Balaram · 2025
This study enhances the ongoing advancements in breast cancer diagnostic tools by highlighting the importance of employing adaptive deep learning and optimization strategies to achieve high accuracy rates. Advancements in medical technology have facilitated early diagnosis and enhanced treatment outcomes for breast cancer, potentially providing doctors with a valuable tool for early detection that could significantly improve patient outcomes. This study introduces a novel approach, Learning Assisted Breast Cancer Prediction (LABCP), which incorporates an advanced ensemble of Cascaded Inception Model and the Ant Lion Optimization algorithm. The proposed adaptive deep learning scheme harnesses the power of deep neural networks to enhance breast cancer prediction accuracy. The experimental evaluation demonstrates outstanding predictive performance, with an accuracy of 98%. The Cascaded Inception Model effectively captures intricate features within breast cancer images, while the Ant Lion Optimization algorithm optimizes the model parameters, further refining the predictive capability. The combination of these techniques results in a robust and efficient system for early breast cancer detection.