Catalyzing medical imaging : Exploring the potentials of deep transfer learning

Abstract

Medical imaging plays a crucial role in modern healthcare by aiding in accurate diagnosis, treatment planning, and disease monitoring. The advancement of deep learning has revolutionized the field of medical image processing, leading to extraordinary breakthroughs in various domains. Among the many subdomains within deep learning, deep transfer learning has emerged as a powerful technique for transferring knowledge between domains, greatly enhancing the accuracy and efficiency of medical image analysis. This paper delves into the evolution of deep transfer learning in the realm of medical imaging. This study delves into leveraging pre-trained models and employing transfer learning techniques - specifically, freezing CNN layers and fine-tuning - on the VGG-16 architecture. The results were impressive, as freezing CNN layers and fine-tuning the VGG-16 model with the MIAS dataset yielded astounding accuracies of 98.33% and 99.89% respectively.