Evaluating The Impact Of Transfer Learning Vs Fine-Tuning In Medical Image Segmentation

Abstract

This study investigates the impact of transfer learning and fine-tuning on the performance of medical image segmentation tasks across different imaging modalities, including MRI, CT, and ultrasound. Leveraging pre-trained models such as U-Net, ResNet, and VGG16, we conduct extensive experiments to compare the efficacy of transfer learning against fine-tuning in segmenting brain tumors, livers, and kidneys. Our results demonstrate that while transfer learning provides a strong baseline for medical image analysis, fine-tuning consistently enhances model performance, leading to significant improvements in Dice coefficient, Intersection over Union (IoU), precision, and recall across all datasets. These findings underscore the importance of fine-tuning in adapting pre-trained models to the unique challenges of medical imaging, offering valuable insights for developing more accurate and reliable segmentation models in clinical practice.