Medical Image Analysis for Tumor Segmentation Using U-Net Variants

Abstract: Accurate tumor segmentation from medical images is critical for diagnosis, treatment planning, and prognosis assessment in oncology. With the advent of deep learning, U-Net and its variants have demonstrated remarkable performance in medical image segmentation tasks. This study investigates the comparative effectiveness of U-Net variants—Vanilla U-Net, Attention U-Net, and Residual U-Net—on publicly available datasets such as BraTS and ISIC. By applying various preprocessing techniques and using Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) for evaluation, we identify significant improvements in segmentation accuracy. Our findings show that the Attention U-Net outperforms others, achieving an average DSC of 0.89 and IoU of 0.83, suggesting its suitability for clinical deployment. Keywords: Medical imaging, tumor segmentation, U-Net, deep learning, Attention U-Net, Residual U-Net, BraTS, ISIC, DSC, IoU