An Empirical Analysis of Encoder-Decoder (U-Net) Variants for Medical Image Segmentation

Abstract

U-Net convolutional neural networks have become a cornerstone in medical image processing, particularly for complex segmentation tasks. However, with the proliferation of various U-Net variants, it is imperative to evaluate their performance across diverse medical datasets to determine the most suitable architecture for specific applications. This study presents a comprehensive empirical analysis of six U-Net variants namely; U-Net, U-Net++, ResU-Net, TransU-Net, V-Net, and U-Net 3+, focusing on their effectiveness in medical image segmentation. The research used two publicly available medical image datasets: the Breast Cancer Ultrasound dataset and the Brain MRI FLAIR dataset. These datasets were selected to represent a range of challenges in medical imaging, including varying levels of noise, contrast, color channels, and lesion visibility. Each U-Net variant was trained and evaluated under consistent experimental conditions, with the Dice Similarity Coefficient (DSC), Jaccard Index and accuracy serving as the primary evaluation metrics. The findings reveal that while all U-Net variants exhibit strong performance, ResU-Net consistently outperformed other architectures across both datasets. Specifically, ResU-Net achieved the highest Jaccard Index and DSC values, recording 0.5158 and 0.5930 for the Breast Cancer Ultrasound dataset and 0.7923 and 0.8730 for the Brain MRI dataset, respectively. Additionally, ResU-Net demonstrated the highest accuracy of 96.20% in the Breast Ultrasound dataset and emerged as the first runner-up in the Brain MRI dataset with an accuracy of 99.70%, trailing slightly behind U-Net++, which achieved 97.72%. Conversely, U-Net 3+ registered the lowest performance in both datasets. ResU-Net's superior performance suggests that its residual connections enhance feature propagation and mitigate the vanishing gradient problem, leading to better segmentation outcomes. Conversely, U-Net 3+ showed lower performance, indicating that complexity doesn’t always equate to better results. This study offers insights into the strengths and weaknesses of different U-Net variants, guiding practitioners in choosing the most suitable model for their specific applications especially in medical image processing domain.