Transformer Skip‐Fusion Based SwinUNet for Liver Segmentation From CT Images

ABSTRACT Liver segmentation is a crucial step in medical image analysis and is essential for diagnosing and treating liver diseases. However, manual segmentation is time‐consuming and subject to variability among observers. To address these challenges, a novel liver segmentation approach, SwinUNet with transformer skip‐fusion is proposed. This method harnesses the Swin Transformer's capacity to model long‐range dependencies efficiently, the U‐Net's ability to preserve fine spatial details, and the transformer skip‐fusion's effectiveness in enabling the decoder to learn intricate features from encoder feature maps. In experiments using the 3DIRCADb and CHAOS datasets, this technique outperformed traditional CNN‐based methods, achieving a mean DICE coefficient of 0.988% and a mean Jaccard coefficient of 0.973% by aggregating the results obtained from each dataset, signifying outstanding agreement with ground truth. This remarkable accuracy in liver segmentation holds significant promise for improving liver disease diagnosis and enhancing healthcare outcomes for patients with liver conditions.