What question did this study set out to answer?

The aim is to evaluate and compare CNN architectures for accurate segmentation of liver and tumor regions in CT scans.

May 22, 2026Open Access

Optimized U 3 -Net framework for multi-class liver and tumor segmentation: a comparative study with boundary-aware clinical metrics

Key Points

The aim is to evaluate and compare CNN architectures for accurate segmentation of liver and tumor regions in CT scans.
Implemented strategic oversampling and extensive data augmentation to manage class imbalance and sample scarcity.
Utilized a hybrid loss function (Focal and Dice loss) to improve sensitivity to small tumor boundaries.
Compared performance using metrics such as DSC, IoU, HD95, ASSD, and RAVD on the LiTS dataset.
U3-Net achieved a Dice score of 0.97 for Liver Segmentation and 0.95 for Tumor Segmentation.
Outperformed U-Net and U2-Net in clinical metric evaluation.
Demonstrated superior boundary awareness compared to previous models.

Abstract

Accurate segmentation of liver and tumor regions in Computed Tomography (CT) scans is fundamental for the effective diagnosis and surgical planning of hepatic malignancies. This study evaluates and compares three sophisticated Convolutional Neural Network (CNN) architectures—U-Net, U 2 -Net, and U 3 -Net—for the automated multi-class segmentation of background, liver, and tumor tissues. To address the inherent challenge of class imbalance and the scarcity of lesion samples, we implemented a strategic oversampling technique combined with extensive data augmentation. The models were optimized using a hybrid loss function (integrating Focal and Dice loss) to enhance sensitivity toward small and irregular tumor boundaries. Quantitative assessment was performed using a comprehensive suite of metrics, including overlap-based measures such as Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) as well as boundary-based clinical measures including the 95th percentile Hausdorff Distance (HD95), Average Symmetric Surface Distance (ASSD), and Relative Absolute Volume Difference (RAVD). Experimental results on the LiTS dataset demonstrate that U 3 -Net achieves superior performance, resulting in a Dice score of 0.97 for Liver Segmentation (LS) and 0.95 for Tumor Segmentation (TS).

Bookmark

View Full Paper