A Study on the Performance of U-Net Modifications in Retroperitoneal Tumor Segmentation

TL;DR

This paper evaluates various modifications of U-Net, including ViT, Mamba, and xLSTM, for retroperitoneal tumor segmentation, demonstrating that xLSTM offers efficient performance with lower computational costs.

Contribution

It introduces and compares multiple U-Net enhancements, notably the ViLU-Net with ViT blocks, and highlights xLSTM's efficiency in tumor segmentation tasks.

Findings

xLSTM achieves high efficiency with lower resource consumption.

ViLU-Net with ViT blocks improves segmentation accuracy.

The proposed models outperform baseline U-Net on CT datasets.

Abstract

The retroperitoneum hosts a variety of tumors, including rare benign and malignant types, which pose diagnostic and treatment challenges due to their infrequency and proximity to vital structures. Estimating tumor volume is difficult due to their irregular shapes, and manual segmentation is time-consuming. Automatic segmentation using U-Net and its variants, incorporating Vision Transformer (ViT) elements, has shown promising results but struggles with high computational demands. To address this, architectures like the Mamba State Space Model (SSM) and Extended Long-Short Term Memory (xLSTM) offer efficient solutions by handling long-range dependencies with lower resource consumption. This study evaluates U-Net enhancements, including CNN, ViT, Mamba, and xLSTM, on a new in-house CT dataset and a public organ segmentation dataset. The proposed ViLU-Net model integrates Vi-blocks for improved segmentation. Results highlight xLSTM's efficiency in the U-Net framework. The code is publicly accessible on GitHub.