Are Vision xLSTM Embedded UNet More Reliable in Medical 3D Image Segmentation?

TL;DR

This paper introduces U-VixLSTM, a hybrid CNN and Vision-xLSTM architecture for medical 3D image segmentation that achieves high accuracy with lower computational costs, outperforming current state-of-the-art models.

Contribution

The paper proposes a novel U-VixLSTM architecture combining CNNs with Vision-xLSTM blocks for efficient and reliable medical image segmentation.

Findings

U-VixLSTM outperforms state-of-the-art networks on multiple datasets.

The model achieves high segmentation accuracy with reduced computational costs.

Code is publicly available for reproducibility.

Abstract

The development of efficient segmentation strategies for medical images has evolved from its initial dependence on Convolutional Neural Networks (CNNs) to the current investigation of hybrid models that combine CNNs with Vision Transformers (ViTs). There is an increasing focus on creating architectures that are both high-performing and computationally efficient, capable of being deployed on remote systems with limited resources. Although transformers can capture global dependencies in the input space, they face challenges from the corresponding high computational and storage expenses involved. This research investigates the integration of CNNs with Vision Extended Long Short-Term Memory (Vision-xLSTM)s by introducing the novel U-VixLSTM. The Vision-xLSTM blocks capture the temporal and global relationships within the patches extracted from the CNN feature maps. The convolutional feature reconstruction path upsamples the output volume from the Vision-xLSTM blocks to produce the segmentation output. Our primary objective is to propose that Vision-xLSTM forms an appropriate backbone for medical image segmentation, offering excellent performance with reduced computational costs. The U-VixLSTM exhibits superior performance compared to the state-of-the-art networks in the publicly available Synapse, ISIC and ACDC datasets. Code provided: https://github.com/duttapallabi2907/U-VixLSTM