U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

By Jun Ma, Feifei Li, Bo Wang. arXiv.org, 2024

896 citations recorded by the source corpus.

Convolutional Neural Networks (CNNs) and Transformers have been the most popular architectures for biomedical image segmentation, but both of them have limited ability to handle long-range dependencies because of inherent locality or computational complexity. To address this challenge, we introduce U-Mamba, a general-purpose network for biomedical image segmentation. Inspired by the State Space Sequence Models (SSMs), a new family of deep sequence models known for their strong capability in handling long sequences, we design a hybrid CNN-SSM block that integrates the local feature extraction power of convolutional layers with the abilities of SSMs for capturing the long-range dependency. Moreover, U-Mamba enjoys a self-configuring mechanism, allowing it to automatically adapt to various datasets without manual intervention. We conduct extensive experiments on four diverse tasks, including the 3D abdominal organ segmentation in CT and MR images, instrument segmentation in endoscopy images, and cell segmentation in microscopy images. The results reveal that U-Mamba outperforms state-of-the-art CNN-based and Transformer-based segmentation networks across all tasks. This opens new avenues for efficient long-range dependency modeling in biomedical image analysis. The code, models, and data are publicly available at https://wanglab.ai/u-mamba.html.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/c1a04730c83967d0bb904b02263b17893cb50bad

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

MambaIR: A Simple Baseline for Image Restoration with State-Space Model (2024, background): “Moreover, there are also pioneering works that adopt Mamba to vision tasks such as image classification [44, 92], video understanding [37, 66], biomedical image segmentation [48,71] and others [28,31,56,59,76].”
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model (2024, neutral): “[45] proposes U-Mamba, a hybrid CNN-SSM architecture, to handle the long-range dependencies in biomedical image segmentation.”
VM-UNet: Vision Mamba UNet for Medical Image Segmentation (2024, positive): “Building on the foundation of classical SSM [17] research, the modern SSMs (e.g., Mamba [13]) not only establish long-distance dependencies but also exhibit linear complexity with respect to input size.”
MambaHSI: Spatial–Spectral Mamba for Hyperspectral Image Classification (2025, background): “U-Mamba [25] combined Mamba with U-shaped architecture for biomedical image segmentation.”
VideoMamba: State Space Model for Efficient Video Understanding (2024, neutral): “Mamba’s potential has motivated a series of works [11,28,30, 32, 46, 50, 56, 79, 80, 88, 91], demonstrating better performance and higher GPU e ﬃ ciency than Transformers on visual tasks like object detection and semantic segmentation.”
Gated Linear Attention Transformers with Hardware-Efficient Training (2023, background): “…(especially modalities with long-range dependencies), in line with recent work on applying state-of-the-art state-space models to other types of data (Yan et al., 2023; Zhu et al., 2024; Ma et al., 2024; Liu et al., 2024; Xing et al., 2024; Wang et al., 2024a;b; Yang et al., 2024, inter alia ).”
nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation (2024, methodology): “One example is coupling the claimed innovation with residual connections in the encoder while the base-line uses a vanilla CNN encoder [26].”
SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation (2024, methodology): “U-Mamba [17] integrates the Mamba layer into the encoder of nnUNet [9] to enhance general medical image segmentation.”
U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation (2024, methodology): “For medical image segmentation, U-Mamba [56] and SegMamba [88] have proposed task-specific architectures with Mamba blocks respectively based on nn-UNet [32] and Swin UNETR [22], respectively, achieving promising results in various visual tasks and demonstrating the potential of SSMs in vision.”
LocalMamba: Visual State Space Model with Windowed Selective Scan (2024, positive): “Leveraging Mamba’s foundation in generic models, new methodologies have been developed for visual tasks, such as image segmentation [30, 34, 40, 54] and image synthetic [14], showcasing the adaptability and effectiveness of visual Mamba models in addressing complex vision challenges.”
PointMamba: A Simple State Space Model for Point Cloud Analysis (2024, background): “Besides, the great potential of Mamba motivates a series of work across diverse domains, including graph [50, 3], medical segmentation [36, 34], video understanding [30, 7] and generative models [29, 31].”
Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining (2024, neutral): “We report the results of nnFormer [31] based on official implementation and the other baseline results were referenced from [18].”