VM-UNet: Vision Mamba UNet for Medical Image Segmentation

2024/02/04 by Jiacheng Ruan, Ruan, Jiacheng, Li, Jincheng +1 · 215 citations
Computer Science · Psychology · #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #FOS: Electrical engineering #Image (mathematics) #Image and Video Processing (eess.IV) #Medical Image Segmentation Techniques #Psychology #Segmentation #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2402.02491

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2024/02/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08

Abstract

In the realm of medical image segmentation, both CNN-based and Transformer-based models have been extensively explored. However, CNNs exhibit limitations in long-range modeling capabilities, whereas Transformers are hampered by their quadratic computational complexity. Recently, State Space Models (SSMs), exemplified by Mamba, have emerged as a promising approach. They not only excel in modeling long-range interactions but also maintain a linear computational complexity. In this paper, leveraging state space models, we propose a U-shape architecture model for medical image segmentation, named Vision Mamba UNet (VM-UNet). Specifically, the Visual State Space (VSS) block is introduced as the foundation block to capture extensive contextual information, and an asymmetrical encoder-decoder structure is constructed with fewer convolution layers to save calculation cost. We conduct comprehensive experiments on the ISIC17, ISIC18, and Synapse datasets, and the results indicate that VM-UNet performs competitively in medical image segmentation tasks. To our best knowledge, this is the first medical image segmentation model constructed based on the pure SSM-based model. We aim to establish a baseline and provide valuable insights for the future development of more efficient and effective SSM-based segmentation systems. Our code is available at https://github.com/JCruan519/VM-UNet.

Cited by

• UltraLBM-UNet: Ultralight Bidirectional Mamba-based Model for Skin Lesion Segmentation
• Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentation
• WDFFU-Mamba: A Wavelet-guided Dual-attention Feature Fusion Mamba for Breast Tumor Segmentation in Ultrasound Images
• TextMamba: Scene Text Detector with Mamba
• Toward Content-based Indexing and Retrieval of Head and Neck CT with Abscess Segmentation
• MasHeNe: A Benchmark for Head and Neck CT Mass Segmentation using Window-Enhanced Mamba with Frequency-Domain Integration
• ReactionMamba: Generating Short & Long Human Reaction Sequences
• UAM: A Unified Attention-Mamba Backbone of Multimodal Framework for Tumor Cell Classification
• Layer-wise Noise Guided Selective Wavelet Reconstruction for Robust Medical Image Segmentation
• Domain-Adaptive Transformer for Data-Efficient Glioma Segmentation in Sub-Saharan MRI
• AFM-Net: Advanced Fusing Hierarchical CNN Visual Priors with Global Sequence Modeling for Remote Sensing Image Scene Classification
• TinyUSFM: Towards Compact and Efficient Ultrasound Foundation Models
• Intelligent Communication Mixture-of-Experts Boosted-Medical Image Segmentation Foundation Model
• Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation
• PC-UNet: An Enforcing Poisson Statistics U-Net for Positron Emission Tomography Denoising
• MambaCAFU: Hybrid Multi-Scale and Multi-Attention Model with Mamba-Based Fusion for Medical Image Segmentation
• An Enhanced Pyramid Feature Network Based on Long-Range Dependencies for Multi-Organ Medical Image Segmentation
• Similarity-Aware Selective State-Space Modeling for Semantic Correspondence
• BALR-SAM: Boundary-Aware Low-Rank Adaptation of SAM for Resource-Efficient Medical Image Segmentation
• Multimodal Slice Interaction Network Enhanced by Transfer Learning for Precise Segmentation of Internal Gross Tumor Volume in Lung Cancer PET/CT Imaging
• Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation
• CMFDNet: Cross-Mamba and Feature Discovery Network for Polyp Segmentation
• Sequential Token Merging: Revisiting Hidden States
• DEPFusion: Dual-Domain Enhancement and Priority-Guided Mamba Fusion for UAV Multispectral Object Detection
• Dual Interaction Network with Cross-Image Attention for Medical Image Segmentation
• CD-Mamba: Cloud detection with long-range spatial dependency modeling
• Rethinking the long-range dependency in Mamba/SSM and transformer models
• SpectMamba: Integrating Frequency and State Space Models for Enhanced Medical Image Detection
• Mitosis detection in domain shift scenarios: a Mamba-based approach
• Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation
• SRMA-Mamba: Spatial Reverse Mamba Attention Network for Pathological Liver Segmentation in MRI Volumes
• Automated Charge Transition Detection in Quantum Dot Charge Stability Diagrams
• ASM-UNet: Adaptive Scan Mamba Integrating Group Commonalities and Individual Variations for Fine-Grained Segmentation
• MedMambaLite: Hardware-Aware Mamba for Medical Image Classification
• Spatiotemporal wall pressure forecast of a rectangular cylinder with physics-aware DeepU-Fourier neural network
• HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning
• HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation
• Multispectral State-Space Feature Fusion: Bridging Shared and Cross-Parametric Interactions for Object Detection
• A Hybrid CNN-VSSM model for Multi-View, Multi-Task Mammography Analysis: Robust Diagnosis with Attention-Based Fusion
• Flatten Wisely: How Patch Order Shapes Mamba-Powered Vision for MRI Segmentation
• U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV
• A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging
• Omni-Fusion of Spatial and Spectral for Hyperspectral Image Segmentation
• Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis
• UltraSAM3: A Concept-Driven Foundation Model for Universal Ultrasound Image Segmentation
• PLUS: Plug-and-Play Enhanced Liver Lesion Diagnosis Model on Non-Contrast CT Scans
• SWinMamba: Serpentine Window State Space Model for Vascular Segmentation
• Medical Image Segmentation Using Advanced Unet: VMSE-Unet and VM-Unet CBAM+
• OSDMamba: Enhancing Oil Spill Detection from Remote Sensing Images Using Selective State Space Model
• Simple is what you need for efficient and accurate medical image segmentation
• MS-UMamba: An Improved Vision Mamba Unet for Fetal Abdominal Medical Image Segmentation
• FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks
• ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration
• Hierarchical Self-Prompting SAM: A Prompt-Free Medical Image Segmentation Framework
• ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation
• HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion
• Zig-RiR: Zigzag RWKV-in-RWKV for Efficient Medical Image Segmentation
• MSLAU-Net: A Hybrid CNN-Transformer Network for Medical Image Segmentation
• CENet: Context Enhancement Network for Medical Image Segmentation
• UNet with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning for Medical Image Segmentation
• Spec2VolCAMU-Net: A Spectrogram-to-Volume Model for EEG-to-fMRI Reconstruction based on Multi-directional Time-Frequency Convolutional Attention Encoder and Vision-Mamba U-Net
• Topo-VM-UNetV2: Encoding Topology into Vision Mamba UNet for Polyp Segmentation
• LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment
• Federated Client-tailored Adapter for Medical Image Segmentation
• Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation
• EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment
• HS-Mamba: Full-Field Interaction Multi-Groups Mamba for Hyperspectral Image Classification
• A Novel Hybrid Approach for Retinal Vessel Segmentation with Dynamic Long-Range Dependency and Multi-Scale Retinal Edge Fusion Enhancement
• Hierarchical Feature Learning for Medical Point Clouds via State Space Model
• Ring Artifacts Correction Based on Global-Local Features Interaction Guidance in the Projection Domain
• Dynamic Vision Mamba
• Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection
• Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation
• Multi-Granularity Vision Fastformer with Fusion Mechanism for Skin Lesion Segmentation

Related

• VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation
• HMT-UNet: A hybird Mamba-Transformer Vision UNet for Medical Image Segmentation
• MSVM-UNet: Multi-Scale Vision Mamba UNet for Medical Image Segmentation
• Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation
• Rotate to Scan: UNet-like Mamba with Triplet SSM Module for Medical Image Segmentation