Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation
read the original abstract
In recent advancements in medical image analysis, Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have set significant benchmarks. While the former excels in capturing local features through its convolution operations, the latter achieves remarkable global context understanding by leveraging self-attention mechanisms. However, both architectures exhibit limitations in efficiently modeling long-range dependencies within medical images, which is a critical aspect for precise segmentation. Inspired by the Mamba architecture, known for its proficiency in handling long sequences and global contextual information with enhanced computational efficiency as a State Space Model (SSM), we propose Mamba-UNet, a novel architecture that synergizes the U-Net in medical image segmentation with Mamba's capability. Mamba-UNet adopts a pure Visual Mamba (VMamba)-based encoder-decoder structure, infused with skip connections to preserve spatial information across different scales of the network. This design facilitates a comprehensive feature learning process, capturing intricate details and broader semantic contexts within medical images. We introduce a novel integration mechanism within the VMamba blocks to ensure seamless connectivity and information flow between the encoder and decoder paths, enhancing the segmentation performance. We conducted experiments on publicly available ACDC MRI Cardiac segmentation dataset, and Synapse CT Abdomen segmentation dataset. The results show that Mamba-UNet outperforms several types of UNet in medical image segmentation under the same hyper-parameter setting. The source code and baseline implementations are available.
This paper has not been read by Pith yet.
Forward citations
Cited by 18 Pith papers
-
SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition
SurgicalMamba adapts Mamba2 with dual-path SSD, intensity-modulated stepping, and state regramming to reach state-of-the-art online accuracy on seven surgical phase recognition benchmarks while keeping per-frame cost ...
-
SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition
SurgicalMamba achieves SOTA online accuracy on surgical phase recognition benchmarks by adding dual-path SSD, intensity-modulated stepping, and state regramming to Mamba2 while keeping per-frame cost O(d).
-
Bengal-HP_RU: A Dataset of Bengal People For Head Pose Estimation
Bengal-HP_RU is the first publicly available head pose dataset for Bengali subjects, with 12,894 images collected from Wikimedia Commons and partitioned by uploader identity.
-
BiSegMamba: Efficient Bidirectional Tri-Oriented Mamba for 3D Medical Image Segmentation
BiSegMamba is a bidirectional tri-oriented Mamba architecture that improves performance and reduces FLOPs in 3D medical image segmentation across brain, cardiac, abdominal, and vascular tasks.
-
SO-Mamba: State-Ownership Mamba for Unrolled MRI Reconstruction
SO-Mamba introduces state-ownership routing in Mamba regularizers for unrolled MRI reconstruction to separate resident carrier content from non-resident evidence across stages.
-
Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention
Polygon-Mamba achieves F1 scores of 0.8283, 0.8282, and 0.8251 on DRIVE, STARE, and CHASE_DB1 by combining polygon scanning Mamba with space-frequency collaborative attention to better detect small retinal vessels.
-
APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms
APRIL-MedSeg is a new open-source modular toolbox that uses YAML configuration and component registries to unify multiple advanced paradigms for medical image segmentation.
-
Motion-Guided Causal Disentanglement for Robust Multi-View Cine Cardiac MRI Diagnosis
MoViD factorizes multi-view cine cardiac MRI representations into view-specific and disease-discriminative components via dual-branch supervised contrastive objectives, gradient-reversal adversarial constraint, and an...
-
USEMA: a Scalable Efficient Mamba Like Attention for Medical Image Segmentation
USEMA is a hybrid UNet architecture merging CNNs with scalable Mamba-like attention (SEMA) that achieves better efficiency than transformers and superior segmentation accuracy than pure CNN or Mamba models across medi...
-
TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media
TopoMamba improves medical image segmentation by combining topology-aware diagonal scans with standard cross-scans and a HSIC Gate for efficient fusion, yielding gains on thin and curved targets like the pancreas.
-
Unifying VLM-Guided Flow Matching and Spectral Anomaly Detection for Interpretable Veterinary Diagnosis
New public dataset and VLM-guided flow matching segmentation combined with random matrix theory anomaly detection for interpretable canine pneumothorax diagnosis.
-
Enabling Real-Time Colonoscopic Polyp Segmentation on Commodity CPUs via Ultra-Lightweight Architecture
UltraSeg-130K delivers Dice scores above 0.8 on seven polyp datasets at over 30 FPS on a single CPU core using 0.13M parameters, outperforming other sub-0.3M models and approaching larger networks on external tests.
-
Hierarchical Feature Learning for Medical Point Clouds via State Space Model
Presents an SSM-based hierarchical feature learning method for medical point clouds that reports superior performance on classification, completion, and segmentation using a new dataset MedPointS.
-
APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms
Presents APRIL-MedSeg, a modular YAML-configurable toolbox for 2D medical image segmentation integrating semi-supervised, domain adaptation, distillation, weakly supervised, text-guided, and foundation model paradigms...
-
MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection
MambaADv2 evolves Mamba state space models with hybrid blocks, frequency convolutions, and adaptive scanning for improved unsupervised anomaly detection.
-
3D Segment Anything Model with Visual Mamba for Diagnosing Placenta Accreta Spectrum
Introduces the first MRI-based PAS dataset and 3DSAMba, a 3D SAM with adapter, MLAM, and FSSM modules, claiming improved lesion segmentation and PAS diagnosis via released code and data.
-
Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention
Polygon-mamba applies polygon scanning Mamba and space-frequency collaborative attention to retinal vessel segmentation, reporting F1 scores of ~0.828 and AUC ~0.98 on DRIVE, STARE, and CHASE_DB1.
-
Flemme: A Flexible and Modular Learning Platform for Medical Images
Flemme is a modular platform separating encoders (conv/transformer/SSM) from encoder-decoder architectures for medical images, with a hierarchical pyramid loss yielding reported average gains of 5.6% Dice and 5.57% PSNR.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.