Pith. sign in

REVIEW 9 cited by

Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.05079 v2 pith:7PA6OBNO submitted 2024-02-07 eess.IV cs.CV

Ziyang Wang , Jian-Qing Zheng , Yichi Zhang , Ge Cui , Lei Li This is my paper · ORCID
classification eess.IVcs.CV
keywords segmentationmedicalimagemambamamba-unetinformationarchitectureavailable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CARDIAG: A Dense Segment Classification Benchmark of Deep Learning Architectures for Coronary Angiography

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A new public coronary-angiography benchmark finds ConvNeXt V2 + DeepLabV3+ is the best single model (macro F1 = 0.456), with a three-model ensemble reaching 0.479.

  2. Frequency-Hierarchical Active k-Space Sampling for Diagnostic MRI

    cs.CV 2026-07 conditional novelty 6.0 of 10

    HieraSample, a Mamba-based frequency-hierarchical active sampler, matches fully-sampled ACL diagnosis AUC at 4-10x acceleration on fastMRI+ knee MRI.

  3. Adaptive Gate-Aware Mamba Networks for Magnetic Resonance Fingerprinting

    eess.IV 2025-07 conditional novelty 6.0 of 10

    GAST-Mamba, a Mamba-based network with a spatial-temporal gate, improves simulated and qualitative in vivo MRF T1/T2 reconstruction over SCQ, LG-ViT, CONV-ICA, and MRF-Mixer.

  4. QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models

    cs.CV 2025-07 conditional novelty 5.0 of 10

    QuarterMap prunes spatial activations before VMamba's four-directional scan and upsamples after, yielding up to 1.11x throughput with under 1% accuracy loss on ImageNet classification.

  5. HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion

    cs.CV 2025-05 conditional novelty 5.0 of 10

    HTMNet combines a CNN-Transformer encoder, a Transformer-Mamba bottleneck fusion block, and a multi-scale attention decoder to improve depth completion for transparent and reflective objects, claiming state-of-the-art...

  6. SFD-Mamba2Net: Structure-Guided Frequency-Enhanced Dual-Stream Mamba2 Network for Coronary Artery Segmentation

    cs.CV 2025-09 conditional novelty 4.0 of 10

    SFD-Mamba2Net combines Hessian vesselness priors, a dual-stream Mamba2 module, and wavelet high-frequency enhancement to segment coronary arteries and detect stenoses in angiography, reporting improved Dice and stenos...

  7. MambaVesselNet++: A Hybrid CNN-Mamba Architecture for Medical Image Segmentation

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A CNN-Mamba U-shape model, extended from the authors' MambaVesselNet, reports state-of-the-art segmentation on six public medical datasets, though some table entries contradict the text.

  8. MS-UMamba: An Improved Vision Mamba Unet for Fetal Abdominal Medical Image Segmentation

    cs.CV 2025-06 conditional novelty 4.0 of 10

    MS-UMamba, a hybrid CNN-Mamba U-Net with an attention-based fusion module, reports mIoU 67.62 and mDice 79.82, exceeding VM-UNet and other baselines on a private fetal ultrasound dataset.

  9. SAMba-UNet: SAM2-Mamba UNet for Cardiac MRI in Medical Robotic Perception

    cs.CV 2025-05 conditional novelty 4.0 of 10

    A combined SAM2, Mamba, and UNet architecture reports state-of-the-art Dice of 0.9103 on the ACDC cardiac MRI benchmark, with no code or error bars yet released.

Pith tools