CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation

• URL: http://arxiv.org/abs/2511.01243v1
• Date: Mon, 03 Nov 2025 05:27:28 GMT
• Title: CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation
• Abstract summary: CenterMamba-SAM is an end-to-end framework that freezes a pretrained backbone and trains only lightweight adapters for efficient fine-tuning.<n>At its core is the CenterMamba encoder, which employs a novel 3x3 corner-axis-center short-sequence scanning strategy.<n>A memory-driven structural prompt generator maintains a prototype bank across neighboring slices, enabling automatic synthesis of reliable prompts.
• Score: 8.455097722395125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Brain lesion segmentation remains challenging due to small, low-contrast lesions, anisotropic sampling, and cross-slice discontinuities. We propose CenterMamba-SAM, an end-to-end framework that freezes a pretrained backbone and trains only lightweight adapters for efficient fine-tuning. At its core is the CenterMamba encoder, which employs a novel 3x3 corner-axis-center short-sequence scanning strategy to enable center-prioritized, axis-reinforced, and diagonally compensated information aggregation. This design enhances sensitivity to weak boundaries and tiny foci while maintaining sparse yet effective feature representation. A memory-driven structural prompt generator maintains a prototype bank across neighboring slices, enabling automatic synthesis of reliable prompts without user interaction, thereby improving inter-slice coherence. The memory-augmented multi-scale decoder integrates memory attention modules at multiple levels, combining deep supervision with progressive refinement to restore fine details while preserving global consistency. Extensive experiments on public benchmarks demonstrate that CenterMamba-SAM achieves state-of-the-art performance in brain lesion segmentation.

Related papers

• Rad-JEPA 3D: Radiology Joint-Embedding Predictive Model for 3D Computed Tomography [10.665332135327205]
  We introduce Rad-JEPA 3D, a joint-embedding predictive framework that learns volumetric CT representations.<n>To improve the quality of intermediate representations, we propose Hidden States Orthogonal Regularization (HSOR)<n>HSOR aligns student-teacher hidden states and reduces feature redundancy throughout the encoder.
  arXiv  Detail & Related papers  (2026-07-28T19:00:17Z)
• Degradation-Aware Blur-Segmentation of Brain Tumor [6.772154747032075]
  Degradation-Aware Blur-Segmentation Net (DABSeg) is a synchronous deblurring 3D multimodal MRI segmentation network.<n>We propose a feature-domain motion-deblurring stem to compensate for blur and rebalance intensity.<n>System embeds a blur-aware cross-modal cross-attention module and multi-scale residual aggregation to yield effective modality complementarity.
  arXiv  Detail & Related papers  (2026-05-15T06:47:37Z)
• TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media [36.26611641287451]
  TopoMamba is a topology-aware scan-and-fuse framework for segmenting heterogeneous medical visual media.<n>We show that TopoMamba consistently improves segmentation quality over strong CNN, Transformer, and SSM baselines.
  arXiv  Detail & Related papers  (2026-04-28T12:11:58Z)
• Adapting SAM to Nuclei Instance Segmentation and Classification via Cooperative Fine-Grained Refinement [24.433000105666114]
  We propose a parameter-efficient fine-tuning framework, named Cooperative Fine-Grained Refinement of SAM.<n>These three components work cooperatively to enhance local perception, preserve spatial details, and refine boundaries, enabling SAM to perform accurate nuclei instance segmentation directly.
  arXiv  Detail & Related papers  (2026-03-30T04:39:07Z)
• StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models [57.674757786328236]
  StructSAM is a resolution-preserving merge-unmerge framework tailored to Segment Anything Model (SAM)<n>We show that StructSAM reduces encoder FLOPs by 25-30% (up to 40%+ with prompt-aware merging) with minor drops in mIoU/Dice.<n>We also provide a spectral graph coarsening view showing that score-guided merging yields bounded Laplacian spectral distortion compared to random or window-restricted baselines.
  arXiv  Detail & Related papers  (2026-03-07T18:30:58Z)
• Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank [65.00301565190824]
  mname is a plug-and-play training framework that requires no external encoders.<n>mname achieves a state-of-the-art FID of textbf2.40 within 400k steps, significantly outperforming comparable methods.
  arXiv  Detail & Related papers  (2025-12-09T14:39:26Z)
• Memory-Guided Point Cloud Completion for Dental Reconstruction [2.9422243774213075]
  We propose a retrieval-augmented framework for tooth completion that integrates a prototype memory into encoder--decoder pipelines.<n>The memory is optimized end-to-end and self-organizes into reusable tooth-shape prototypes.<n>Our approach provides a simple yet effective way to exploit cross-sample regularities for more accurate and faithful dental point-cloud completion.
  arXiv  Detail & Related papers  (2025-12-03T09:31:07Z)
• VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel [68.24765319399286]
  We present VesSAM, a powerful and efficient framework tailored for 2D vessel segmentation.<n>VesSAM integrates (1) a convolutional adapter to enhance local texture features, (2) a multi-prompt encoder that fuses anatomical prompts, and (3) a lightweight mask decoder to reduce jagged artifacts.<n>VesSAM consistently outperforms state-of-the-art PEFT-based SAM variants by over 10% Dice and 13% IoU.
  arXiv  Detail & Related papers  (2025-11-02T15:47:05Z)
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation [0.9342663938194833]
  MambaX-Net is a novel semi-supervised, dual-scan 3D segmentation architecture.<n>It computes the segmentation for time point t by leveraging the MRI and the corresponding segmentation mask from the previous time point.<n>MambaX-Net was evaluated on a longitudinal AS dataset, and results showed that it significantly outperforms state-of-the-art U-Net and Transformer-based models.
  arXiv  Detail & Related papers  (2025-10-20T13:32:42Z)
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech [51.14752758616364]
  Speech-based depression detection (SDD) is a promising, non-invasive alternative to traditional clinical assessments.<n>We propose HAREN-CTC, a novel architecture that integrates multi-layer SSL features using cross-attention within a multitask learning framework.<n>The model achieves state-of-the-art macro F1-scores of 0.81 on DAIC-WOZ and 0.82 on MODMA, outperforming prior methods across both evaluation scenarios.
  arXiv  Detail & Related papers  (2025-10-05T09:32:12Z)
• Enhancing Dual Network Based Semi-Supervised Medical Image Segmentation with Uncertainty-Guided Pseudo-Labeling [5.1962665598872135]
  This paper proposes a novel semi-supervised 3D medical image segmentation framework based on a dual-network architecture.<n>Specifically, we investigate a Cross Consistency Enhancement module using both cross pseudo and entropy-filtered supervision to reduce the noisy pseudo-labels.<n>In addition, we use a self-supervised contrastive learning mechanism to align uncertain voxel features with reliable class prototypes.
  arXiv  Detail & Related papers  (2025-09-16T13:40:20Z)
• Scalable Segmentation for Ultra-High-Resolution Brain MR Images [9.295998760042169]
  We propose a novel framework that leverages easily accessible, low-resolution coarse labels as spatial references and guidance.<n>Our approach regresses per-class signed distance transform maps, enabling smooth, boundary-aware supervision.<n>We validate our method through comprehensive experiments on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2025-05-27T19:34:55Z)
• MSA-UNet3+: Multi-Scale Attention UNet3+ with New Supervised Prototypical Contrastive Loss for Coronary DSA Image Segmentation [8.850534640462081]
  We propose a Supervised Prototypical Contrastive Loss that fuses supervised and prototypical contrastive learning to enhance coronary DSA image segmentation.<n>We implement the proposed SPCL loss within an MSA-UNet3+: a Multi-Scale Attention-Enhanced UNet3+ architecture.<n> Experiments on a private coronary DSA dataset show that MSA-UNet3+ outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-07T15:35:30Z)
• Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
  We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder.<n>Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder.<n> Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-23T03:21:33Z)
• FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object Detection [9.291995455336929]
  We propose a Focal Token Acquring-and-Scaling Transformer (FASTer)<n>FASTer condenses token sequences in an adaptive and lightweight manner.<n>It significantly outperforms other state-of-the-art detectors in both performance and efficiency.
  arXiv  Detail & Related papers  (2025-02-28T03:15:33Z)
• Center Focusing Network for Real-Time LiDAR Panoptic Segmentation [58.1194137706868]
  A novel center focusing network (CFNet) is introduced to achieve accurate and real-time LiDAR panoptic segmentation. CFFE is proposed to explicitly understand the relationships between the original LiDAR points and virtual instance centers. Our CFNet outperforms all existing methods by a large margin and is 1.6 times faster than the most efficient method.
  arXiv  Detail & Related papers  (2023-11-16T01:52:11Z)
• UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation [93.88170217725805]
  We propose a 3D medical image segmentation approach, named UNETR++, that offers both high-quality segmentation masks as well as efficiency in terms of parameters, compute cost, and inference speed. The core of our design is the introduction of a novel efficient paired attention (EPA) block that efficiently learns spatial and channel-wise discriminative features. Our evaluations on five benchmarks, Synapse, BTCV, ACDC, BRaTs, and Decathlon-Lung, reveal the effectiveness of our contributions in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2022-12-08T18:59:57Z)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.