U-Mamba2: Scaling State Space Models for Dental Anatomy Segmentation in CBCT

• URL: http://arxiv.org/abs/2509.12069v2
• Date: Tue, 30 Sep 2025 12:16:30 GMT
• Title: U-Mamba2: Scaling State Space Models for Dental Anatomy Segmentation in CBCT
• Abstract summary: Cone-Beam Computed Tomography (CBCT) is a widely used 3D imaging technique in dentistry.<n>We present U-Mamba2, a new neural network architecture designed for multi-anatomy CBCT segmentation.
• Score: 44.3806898357896
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Cone-Beam Computed Tomography (CBCT) is a widely used 3D imaging technique in dentistry, providing volumetric information about the anatomical structures of jaws and teeth. Accurate segmentation of these anatomies is critical for clinical applications such as diagnosis and surgical planning, but remains time-consuming and challenging. In this paper, we present U-Mamba2, a new neural network architecture designed for multi-anatomy CBCT segmentation in the context of the ToothFairy3 challenge. U-Mamba2 integrates the Mamba2 state space models into the U-Net architecture, enforcing stronger structural constraints for higher efficiency without compromising performance. In addition, we integrate interactive click prompts with cross-attention blocks, pre-train U-Mamba2 using self-supervised learning, and incorporate dental domain knowledge into the model design to address key challenges of dental anatomy segmentation in CBCT. Extensive experiments, including independent tests, demonstrate that U-Mamba2 is both effective and efficient, securing first place in both tasks of the Toothfairy3 challenge. In Task 1, U-Mamba2 achieved a mean Dice of 0.84, HD95 of 38.17 with the held-out test data, with an average inference time of 40.58s. In Task 2, U-Mamba2 achieved the mean Dice of 0.87 and HD95 of 2.15 with the held-out test data. The code is publicly available at https://github.com/zhiqin1998/UMamba2.

Related papers

• BiSegMamba: Efficient Bidirectional Tri-Oriented Mamba for 3D Medical Image Segmentation [6.344197178127241]
  We propose BiSegMamba, an efficient tri-oriented Mamba network for 3D medical image segmentation.<n>BiSegMamba generalizes well across vascular, cardiac, brain tumor, and abdominal multi-organ segmentation tasks.<n>Compared with SegMamba-V2, BiSegMamba achieves slightly better performance on BraTS2023 and clear improvements on ACDC and the carotid dataset.
  arXiv  Detail & Related papers  (2026-05-29T08:13:22Z)
• Adaptive Texture-aware Masking for Self-Supervised Learning in 3D Dental CBCT Analysis [46.96606285805449]
  Cone Beam Computed Tomography (CBCT) is pivotal for 3D diagnostic imaging in dentistry.<n>The development of robust AI models for volumetric analysis is often constrained by the scarcity of large, annotated datasets.<n>We propose ATMask, a novel adaptive masking strategy.
  arXiv  Detail & Related papers  (2026-05-03T06:42:28Z)
• MATHENA: Mamba-based Architectural Tooth Hierarchical Estimator and Holistic Evaluation Network for Anatomy [17.684884393582994]
  Dental diagnosis from Orthopantomograms (OPGs) requires coordination of tooth detection, caries segmentation (CarSeg), anomaly detection (AD) and dental developmental staging (DDS)<n>We propose Mamba-based Architectural Tooth Hierarchical Estor and Holistic Evaluation Network for Anatomy (MATHENA) to address all four tasks.<n>MATHENA integrates MATHENA, a multi-resolution SSM-driven detector with four-directional Vision State Space (VSS) blocks for O(N) global context modeling, generating per-tooth crops.<n>In the triple-head architecture, CarSeg is
  arXiv  Detail & Related papers  (2026-04-01T06:28:52Z)
• A Hybrid Mamba-SAM Architecture for Efficient 3D Medical Image Segmentation [0.4358626952482685]
  Mamba-SAM is a novel and efficient hybrid architecture that combines a frozen SAM encoder with the linear-time efficiency and long-range modeling capabilities of Mamba-based State Space Models (SSMs)<n>We introduce Multi-Frequency Gated Convolution (MFGC), which enhances feature representation by jointly analyzing spatial and frequency-domain information via 3D discrete cosine transforms and adaptive gating.<n>The dual-branch Mamba-SAM-Base model achieves a mean Dice score of 0.906, comparable to UNet++ (0.907), while outperforming all baselines on Myocardium (0.910) and Left Ventric
  arXiv  Detail & Related papers  (2026-01-31T10:51:17Z)
• Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification [69.87877580725768]
  Multimodal Visual Surrogate Compression (MVSC) learns to compress and adapt large 3D sMRI volumes into compact 2D features.<n>MVSC has two key components: a Volume Context that captures global cross-slice context under textual guidance, and an Adaptive Slice Fusion module that aggregates slice-level information in a text-enhanced, patch-wise manner.
  arXiv  Detail & Related papers  (2026-01-29T13:05:46Z)
• When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation [9.108764893521526]
  We present the first comprehensive benchmarking of convolutional neural networks, vision transformers and state-space mamba architectures for automated dental caries segmentation on panoramic radiographs through a DC1000 dataset.<n>Results reveal that, contrary to the growing trend toward complex attention based architectures, the CNN-based DoubleU-Net achieved the highest dice coefficient of 0.7345, mIoU of 0.5978, and precision of 0.8145, outperforming all transformer and Mamba variants.
  arXiv  Detail & Related papers  (2025-11-18T19:16:21Z)
• 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)
• U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT [44.3806898357896]
  We propose U-Mamba2-SSL, a novel semi-supervised learning framework that builds on the U-Mamba2 model and employs a multi-stage training strategy.<n>U-Mamba2-SSL achieved an average score of 0.789 and a DSC of 0.917 on the hidden test set, achieving first place in Task 1 of the STSR 2025 challenge.
  arXiv  Detail & Related papers  (2025-09-24T14:19:33Z)
• Multimodal Contrastive Pretraining of CBCT and IOS for Enhanced Tooth Segmentation [8.574756499299374]
  We present ToothMCL, a Tooth Multimodal Contrastive Learning for pretraining that integrates volumetric (CBCT) and surface-based (IOS) modalities.<n>Our approach effectively models fine-grained anatomical features, enabling precise multi-class segmentation and accurate identification of F'ederation Dentaire Internationale (FDI) tooth numbering.
  arXiv  Detail & Related papers  (2025-09-09T17:05:04Z)
• Multi-Phase Automated Segmentation of Dental Structures in CBCT Using a Lightweight Auto3DSeg and SegResNet Implementation [0.0]
  Cone-beam computed tomography (CBCT) has become an invaluable imaging modality in dentistry, enabling 3D visualization of teeth and surrounding structures for diagnosis and treatment planning.<n>We describe the DLaBella29 team's approach for the MICCAI 2025 ToothFairy3 Challenge, which involves a deep learning pipeline for multi-class tooth segmentation.<n>Key preprocessing steps included image resampling to 0.6 mm isotropic resolution and intensity clipping.<n>Our method achieved an average Dice of 0.87 on the ToothFairy3 challenge out-of-sample validation set.
  arXiv  Detail & Related papers  (2025-08-18T14:35:26Z)
• SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms [60.35639972035727]
  The lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. Dice scores reached up to 0.838 $pm$ 0.066 and 0.716 $pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $pm$ 0.15.
  arXiv  Detail & Related papers  (2024-11-14T17:06:00Z)
• T-Mamba: A unified framework with Long-Range Dependency in dual-domain for 2D & 3D Tooth Segmentation [4.882283647589811]
  Tooth segmentation is fraught with challenges due to the high noise and low contrast inherent in 2D and 3D tooth data. This paper introduces T-Mamba, integrating frequency-based features and shared bi-positional encoding into vision mamba. T-Mamba is the first work to introduce frequency-based features into vision mamba, and its flexibility allows it to process both 2D and 3D tooth data without the need for separate modules.
  arXiv  Detail & Related papers  (2024-04-01T11:57:40Z)
• Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain [46.44049019428938]
  We introduce a new neural network architecture, termed LoGoNet, with a tailored self-supervised learning (SSL) method.<n>LoGoNet integrates a novel feature extractor within a U-shaped architecture, leveraging Large Kernel Attention (LKA) and a dual encoding strategy.<n>We propose a novel SSL method tailored for 3D images to compensate for the lack of large labeled datasets.
  arXiv  Detail & Related papers  (2024-02-09T05:06:58Z)
• TSegFormer: 3D Tooth Segmentation in Intraoral Scans with Geometry Guided Transformer [47.18526074157094]
  Optical Intraoral Scanners (IOSs) are widely used in digital dentistry to provide detailed 3D information of dental crowns and the gingiva. Previous methods are error-prone at complicated boundaries and exhibit unsatisfactory results across patients. We propose TSegFormer which captures both local and global dependencies among different teeth and the gingiva in the IOS point clouds with a multi-task 3D transformer architecture.
  arXiv  Detail & Related papers  (2023-11-22T08:45:01Z)
• AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications [29.065668174732014]
  A critical step in virtual dental treatment planning is to accurately delineate all tooth-bone structures from CBCT. Previous studies have established several methods for CBCT segmentation using deep learning. Here, we present a Deep Dental Multimodal Analysis framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model, and a fusion model to generate 3D fused crown-root-bone structures.
  arXiv  Detail & Related papers  (2022-03-11T07:50:15Z)
• Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans [56.55092443401416]
  emphiMeshSegNet in the first stage of TS-MDL reached an averaged Dice similarity coefficient (DSC) at 0.953pm0.076$, significantly outperforming the original MeshSegNet. PointNet-Reg achieved a mean absolute error (MAE) of $0.623pm0.718, mm$ in distances between the prediction and ground truth for $44$ landmarks, which is superior compared with other networks for landmark detection.
  arXiv  Detail & Related papers  (2021-09-24T13:00:26Z)

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.