MATHENA: Mamba-based Architectural Tooth Hierarchical Estimator and Holistic Evaluation Network for Anatomy

• URL: http://arxiv.org/abs/2604.00537v1
• Date: Wed, 01 Apr 2026 06:28:52 GMT
• Title: MATHENA: Mamba-based Architectural Tooth Hierarchical Estimator and Holistic Evaluation Network for Anatomy
• Abstract summary: 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
• Score: 17.684884393582994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dental diagnosis from Orthopantomograms (OPGs) requires coordination of tooth detection, caries segmentation (CarSeg), anomaly detection (AD), and dental developmental staging (DDS). We propose Mamba-based Architectural Tooth Hierarchical Estimator and Holistic Evaluation Network for Anatomy (MATHENA), a unified framework leveraging Mamba's linear-complexity State Space Models (SSM) to address all four tasks. MATHENA integrates MATHE, a multi-resolution SSM-driven detector with four-directional Vision State Space (VSS) blocks for O(N) global context modeling, generating per-tooth crops. These crops are processed by HENA, a lightweight Mamba-UNet with a triple-head architecture and Global Context State Token (GCST). In the triple-head architecture, CarSeg is first trained as an upstream task to establish shared representations, which are then frozen and reused for downstream AD fine-tuning and DDS classification via linear probing, enabling stable, efficient learning. We also curate PARTHENON, a benchmark comprising 15,062 annotated instances from ten datasets. MATHENA achieves 93.78% mAP@50 in tooth detection, 90.11% Dice for CarSeg, 88.35% for AD, and 72.40% ACC for DDS.

Related papers

• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• U-Mamba2: Scaling State Space Models for Dental Anatomy Segmentation in CBCT [44.3806898357896]
  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.
  arXiv  Detail & Related papers  (2025-09-15T15:52:43Z)
• DeSamba: Decoupled Spectral Adaptive Framework for 3D Multi-Sequence MRI Lesion Classification [0.6749750044497732]
  DeSamba is a framework designed to extract decoupled representations and adaptively fuse spatial and spectral features for lesion classification.<n>DeSamba achieves 62.10% Top-1 accuracy, 63.62% F1-score, 87.71% AUC, and 93.55% Top-3 accuracy on an external validation set.
  arXiv  Detail & Related papers  (2025-07-21T10:42:21Z)
• Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge [55.252714550918824]
  AortaSeg24 MICCAI Challenge introduced the first dataset of 100 CTA volumes annotated for 23 clinically relevant aortic branches and zones.<n>This paper presents the challenge design, dataset details, evaluation metrics, and an in-depth analysis of the top-performing algorithms.
  arXiv  Detail & Related papers  (2025-02-07T21:09:05Z)
• CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localization [1.8705038743447968]
  We present CHaRM, the first fully end-to-end deep learning approach for tooth landmark detection in 3D IOS.<n> CHaRM integrates four components: a point cloud encoder, a teeth-presence classification head, and the novel CHaR module.<n>Unlike two-stage that segment teeth before landmarking, CHaRM operates directly on IOS point clouds.
  arXiv  Detail & Related papers  (2025-01-22T18:35:57Z)
• OralBBNet: Spatially Guided Dental Segmentation of Panoramic X-Rays with Bounding Box Priors [34.82692226532414]
  OralBBNet is designed to improve the accuracy and robustness of tooth classification and segmentation on panoramic X-rays.<n>Our approach achieved a 1-3% improvement in mean average precision (mAP) for tooth detection compared to existing techniques.<n>Results of this study establish a foundation for the wider implementation of object detection models in dental diagnostics.
  arXiv  Detail & Related papers  (2024-06-06T04:57:29Z)
• A Deep Learning Approach to Teeth Segmentation and Orientation from Panoramic X-rays [0.0]
  We present a comprehensive approach to teeth segmentation and orientation from panoramic X-ray images, leveraging deep-learning techniques.<n>We built an end-to-end instance segmentation network that uses an encoder-decoder architecture reinforced with grid-aware attention gates.<n>We introduce oriented bounding box (OBB) generation through principal component analysis (PCA) for precise tooth orientation estimation.
  arXiv  Detail & Related papers  (2023-10-26T06:01:25Z)
• Semantic segmentation of surgical hyperspectral images under geometric domain shifts [69.91792194237212]
  We present the first analysis of state-of-the-art semantic segmentation networks in the presence of geometric out-of-distribution (OOD) data. We also address generalizability with a dedicated augmentation technique termed "Organ Transplantation" Our scheme improves on the SOA DSC by up to 67 % (RGB) and 90 % (HSI) and renders performance on par with in-distribution performance on real OOD test data.
  arXiv  Detail & Related papers  (2023-03-20T09:50:07Z)
• CNN-based fully automatic wrist cartilage volume quantification in MR Image [55.41644538483948]
  The U-net convolutional neural network with additional attention layers provides the best wrist cartilage segmentation performance. The error of cartilage volume measurement should be assessed independently using a non-MRI method.
  arXiv  Detail & Related papers  (2022-06-22T14:19:06Z)
• 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.