Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Kyeonghun Kim, Jaehyung Park, Youngung Han, Anna Jung, Seongbin Park, Sumin Lee, Jiwon Yang, Jiyoon Han, Subeen Lee, Junsu Lim, Hyunsu Go, Eunseob Choi, Hyeonseok Jung, Soo Yong Kim, Woo Kyoung Jeong, Won Jae Lee, Pa Hong, Hyuk-Jae Lee, Ken Ying-Kai Liao, Nam-Joon Kim

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.

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

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.

Paper Structure

This paper contains 23 sections, 5 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Dataset
  3. PARTHENON Dataset
  4. Data Preprocessing
  5. Semi-Supervised Pseudo-Label Generation.
  6. Pseudo-Label Quality Filtering.
  7. Label Merging.
  8. Cropping and Augmentation.
  9. Methodology: The MATHENA Framework
  10. MATHE: Mamba-based Architectural Tooth Hierarchical Estimator
  11. Hybrid CNN-SSM Backbone.
  12. Bidirectional Feature Pyramid and Head.
  13. HENA: Holistic Evaluation Network for Anatomy
  14. Lightweight Encoder.
  15. Mamba Bottleneck with GCST.
  16. ...and 8 more sections

Figures (3)

  • Figure 1: Quantitative results on PARTHENON: (a) MATHE variants outperform baseline models in tooth detection (mAP50); (b, c) MATHENA variants show superior Dice scores in CarSeg and AD. ($\dagger$: baseline enhanced with P2, BiFPN, and WIoU).
  • Figure 2: MATHENA architecture: Left shows MATHE backbone, BiFPN, and detection head; Right depicts HENA encoder-decoder with GCST skip fusion. SRA (Spatial Re-Alignment) remaps the output mask to the original OPG for visualization.
  • Figure 3: Visual comparison: Left shows Tooth Detection; Right depicts CarSeg.