Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

FDNet: Feature Decoupled Segmentation Network for Tooth CBCT Image

Xiang Feng, Chengkai Wang, Chengyu Wu, Yunxiang Li, Yongbo He, Shuai Wang, Yaiqi Wang

TL;DR

This paper proposes FDNet, a Feature Decoupled Segmentation Network, to excel in the face of the variable dental conditions encountered in CBCT scans, such as complex artifacts and indistinct tooth boundaries.

Abstract

Precise Tooth Cone Beam Computed Tomography (CBCT) image segmentation is crucial for orthodontic treatment planning. In this paper, we propose FDNet, a Feature Decoupled Segmentation Network, to excel in the face of the variable dental conditions encountered in CBCT scans, such as complex artifacts and indistinct tooth boundaries. The Low-Frequency Wavelet Transform (LF-Wavelet) is employed to enrich the semantic content by emphasizing the global structural integrity of the teeth, while the SAM encoder is leveraged to refine the boundary delineation, thus improving the contrast between adjacent dental structures. By integrating these dual aspects, FDNet adeptly addresses the semantic gap, providing a detailed and accurate segmentation. The framework's effectiveness is validated through rigorous benchmarks, achieving the top Dice and IoU scores of 85.28% and 75.23%, respectively. This innovative decoupling of semantic and boundary features capitalizes on the unique strengths of each element to elevate the quality of segmentation performance.

FDNet: Feature Decoupled Segmentation Network for Tooth CBCT Image

TL;DR

This paper proposes FDNet, a Feature Decoupled Segmentation Network, to excel in the face of the variable dental conditions encountered in CBCT scans, such as complex artifacts and indistinct tooth boundaries.

Abstract

Precise Tooth Cone Beam Computed Tomography (CBCT) image segmentation is crucial for orthodontic treatment planning. In this paper, we propose FDNet, a Feature Decoupled Segmentation Network, to excel in the face of the variable dental conditions encountered in CBCT scans, such as complex artifacts and indistinct tooth boundaries. The Low-Frequency Wavelet Transform (LF-Wavelet) is employed to enrich the semantic content by emphasizing the global structural integrity of the teeth, while the SAM encoder is leveraged to refine the boundary delineation, thus improving the contrast between adjacent dental structures. By integrating these dual aspects, FDNet adeptly addresses the semantic gap, providing a detailed and accurate segmentation. The framework's effectiveness is validated through rigorous benchmarks, achieving the top Dice and IoU scores of 85.28% and 75.23%, respectively. This innovative decoupling of semantic and boundary features capitalizes on the unique strengths of each element to elevate the quality of segmentation performance.
Paper Structure (12 sections, 2 equations, 3 figures, 2 tables)

This paper contains 12 sections, 2 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. METHODS
  3. Architecture Overview
  4. LF-Wavelet Transform
  5. SAM Encoder
  6. EXPERIMENT
  7. Dataset
  8. Main Results
  9. Ablation Study
  10. CONCLUSION
  11. COMPLIANCE WITH ETHICAL STANDARDS
  12. ACKNOWLEDGMENTS

Figures (3)

  • Figure 1: The architecture of the proposed FDNet segmentation model. Specifically, the LIF module fuses features from the $U_w$ and $U_o$ encoders before passing them to the CTB module.
  • Figure 2: Comparison of low-frequency transformed and original images, with each low-frequency counterpart on the top and its original image at the bottom.
  • Figure 3: The results of segmentation using different methods. It shows our model's adept performance in achieving precise segmentation across four dental conditions, including scenarios with complex artifacts and blurred tooth boundaries.