Earticle

초록

영어

Accurate tooth segmentation from cone-beam computed tomography (CBCT) images is essential for dental diagnosis and treatment planning. This study presents a deep-learning approach for 3D tooth segmentation utilizing the SegMamba architecture enhanced with Squeeze-and-Excitation (SE) attention mechanisms in the skip connections. The proposed method leverages the strengths of state space models for capturing long-range dependencies while the SE attention blocks recalibrate feature representations to focus on the most informative channels and spatial regions. Our end-to-end framework directly processes 3D CBCT volumes to produce accurate tooth segmentation masks. Experimental evaluations demonstrate that our method achieves a high Dice score of 91.42%, outperforming current state-of-the-art approaches for tooth segmentation tasks.

목차

Abstract
Ⅰ. Introduction
Ⅱ. Proposed Method
A. SegMamba Architecture
B. Squeeze-and-Excitation Attention
C. End-to-End Segmentation Framework
III. Experimental Results
A. Dataset and Preprocessing
B. Result and Comparison
IV. Conclusion
ACKNOWLEDGMENT
REFERENCES

저자

• Muhammad Asif Jamal [ Chosun University, Department of Information and Communication Engineering ]
• Bumshik Lee [ 이범식 | Chosun University, Department of Information and Communication Engineering ] Corresponding Author

참고문헌