Home // GLOBAL HEALTH 2024, The Thirteenth International Conference on Global Health Challenges // View article


Evaluation of Segmentation Schemes for Noisy and Denoised Dental Cone Beam Computed Tomography (CBCT) Images

Authors:
Simin Mirzaei
Hamid Reza Tohidypour
Shahriar Mirabbasi
Panos Nasiopoulos

Keywords: Cone Beam Computed Tomography (CBCT) images; segmentation; denoising.

Abstract:
Segmenting Cone Beam Computed Tomography (CBCT) images is challenging due to high noise levels, artifacts, and limited resolution. This paper evaluates the effectiveness of various segmentation methods on both noisy and denoised CBCT images. We examine the performance of state-of-the-art segmentation techniques on CBCT scans processed with three efficient denoising methods tailored for low-dose CBCT images. Our findings indicate that introducing a denoising step before segmentation significantly enhances the segmentation quality of CBCT images. Additionally, the 3D Slicer approach demonstrates the most robust segmentation performance for both noisy and denoised CBCT images. Among the denoising techniques, Chang et al.’s method proves to be the most effective, yielding promising results across all evaluated segmentation methods.

Pages: 5 to 9

Copyright: Copyright (c) IARIA, 2024

Publication date: September 29, 2024

Published in: conference

ISSN: 2308-4553

ISBN: 978-1-68558-189-3

Location: Venice, Italy

Dates: from September 29, 2024 to October 3, 2024