An Advanced Denoising Technique for Low-Dose CBCT Imaging: Enhancing Image Quality and Consumer Safety in Dental Diagnostics
- 28 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 796-807
Abstract
Cone Beam Computed Tomography (CBCT) plays a crucial role in dentistry, providing detailed imaging for diagnosis and treatment planning. However, standard CBCT imaging involves high radiation levels, raising safety concerns and driving the adoption of low-dose imaging, which often compromises image quality. This paper presents a novel denoising pipeline specifically designed to address the complex noise characteristics of low-dose CBCT images, which we have identified as resembling speckle noise. Our approach integrates advanced filtering techniques, innovative noise estimation methods, and brightness correction for 3D image reconstruction, while also leveraging the human visual system’s sensitivity to different frequencies to enhance CBCT visual quality. Experimental results demonstrate that our method outperforms state-of-the-art denoising techniques, including deep learning-based approaches, in achieving superior visual quality. This innovation not only enhances diagnostic precision but also improves patient safety, setting a new benchmark for image quality in dental care.Keywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada (PG 11R12450)
- Telus (PG 11R10321)
This publication has 28 references indexed in Scilit:
- Natural digital image mixed noise removal using regularization Perona–Malik model and pulse coupled neural networksSoft Computing, 2023
- Enhanced artificial intelligence-based diagnosis using CBCT with internal denoising: Clinical validation for discrimination of fungal ball, sinusitis, and normal cases in the maxillary sinusComputer Methods and Programs in Biomedicine, 2023
- Iterative reconstruction of low-dose CT based on differential sparseBiomedical Signal Processing and Control, 2022
- Additive Gaussian noise removal based on generative adversarial network model and semi-soft thresholding approachMultimedia Tools and Applications, 2022
- Low dose cone beam CT for paediatric image-guided radiotherapy: Image quality and practical recommendationsRadiotherapy and Oncology, 2021
- Natural image noise removal using nonlocal means and hidden Markov models in transform domainThe Visual Computer, 2017
- Dental cone beam CT: A reviewPhysica Medica, 2015
- A Simple but Effective Denoising Algorithm in Projection Domain of CBCT2015
- A comprehensive study on the relationship between the image quality and imaging dose in low-dose cone beam CTPhysics in Medicine & Biology, 2012
- Speckle Reduction in Images with WEAD and WECD2006