Visual Quality Enhancement of Low-Dose Dental CBCT Images

Cone-Beam Computed Tomography (CBCT) provides superior image quality in dentistry, but involves higher radiation exposure. To address this, lower radiation levels in CBCT imaging are used, resulting in higher noise levels. Although numerous efforts have been made to improve the visual quality of low-dose CBCT images, they often fail to achieve an optimal balance between noise reduction and edge preservation. This paper introduces a novel denoising algorithm surpassing previous methods, aimed at enhancing diagnostic accuracy by improving visual quality. Our approach begins with an adaptive median filter, followed by a fusion of frequency and spatial domain filtering techniques, supplemented by nonlocal means (NLM) smoothing and Laplacian sharpening. Subjective evaluations show a significant performance improvement over current state-of-the-art methods, marking a substantial progress toward achieving visual fidelity parity between low and high radiation CBCT scans.