Enhancing Cone-Beam Computed Tomography Image Quality Using Deep Learning-based Super-Resolution

OBJECTIVES: To develop deep learning super-resolution (SR) models for enhancing cone-beam computed tomography (CBCT). METHODS: Seventy CBCT volumes (75 µm voxel size) served as references. Paired low-resolution (LR) volumes (300 µm) were simulated using physics-based degradation. Four architectures were each trained with three loss configurations (L1; L1+edge; L1+edge+perceptual): Swin Transformer for Image Restoration (SwinIR), Hybrid Attention Transformer (HAT), Hybrid Multi-Axis Aggregation Network (HMA-Net), and Dense-Residual-Connected Transformer (DRCT). Performance was assessed with peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), learned perceptual image patch similarity (LPIPS), and deep image structure and texture similarity (DISTS). Three dentists ranked the 12 configurations in 28 sets using blinded forced-choice pairwise comparisons. Correlations of metrics and expert ranks were assessed using Spearman correlation. RESULTS: All configurations outperformed LR input and bicubic interpolation on every metric (p < 0.05). HMA-Net trained with L1+edge+perceptual loss performed best on LPIPS (0.216) and DISTS (0.186). HAT with L1 loss achieved the highest PSNR (28.79 dB) and SSIM (0.820). Experts ranked DRCT and HAT with L1 loss, and DRCT with L1+edge loss, as the best configurations (p < 0.001 versus others). Expert rank correlated moderately only with PSNR (rho = -0.65) and SSIM (rho = -0.60; both p < 0.05). CONCLUSIONS: Transformer-based SR improved the perceived quality of clinical CBCT images. HAT and DRCT trained with L1 pixel loss alone, and DRCT trained with L1 and edge loss, demonstrated superior performance. ADVANCES IN KNOWLEDGE: Transformer-based super-resolution improved expert-perceived detail of simulated low-resolution in vivo CBCT scans without additional radiation dose, supporting further validation on directly acquired low-resolution scans.

Authors

Institutions

Publication Details

Journal
Dentomaxillofacial Radiology
Published
2026-11-13
DOI
https://doi.org/10.1093/dmfr/twag075
Primary Topic
Advanced Image Processing Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Enhancing Cone-Beam Computed Tomography Image Quality Using Deep Learning-based Super-Resolution

Matheus Sampaio‐Oliveira, Ali Nosrat, Lars Schropp, Rubens Spin‐Neto et al.
6 links
Dentomaxillofacial Radiology
Advanced Image Processing Techniques
article

Enhancing Cone-Beam Computed Tomography Image Quality Using Deep Learning-based Super-Resolution

Matheus Sampaio‐Oliveira, Ali Nosrat, Lars Schropp, Rubens Spin‐Neto, Hossein Mohammad‐Rahimi, Jennifer Christensen, Ruben Pauwels
article en

Abstract

OBJECTIVES: To develop deep learning super-resolution (SR) models for enhancing cone-beam computed tomography (CBCT). METHODS: Seventy CBCT volumes (75 µm voxel size) served as references. Paired low-resolution (LR) volumes (300 µm) were simulated using physics-based degradation. Four architectures were each trained with three loss configurations (L1; L1+edge; L1+edge+perceptual): Swin Transformer for Image Restoration (SwinIR), Hybrid Attention Transformer (HAT), Hybrid Multi-Axis Aggregation Network (HMA-Net), and Dense-Residual-Connected Transformer (DRCT). Performance was assessed with peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), learned perceptual image patch similarity (LPIPS), and deep image structure and texture similarity (DISTS). Three dentists ranked the 12 configurations in 28 sets using blinded forced-choice pairwise comparisons. Correlations of metrics and expert ranks were assessed using Spearman correlation. RESULTS: All configurations outperformed LR input and bicubic interpolation on every metric (p < 0.05). HMA-Net trained with L1+edge+perceptual loss performed best on LPIPS (0.216) and DISTS (0.186). HAT with L1 loss achieved the highest PSNR (28.79 dB) and SSIM (0.820). Experts ranked DRCT and HAT with L1 loss, and DRCT with L1+edge loss, as the best configurations (p < 0.001 versus others). Expert rank correlated moderately only with PSNR (rho = -0.65) and SSIM (rho = -0.60; both p < 0.05). CONCLUSIONS: Transformer-based SR improved the perceived quality of clinical CBCT images. HAT and DRCT trained with L1 pixel loss alone, and DRCT trained with L1 and edge loss, demonstrated superior performance. ADVANCES IN KNOWLEDGE: Transformer-based super-resolution improved expert-perceived detail of simulated low-resolution in vivo CBCT scans without additional radiation dose, supporting further validation on directly acquired low-resolution scans.

Dentomaxillofacial Radiology
University of Maryland, Baltimore (US), Aarhus University (DK), LMU Klinikum (DE), Ludwig-Maximilians-Universität München (DE)
Good health and well-being
Advanced Image Processing Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon