Deep learning-driven super-resolution for cone-beam computed tomography: An <i>ex vivo</i> proof-of-concept study using artificially degraded micro-computed tomography data.
Authors
Affiliations (7)
Affiliations (7)
- Department of Dentistry and Oral Health, Aarhus University, Aarhus, Denmark.
- Conservative Dentistry, Periodontology and Digital Dentistry, LMU Klinikum, Munich, Germany.
- Department of Endodontics and Center for Craniofacial Regeneration, University of Pittsburgh, School of Dental Medicine, Pittsburgh, PA, USA.
- Aarhus Institute of Advanced Studies, Aarhus University, Aarhus, Denmark.
- Department of Oral and Maxillofacial Radiology, School of Dentistry, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Research Center, Research Institute of Dental Sciences, School of Dentistry, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Shahed University of Medical Sciences, School of Dentistry, Oral and Maxillofacial Radiology Department, Tehran, Iran.
Abstract
This ex vivo proof-of-concept study aimed to develop deep learning (DL)-based super-resolution (SR) models to enhance simulated cone-beam computed tomography (CBCT) images. Micro-computed tomography data from 51 extracted teeth were artificially degraded to simulate CBCT images. Three DL models, super-resolution convolutional neural network (SRCNN), local texture estimator (LTE), and Swin Transformer for image restoration (SwinIR), were compared with bicubic interpolation. Image quality was assessed using 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 evaluated sharpness and noise using a 5-point Likert scale. Eight observers assessed crack visibility in 47 images for LTE and bicubic interpolation using a 5-point Likert scale; scores were binarized using high and low thresholds. All models significantly outperformed bicubic interpolation on objective metrics. SwinIR showed the highest PSNR (30.36 ± 2.66), whereas SRCNN achieved the highest SSIM (0.889 ± 0.073). LTE achieved the best LPIPS (0.253 ± 0.101) and DISTS (0.203 ± 0.049). Subjectively, LTE received the highest sharpness ratings (mean. 3.79 ± 0.47), whereas bicubic interpolation received the highest noise ratings (3.97 ± 1.43). LTE significantly improved crack visibility (odds ratio = 1.326, <i>P</i> = 0.006 for the low-threshold analysis; odds ratio = 1.310, <i>P</i> = 0.010 for the high-threshold analysis), with a higher pooled area under the curve (0.81 vs. 0.76, <i>P</i> = 0.063). DL-based SR models can enhance simulated CBCT images, with LTE demonstrating superior perceptual sharpness and crack visibility.