Assessment of Deep-Learning Methods for the Enhancement of Experimental Low Dose Dental CBCT Volumes

TL;DR

This paper evaluates deep learning techniques, especially 3D U-Net, for enhancing low-dose dental CBCT images by reducing noise and artifacts while preserving details, offering a faster alternative to traditional methods.

Contribution

It demonstrates the effectiveness of supervised convolutional neural networks, particularly 3D U-Net, in improving low-dose CBCT image quality compared to traditional regularized iterative methods.

Findings

3D U-Net outperforms traditional methods in artifact reduction

Neural networks preserve and enhance image details

Deep learning offers faster processing for dental CBCT enhancement

Abstract

Cone-beam tomography enables rapid 3D acquisitions, making it a suitable imaging modality for dental imaging. However, as with all X-ray techniques, the main challenge is to reduce the dose while maintaining good image quality. Moreover, dental reconstructions face a series of issues stemming from truncated projections as well as metal and cone beam artifacts. The aim here is to investigate the ability of neural networks to improve the quality of 3D CBCT dental images at low doses. We test different configurations of convolutional neural networks, trained in a supervised way to reduce artifacts and noise present in analytically reconstructed volumes. In a study on 32 experimental cone beam volumes, we show their capacity to preserve and enhance details while still reducing the artifacts. The best results are obtained with a 3D U-Net which compares advantageously with a TV regularized iterative method and is considerably faster.