Metal artifact reduction for practical dental computed tomography by improving interpolation‐based reconstruction with deep learning

Abstract

Purpose Metal artifact is a quite common problem in diagnostic dental computed tomography (CT) images. Due to the high attenuation of heavy materials such as metal, severe global artifacts can occur in reconstructions. Typical metal artifact reduction (MAR) techniques segment out the metal regions and estimate the corrupted projection data by various interpolation methods. However, interpolations are not accurate and introduce new artifacts or even deform the teeth in the reconstructed image. This work presents a new strategy to take advantage of the power of deep learning for metal artifact reduction. Method The analysis first uses coarse reconstructions from simulated locally interpolated data affected by metal fillings as a starting point. A deep learning network is then trained using the simulated data and applied to practical data. Thus, an easily implemented three‐step MAR method is formed: Firstly, use the acquired projection data to create a preliminary image reconstruction with linearly interpolated data for the metal‐related projections. Secondly, a deep learning network is used to remove the artifacts from the linear interpolation and recover the nonmetal region information. Thirdly, the method adds the ROI reconstruction of the metal regions. The structures behind the shading artifacts in the direct filtered back‐projection (FBP) reconstruction can be partially recovered by interpolation‐based MAR (I‐MAR) with the network further correcting for interpolation errors. The key to this method is that the linear interpolation reconstruction errors can be easily simulated to train a network and the effectiveness of the network can be easily generalized to I‐MAR results in real situations. Results We trained a network with a simulation dataset and validated the network against a separate simulation dataset. Then, the network was tested using simulation data that did not overlap with the training/validation datasets and real patient datasets. Both tests gave encouraging results with accurate tooth structure recovery and few artifacts. The relative root mean square error and structure similarity index method indexes were significantly improved in the tests. The method was also evaluated by two experienced dentists who gave positive evaluations. Conclusions This work presents a strategy to build a transferable learning from simulations to practical systems for metal artifact reduction using a supervised deep learning method. The system transforms the MAR analyses to an interpolation‐artifact reduction problem to recover structural details from the coarse interpolation reconstruction. In this way, training data from simulations with ground truth labels can easily model the similar features in real data with I‐MAR as the bridge. The network can seamlessly optimize both simulations and real data. The whole method is easily implemented with little computational cost. Test results demonstrated that this is an effective MAR method applicable to practical dental CT systems.

Deep learning–based metal artefact reduction in PET/CT imaging

“…Different strategies for deep learning-based metal artefact reduction (MAR) of CT images were explored either in the image or projection domains [18][19][20][21][22]. The evaluation of CT images after MAR demonstrated the superior performance of the deep learning-based MAR in the image domain (DLI-MAR) when additional information (prior knowledge) in the form of CT images corrected by the normalized MAR approach was also fed to the network (Fig.…”

“…Two clinical databases were utilized in this work, including a simulation dataset used for training and assessment of the deep learning-based MAR approaches and whole-body 18 F-FDG PET/CT images used for clinical evaluation. The simulation dataset consisted of 80 metal-free whole-body CT images acquired on a Biograph mCT PET/CT scanner (Siemens Healthcare) using the following parameters: effective tube current = 100 mAs, tube voltage = 110-120 kVp, slice thickness = 3 mm, automated tube voltage selection, automated tube current modulation, pitch factor of 1, mean CTDIvol = 5.8 mGy and DLP of 65 mGy•cm (average BMI = 29.5).…”

“…Deep learning-based algorithms emerged as promising approaches for solving a variety of image analysis and pattern recognition problems and have been successfully implemented in the context of metal artefact reduction in CT imaging [18][19][20][21][22][23]. Deep learning-based MAR techniques could be categorized as the 4th type of MAR approaches, wherein the correction for metal-induced beam hardening is applied in either the projection [22] or image domain [19].…”

Dentomaxillofacial CBCT: Clinical Challenges for Indication-oriented Imaging

“…Especially the deep learning methods may be useful for removing image artifacts, normalizing/harmonizing images, providing lower radiation dose images, and also shortening the duration of imaging studies (consequently minimizing movement artifacts). [48][49][50][51] Some authors have presented a supervised deep learning method to reduce metal artifacts from dental CT images. They achieved accurate tooth structure recovery and few artifacts by using simulated data for testing the neural network performance.…”

An Improved Dice Loss for Pneumothorax Segmentation by Mining the Information of Negative Areas

“…With the successful application of deep learning methods represented by convolutional neural networks in the field of computer vision, the methods based on neural network have demonstrated considerable success in the field of medical image segmentation [5], [6]. Wang et al first used deep learning to perform pneumothorax segmentation [7], and achieved satisfactory results.…”