Artifact Reduction in 3D and 4D Cone-beam Computed Tomography Images with Deep Learning -- A Review

Abstract

Deep learning based approaches have been used to improve image quality in cone-beam computed tomography (CBCT), a medical imaging technique often used in applications such as image-guided radiation therapy, implant dentistry or orthopaedics. In particular, while deep learning methods have been applied to reduce various types of CBCT image artifacts arising from motion, metal objects, or low-dose acquisition, a comprehensive review summarizing the successes and shortcomings of these approaches, with a primary focus on the type of artifacts rather than the architecture of neural networks, is lacking in the literature. In this review, the data generation and simulation pipelines, and artifact reduction techniques are specifically investigated for each type of artifact. We provide an overview of deep learning techniques that have successfully been shown to reduce artifacts in 3D, as well as in time-resolved (4D) CBCT through the use of projection- and/or volume-domain optimizations, or by introducing neural networks directly within the CBCT reconstruction algorithms. Research gaps are identified to suggest avenues for future exploration. One of the key findings of this work is an observed trend towards the use of generative models including GANs and score-based or diffusion models, accompanied with the need for more diverse and open training datasets and simulations.

arXiv comment16 pages, 4 figures, 1 Table, published in IEEE Access Journal

References in corpus (20)

• Denoising Diffusion Probabilistic Models
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• MONAI: An open-source framework for deep learning in healthcare
• Generating Synthesized Computed Tomography (CT) from Cone-Beam Computed Tomography (CBCT) using CycleGAN for Adaptive Radiation Therapy
• Denoising Diffusion Restoration Models
• Deep learning-based synthetic-CT generation in radiotherapy and PET: a review
• Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
• Learning with Known Operators reduces Maximum Training Error Bounds
• Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
• SynthRAD2023 Grand Challenge dataset: generating synthetic CT for radiotherapy
• Visual enhancement of Cone-beam CT by use of CycleGAN
• Computationally Efficient Deep Neural Network for Computed Tomography Image Reconstruction
• PYRO-NN: Python Reconstruction Operators in Neural Networks
• Deep Efficient End-to-end Reconstruction (DEER) Network for Few-view Breast CT Image Reconstruction
• Multitask 3D CBCT-to-CT Translation and Organs-at-Risk Segmentation Using Physics-Based Data Augmentation
• Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
• Deep Encoder-decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-view Data
• Fiducial marker recovery and detection from severely truncated data in navigation assisted spine surgery
• Parallel Diffusion Model-based Sparse-view Cone-beam Breast CT

Cited by in corpus (1)

• Unsupervised Metal Artifact Reduction in Dental CBCT using Fine-tuned Cycle-Consistent Adversarial Networks