Visual enhancement of Cone-beam CT by use of CycleGAN

Abstract

Cone-beam computed tomography (CBCT) offers advantages over conventional fan-beam CT in that it requires a shorter time and less exposure to obtain images. CBCT has found a wide variety of applications in patient positioning for image-guided radiation therapy, extracting radiomic information for designing patient-specific treatment, and computing fractional dose distributions for adaptive radiation therapy. However, CBCT images suffer from low soft-tissue contrast, noise, and artifacts compared to conventional fan-beam CT images. Therefore, it is essential to improve the image quality of CBCT. In this paper, we propose a synthetic approach to translate CBCT images with deep neural networks. Our method requires only unpaired and unaligned CBCT images and planning fan-beam CT (PlanCT) images for training. Once trained, 3D reconstructed CBCT images can be directly translated to high-quality PlanCT-like images. We demonstrate the effectiveness of our method with images obtained from 24 prostate patients, and we provide a statistical and visual comparison. The image quality of the translated images shows substantial improvement in voxel values, spatial uniformity, and artifact suppression compared to those of the original CBCT. The anatomical structures of the original CBCT images were also well preserved in the translated images. Our method enables more accurate adaptive radiation therapy, and opens up new applications for CBCT that hinge on high-quality images.

References in corpus (7)

• Instance Normalization: The Missing Ingredient for Fast Stylization
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Improved Training of Wasserstein GANs
• Generating Synthesized Computed Tomography (CT) from Cone-Beam Computed Tomography (CBCT) using CycleGAN for Adaptive Radiation Therapy
• Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
• Deep learning in radiology: an overview of the concepts and a survey of the state of the art
• On the Effectiveness of Least Squares Generative Adversarial Networks

Cited by in corpus (9)

• Deep learning-based synthetic-CT generation in radiotherapy and PET: a review
• CBCT-Based Synthetic CT Image Generation Using Conditional Denoising Diffusion Probabilistic Model
• Three-dimensional Generative Adversarial Nets for Unsupervised Metal Artifact Reduction
• Artifact Reduction in 3D and 4D Cone-beam Computed Tomography Images with Deep Learning -- A Review
• Medical Imaging Synthesis using Deep Learning and its Clinical Applications: A Review
• Training of deep cross-modality conversion models with a small dataset, and their application in megavoltage CT to kilovoltage CT conversion
• Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks
• Generalizability issues with deep learning models in medicine and their potential solutions: illustrated with Cone-Beam Computed Tomography (CBCT) to Computed Tomography (CT) image conversion
• Exploring constraints on CycleGAN-based CBCT enhancement for adaptive radiotherapy