Corpus ID: 58014127

Cone-beam CT to Planning CT synthesis using generative adversarial networks

  title={Cone-beam CT to Planning CT synthesis using generative adversarial networks},
  author={S. Kida and Shizuo Kaji and K. Nawa and Toshikazu Imae and T. Nakamoto and S. Ozaki and T. Ohta and Y. Nozawa and Keiichi Nakagawa},
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. [...] Key Result Our method enables more accurate adaptive radiation therapy, and opens up new applications for CBCT that hinge on high-quality images.Expand
Chest CBCT-based synthetic CT using cycle-consistent adversarial network with histogram matching
Image-guided radiation therapy (IGRT) is an important technological advancement that has significantly contributed to the accuracy of radiation oncology treatment plan delivery in the last decade.Expand
Synthetic CT generation from CBCT images via unsupervised deep learning
The proposed unsupervised style-transfer-based approach to generate a synthetic CT (sCT) that has the same anatomical structure as CBCT but accurate HU values is desirable for ART and may permit using CBCT for advanced applications such as adaptive treatment planning. Expand
Fully automated dose prediction using generative adversarial networks in prostate cancer patients
The CT-based dose prediction could reduce the time required for both the iterative optimization process and the structure contouring, allowing physicians and dosimetrists to focus their expertise on more challenging cases. Expand
Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imaging
  • S. Kaji, S. Kida
  • Physics, Engineering
  • Radiological Physics and Technology
  • 2019
Since the advent of deep convolutional neural networks (DNNs), computer vision has seen an extremely rapid progress that has led to huge advances in medical imaging. Every year, many new methods areExpand
Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks
A conditional generative adversarial network (GAN) - based method to directly learn the mapping relationship between structure fundus images and fundus fluorescence angiography images is proposed and local saliency maps, which define each pixel's importance, are used to define a novel saliency loss in the GAN cost function. Expand


Medical Image Synthesis with Context-Aware Generative Adversarial Networks
A fully convolutional network is trained to generate CT given the MR image to better model the nonlinear mapping from MRI to CT and produce more realistic images, and an image-gradient-difference based loss function is proposed to alleviate the blurriness of the generated CT. Expand
Deep MR to CT Synthesis Using Unpaired Data
This work proposes to train a generative adversarial network (GAN) with unpaired MR and CT images to synthesize CT images that closely approximate reference CT images, and was able to outperform a GAN model trained with paired MR andCT images. Expand
Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
This work proposes a generic cross-modality synthesis approach and shows that these goals can be achieved with an end-to-end 3D convolutional neural network (CNN) composed of mutually-beneficial generators and segmentors for image synthesis and segmentation tasks. Expand
Investigating deformable image registration and scatter correction for CBCT-based dose calculation in adaptive IMPT.
Using the vCT as prior, errors can be overcome and images suitable for accurate delineation and dose calculation in CBCT-based adaptive IMPT can be retrieved from scatter correction of the CBCT projections. Expand
Fast shading correction for cone beam CT in radiation therapy via sparse sampling on planning CT
An effective shading correction algorithm for CBCT readily implementable on clinical data as a software plug‐in without modifications of current imaging hardware and protocol is developed. Expand
Multiscale registration of planning CT and daily cone beam CT images for adaptive radiation therapy.
The authors present the results of studies of rectum, head-neck, and prostate CT-CBCT registration, and validate their registration method quantitatively using synthetic results in which the exact transformations the authors' known, and qualitatively using clinical deformations in whichthe exact results are not known. Expand
Flat-panel cone-beam computed tomography for image-guided radiation therapy.
A kV cone-beam CT imaging system based on a large-area, flat-panel detector has been successfully adapted to a medical linear accelerator and is capable of producing images of soft tissue with excellent spatial resolution at acceptable imaging doses. Expand
Assessment of residual error for online cone-beam CT-guided treatment of prostate cancer patients.
On the basis of the residual setup error measurements, the margin required after online CBCT correction for the patients enrolled in this study would be approximatively 3 mm and is considered to be a lower limit owing to the small intrafraction motion observed. Expand
Assessing the impact of choosing different deformable registration algorithms on cone-beam CT enhancement by histogram matching
The results suggest that applying DR process based on NCC similarity metric reduces significantly the uncertainties in CBCT images and generates images in good agreement with pCT. Expand
Optimal combination of anti‐scatter grids and software correction for CBCT imaging
The best scatter mitigation strategy was found to be a combination of a grid with selectivity larger than 9, combined with iterative scatter estimation, and none of the investigated grids required increasing the imaging dose. Expand