237 Hits in 6.4 sec

Limited-View Cone-Beam CT Reconstruction Based on an Adversarial Autoencoder Network With Joint Loss

Xiubin Dai, Jianan Bai, Tianliang Liu, Lizhe Xie
2019 IEEE Access  
When the new limited-view 3D CBCT projections are acquired, the proposed method uses the trained adversarial autoencoder network to generate the missing parts of the 2D pieces sliced from the current 3D  ...  First, this method slices the 3D CBCT projections into multiple 2D pieces. Then, an adversarial autoencoder network is trained to estimate the missing parts of these 2D pieces.  ...  network to estimate the missing data in each sliced 2D piece of 3D CBCT projections.  ... 
doi:10.1109/access.2018.2890135 fatcat:kndf57ejwnhypiccxrhj3d2sbi

MRI Reconstruction Using Deep Energy-Based Model [article]

Yu Guan, Zongjiang Tu, Shanshan Wang, Qiegen Liu, Yuhao Wang, Dong Liang
2021 arXiv   pre-print
Purpose: Although recent deep energy-based generative models (EBMs) have shown encouraging results in many image generation tasks, how to take advantage of the self-adversarial cogitation in deep EBMs  ...  More importantly, the proposed reconstruction framework can be generalized for most MRI reconstruction scenarios.  ...  The coil sensitivity maps are estimated from the central k-Space regions of each slice using ESPIRiT [44] and are assumed to be known during experiments.  ... 
arXiv:2109.03237v2 fatcat:s23takonkfaxpdr4lvlpizinw4

Multi-Input and Dataset-Invariant Adversarial Learning (MDAL) for Left and Right-Ventricular Coverage Estimation in Cardiac MRI [chapter]

Le Zhang, Marco Pereañez, Stefan K. Piechnik, Stefan Neubauer, Steffen E. Petersen, Alejandro F. Frangi
2018 Lecture Notes in Computer Science  
This paper proposes a novel adversarial learning (AL) approach based on convolutional neural networks (CNN) that detects and localizes the basal/apical slices in an image volume independently of image-acquisition  ...  The proposed model is trained on multiple cohorts of different provenance, and learns image features from different MRI viewing planes to learn the appearance and predict the position of the basal and  ...  System overview of our proposed dataset-invariant adversarial model with multi-view input channels for bi-ventricular coverage estimation in cardiac MRI.  ... 
doi:10.1007/978-3-030-00934-2_54 fatcat:a2pp6n32jjeyhkq7uqytw2rb2e

Reconstruction techniques for cardiac cine MRI

Rosa-María Menchón-Lara, Federico Simmross-Wattenberg, Pablo Casaseca-de-la-Higuera, Marcos Martín-Fernández, Carlos Alberola-López
2019 Insights into Imaging  
Thus, this paper aims to provide a general vision about cine MRI as the standard procedure in functional evaluation of the heart, focusing on technical methodologies.  ...  A recent contribution [105] is used (not exclusively) for static cardiac imaging. The authors propose an adversarial architecture for CS-like MRI reconstruction of static 2D images.  ...  Golden-angle radial sampling is used for acquisition of multiple 2D slices in a single BH. However, the reconstructions show spatiotemporal blurring.  ... 
doi:10.1186/s13244-019-0754-2 pmid:31549235 pmcid:PMC6757088 fatcat:s5574wj5pjadhbq5rah7k3h6lu

Style Transfer Using Generative Adversarial Networks for Multi-Site MRI Harmonization [article]

Mengting Liu, Piyush Maiti, Sophia I Thomopoulos, Alyssa Zhu, Yaqiong Chai, Hosung Kim, Neda Jahanshad
2021 bioRxiv   pre-print
Using a fully unsupervised deep-learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a reference  ...  We trained our model using data from five large-scale multi-site datasets with varied demographics.  ...  To pilot this work, we used 2D slices as input, and we selected 50 axial slices in the middle of each MRI volume as input.  ... 
doi:10.1101/2021.03.17.435892 fatcat:gb2lpds5jnd6do4xlay4nfogcy

Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation [article]

K. Ruwani M. Fernando, Chris P. Tsokos
2021 arXiv   pre-print
In this study, we critically review major statistical and deep learning models and their applications in brain imaging research with a focus on MRI-based brain tumor segmentation.  ...  The MRI scanner generates 3D volumetric brain imaging data as a stack of 2D slices, and k in the 3D space denotes the slice number.  ...  Generative adversarial networks Initially introduced for image synthesis from noise, GANs made a huge impact on computer vision.  ... 
arXiv:2103.05529v1 fatcat:iqu5ix5tgre6pnokdmoejywh74

Edge-Enhanced Dual Discriminator Generative Adversarial Network for Fast MRI with Parallel Imaging Using Multi-view Information [article]

Jiahao Huang, Weiping Ding, Jun Lv, Jingwen Yang, Hao Dong, Javier Del Ser, Jun Xia, Tiaojuan Ren, Stephen Wong, Guang Yang
2021 arXiv   pre-print
However, MRI suffers from an inherent slow data acquisition process because data is collected sequentially in k-space.  ...  Specifically, we introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction by incorporating multi-view information  ...  In particular, we propose a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction.  ... 
arXiv:2112.05758v1 fatcat:whzephzx5bgsvc6a6i6bwclg24

DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction

Guang Yang, Simiao Yu, Hao Dong, Greg Slabaugh, Pier Luigi Dragotti, Xujiong Ye, Fangde Liu, Simon Arridge, Jennifer Keegan, Yike Guo, David Firmin
2018 IEEE Transactions on Medical Imaging  
In particular, a novel conditional Generative Adversarial Networks-based model (DAGAN)-based model is proposed to reconstruct CS-MRI.  ...  Index Terms-Compressed sensing, magnetic resonance imaging (MRI), fast MRI, deep learning, generative adversarial networks (GAN), de-aliasing, inverse problems.  ...  General GAN Generative Adversarial Networks [52] consist of a generator network G and a discriminator network D.  ... 
doi:10.1109/tmi.2017.2785879 pmid:29870361 fatcat:tqsf5cna2vehjfyu7vppo4i5mu

Deep filter bank regression for super-resolution of anisotropic MR brain images [article]

Samuel W. Remedios, Shuo Han, Yuan Xue, Aaron Carass, Trac D. Tran, Dzung L. Pham, Jerry L. Prince
2022 arXiv   pre-print
In stage 1, we estimate the missing filters using gradient descent and in stage 2, we use deep networks to learn the mapping from coarse coefficients to detail coefficients.  ...  In 2D multi-slice magnetic resonance (MR) acquisition, the through-plane signals are typically of lower resolution than the in-plane signals.  ...  However, for anisotropic 2D-acquired MRI, the slice profile is the low-pass filter and as such we have a fixed, given H 0 .  ... 
arXiv:2209.02611v1 fatcat:cok7fjhgzfhotnuesgwa6bacw4

Narrative review of generative adversarial networks in medical and molecular imaging

Kazuhiro Koshino, Rudolf A. Werner, Martin G. Pomper, Ralph A. Bundschuh, Fujio Toriumi, Takahiro Higuchi, Steven P. Rowe
2021 Annals of Translational Medicine  
Generative adversarial networks (GANs) are techniques to synthesize images based on artificial neural networks and deep learning.  ...  annotations from a source domain to the target domain with no or insufficient knowledge; and (VII) image generation with disease severity and radiogenomics.  ...  images-GANs applied to MRI First, data augmentation techniques have been proposed for 2D sectional images derived from MRI.  ... 
doi:10.21037/atm-20-6325 pmid:34268434 pmcid:PMC8246192 fatcat:6dfpalmijjcrnmlb7e6ppycloq

Accelerating cardiac cine MRI using a deep learning-based ESPIRiT reconstruction [article]

Christopher M. Sandino, Peng Lai, Shreyas S. Vasanawala, Joseph Y. Cheng
2020 arXiv   pre-print
The network is trained on fully-sampled 2D cardiac cine datasets collected from eleven healthy volunteers with IRB approval.  ...  A novel neural network architecture, known as DL-ESPIRiT, is proposed to reconstruct rapidly acquired cardiac MRI data without field-of-view limitations which are present in previously proposed deep learning-based  ...  In a standard cardiac cine MRI scan, a two-dimensional (2D) steady-state gradient echo acquisition is synchronized with the cardiac cycle and typically performed over 10-15 slices covering the entire heart  ... 
arXiv:1911.05845v3 fatcat:n665uj2abbbstmgsshrf4rag7m

Enhanced Direct Joint Attenuation and Scatter Correction of Whole-Body PET Images via Context-Aware Deep Networks [article]

Saeed Izadi, Isaac Shiri, Carlos Uribe, Parham Geramifar, Habib Zaidi, Arman Rahmim, Ghassan Hamarneh
2022 medRxiv   pre-print
Inspired by recent advances in deep learning, many algorithms based on convolutional neural networks have been proposed for automatic attenuation and scatter correction, enabling applications to CT-less  ...  In this work, we present a novel deep learning-based framework for direct reconstruction of attenuation and scatter corrected PET from non-attenuation-corrected images in absence of structural information  ...  Even though 2D models generally benefit from relatively larger training data (i.e. slices), they fail to integrate the contextual coherency within neighboring slices.  ... 
doi:10.1101/2022.05.26.22275662 fatcat:36u3376cbfborgflhi73lqjw4q

Deep-JASC: joint attenuation and scatter correction in whole-body 18F-FDG PET using a deep residual network

Isaac Shiri, Hossein Arabi, Parham Geramifar, Ghasem Hajianfar, Pardis Ghafarian, Arman Rahmim, Mohammad Reza Ay, Habib Zaidi
2020 European Journal of Nuclear Medicine and Molecular Imaging  
Two- and three-dimensional deep residual networks using 2D successive slices (DL-2DS), 3D slices (DL-3DS) and 3D patches (DL-3DP) as input were constructed to perform joint attenuation and scatter correction  ...  We demonstrate the feasibility of direct generation of attenuation and scatter-corrected images from uncorrected images (PET-nonASC) using deep residual networks in whole-body 18F-FDG PET imaging.  ...  [30] proposed a deep learning-based synthetic CT generation which the input to this network is the attenuation map estimated from MLAA reconstruction in brain imaging.  ... 
doi:10.1007/s00259-020-04852-5 pmid:32415552 fatcat:bfkajanmnvcntptgenymkaekxq

A Review of Deep-Learning-Based Medical Image Segmentation Methods

Xiangbin Liu, Liping Song, Shuai Liu, Yudong Zhang
2021 Sustainability  
With the rapid development of deep learning, medical image processing based on deep convolutional neural networks has become a research hotspot.  ...  The second block is used to segment bone structures from MRI and generated CT images.  ...  [64] proposed a new method of multicontrast MRI synthesis based on conditional generative adversarial networks. Wolterink et al. [65] used CycleGAN to convert 2D MR images into CT images.  ... 
doi:10.3390/su13031224 fatcat:pn2qbyv53zbuhhiuem2pc4dg3u

Front Matter: Volume 11312

Hilde Bosmans, Guang-Hong Chen
2020 Medical Imaging 2020: Physics of Medical Imaging  
adversarial networks 11312 48 Attenuation correction for PET/MRI using MRI-based pseudo CT 11312 49 PET attenuation correction using non-AC PET-based synthetic CT 11312 4A Prior knowledge driven machine  ...  and reconstruction with paired variational neural networks 11312 0V Medical image reconstruction with image-adaptive priors learned by use of generative adversarial networks 11312 0W Quality assessment  ... 
doi:10.1117/12.2570912 fatcat:vl6kcecvhvfr5ogs3og5czzvwq
« Previous Showing results 1 — 15 out of 237 results