Filters








112 Hits in 5.4 sec

Bone Suppression on Chest Radiographs With Adversarial Learning [article]

Jia Liang, Yuxing Tang, Youbao Tang, Jing Xiao, Ronald M. Summers
2020 arXiv   pre-print
In this work, we learn the mapping between conventional radiographs and bone suppressed radiographs.  ...  Specifically, we propose to utilize two variations of generative adversarial networks (GANs) for image-to-image translation between conventional and bone suppressed radiographs obtained by DE imaging technique  ...  CONCLUSION We proposed to use generative adversarial networks to learn to suppress bone structures on chest radiographs.  ... 
arXiv:2002.03073v1 fatcat:kom53usinnbwxbwvh474hktr4a

Generation of Virtual Dual Energy Images from Standard Single-Shot Radiographs using Multi-scale and Conditional Adversarial Network [article]

Bo Zhou, Xunyu Lin, Brendan Eck, Jun Hou, David L. Wilson
2021 arXiv   pre-print
Our proposed MCA-Net is trained using the adversarial network so that it learns sharp details for the production of high-quality bone images.  ...  We present a Multi-scale Conditional Adversarial Network (MCA-Net) which produces high-resolution virtual DE bone images from standard, single-shot chest radiographs.  ...  Hybrid loss function With only adversarial learning, artifacts may be present in the generated DE bone image [11] .  ... 
arXiv:1810.09354v2 fatcat:cpjyu7pc3ncm7gf4lyslxvcc4m

Bone Suppression on Chest Radiographs for Pulmonary Nodule Detection: Comparison between a Generative Adversarial Network and Dual-Energy Subtraction

Kyungsoo Bae, Dong Yul Oh, Il Dong Yun, Kyung Nyeo Jeon
2022 Korean Journal of Radiology  
To compare the effects of bone suppression imaging using deep learning (BSp-DL) based on a generative adversarial network (GAN) and bone subtraction imaging using a dual energy technique (BSt-DE) on radiologists  ...  ' performance for pulmonary nodule detection on chest radiographs (CXRs).  ...  CXR = chest radiograph Fig. 2 . 2 Fig. 2. The architecture of bone suppression algorithm based on wavelet transform and generative adversarial networks.A.  ... 
doi:10.3348/kjr.2021.0146 pmid:34983100 pmcid:PMC8743147 fatcat:jz6ft2oux5hehgdlglulc7lmge

The Effectiveness of Data Augmentation for Bone Suppression in Chest Radiograph using Convolutional Neural Network

Ren G, Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China, Lam S-K, Ni R, Yang D, Qin J, Cai J, Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China, Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China, Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China, School of Nursing, The Hong Kong Polytechnic University, Hong Kong SAR, China, Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, China
2021 Austin Journal of Cancer and Clinical Research  
Two CNN models (U-Net and Generative Adversarial Network (GAN)) were adapted to explore the effectiveness of various data augmentation techniques for bone signal suppression in the chest radiograph.  ...  Methods: In this study, chest radiograph and bone-free chest radiograph are derived from 59 high-resolution CT scans.  ...  in the task of chest X-ray bone signal suppression.  ... 
doi:10.26420/austinjcancerclinres.2021.1095 fatcat:ybffi7za6fh2xf6w6xgvfw37nq

Deep learning-based bone suppression in chest radiographs using CT-derived features: a feasibility study

Ge Ren, Haonan Xiao, Sai-Kit Lam, Dongrong Yang, Tian Li, Xinzhi Teng, Jing Qin, Jing Cai
2021 Quantitative Imaging in Medicine and Surgery  
Evaluation on real chest radiographs showed that the bone-suppressed chest radiographs closely matched with the bone-suppressed reference, achieving an accuracy of MAE =0.0087±0.0030, SSIM =0.8458±0.0317  ...  This study aims to develop a deep learning-based bone suppression method using CT-derived features to reduce the reliance on the bone-free dataset.  ...  Footnote Provenance and Peer Review: With the arrangement by the Guest Editors and the editorial office, this article has been reviewed by external peers.  ... 
doi:10.21037/qims-20-1230 pmid:34888191 pmcid:PMC8611463 fatcat:z7melz6xszervm6zqn5bgxuulq

Learning Bone Suppression from Dual Energy Chest X-rays using Adversarial Networks [article]

Dong Yul Oh, Il Dong Yun
2018 arXiv   pre-print
As a result, we achieve state-of-the-art performance on bone suppression as compared to the existing approaches with dual energy chest X-rays.  ...  Suppressing bones on chest X-rays such as ribs and clavicle is often expected to improve pathologies classification.  ...  Main Contributions This work first of all addresses the problem of minimizing average pixel-wise differences to learn bone suppression on single energy chest X-rays.  ... 
arXiv:1811.02628v1 fatcat:ftgyxd6ovbbw5mo4klxsvxrat4

Computer-aided detection in chest radiography based on artificial intelligence: a survey

Chunli Qin, Demin Yao, Yonghong Shi, Zhijian Song
2018 BioMedical Engineering OnLine  
Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.  ...  Bone suppression Bone suppression is a unique preprocessing technique in chest radiography and is an important preprocessing step in lung segmentation and feature extraction.  ...  Subtracting a bone image from the corresponding chest radiograph produces a "soft tissue image", where the rib and clavicle are substantially suppressed. Nguyen et al.  ... 
doi:10.1186/s12938-018-0544-y pmid:30134902 fatcat:moshts5kpjd4hpejcs2irwf6eq

Encoding CT Anatomy Knowledge for Unpaired Chest X-ray Image Decomposition [article]

Zeju Li, Han Li, Hu Han, Gonglei Shi, Jiannan Wang, S. Kevin Zhou
2019 arXiv   pre-print
., bone, lung and soft tissue) improves diagnostic value. We hereby propose a decomposition generative adversarial network (DecGAN) to anatomically decompose a CXR image but with unpaired data.  ...  Although chest X-ray (CXR) offers a 2D projection with overlapped anatomies, it is widely used for clinical diagnosis.  ...  Without domain adaptation, deep learning based methods would fail when the test CXR looks different from DRR: the bone suppression always lacks precision and the non-bone components are suppressed too.  ... 
arXiv:1909.12922v1 fatcat:vmdcbwa7ebabtbfrbw427x2jeq

Image to Images Translation for Multi-Task Organ Segmentation and Bone Suppression in Chest X-Ray Radiography [article]

Mohammad Eslami, Solale Tabarestani, Shadi Albarqouni, Ehsan Adeli, Nassir Navab, Malek Adjouadi
2019 arXiv   pre-print
The literature in this field of research reports many interesting studies dealing with the challenging tasks of bone suppression and organ segmentation but performed separately, limiting any learning that  ...  This study, and for the first time, introduces a multitask deep learning model that generates simultaneously the bone-suppressed image and the organ segmented image, minimizing as a consequence the number  ...  Another bone suppression method, based on deep adversarial networks and 2D Haar wavelet decomposition, has been proposed in [36] .  ... 
arXiv:1906.10089v1 fatcat:fsf4iq26uvc4ldasa2xm6boo54

GAN-based disentanglement learning for chest X-ray rib suppression [article]

Luyi Han, Yuanyuan Lyu, Cheng Peng, S.Kevin Zhou
2021 arXiv   pre-print
Clinical evidence has shown that rib-suppressed chest X-rays (CXRs) can improve the reliability of pulmonary disease diagnosis.  ...  to the state-of-the-art rib suppression methods; (ii) combining CXR with our rib-suppressed result leads to better performance in lung disease classification and tuberculosis area detection.  ...  in chest radiographs (Hogeweg et al., 2013a; Laskey, 1996) .  ... 
arXiv:2110.09134v1 fatcat:fleobmo6vzdyvnvfj4s4jo6vgq

XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors

Cheng Peng, Haofu Liao, Gina Wong, Jiebo Luo, S. Kevin Zhou, Rama Chellappa
2021 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We show that by gaining an understanding of radiography in 3D space, our method can be applied to radiograph bone extraction and suppression without requiring groundtruth bone labels.  ...  Our method, XraySyn, can synthesize novel views on real radiographs through a combination of realistic simulation and finetuning on real radiographs.  ...  As clinical evidence supports that bone suppression on radiograph can improve diagnostic accuracy (Laskey 1996) , Li (Li et al. 2020) proposes to achieve bone suppression by learning a bone segmentation  ... 
doi:10.1609/aaai.v35i1.16120 fatcat:nhuyhlyxazgozgm6dtc4kh65zu

XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors [article]

Cheng Peng, Haofu Liao, Gina Wong, Jiebo Luo, Shaohua Kevin Zhou, Rama Chellappa
2022 arXiv   pre-print
We show that by gaining an understanding of radiography in 3D space, our method can be applied to radiograph bone extraction and suppression without groundtruth bone labels.  ...  Our method, XraySyn, can synthesize novel views on real radiographs through a combination of realistic simulation and finetuning on real radiographs.  ...  As clinical evidence supports that bone suppression on radiograph can improve diagnostic accuracy (Laskey 1996) , Li (Li et al. 2020) proposes to achieve bone suppression by learning a bone segmentation  ... 
arXiv:2012.02407v2 fatcat:a7jacwvbhbb3lf3qx5yxx3e7ta

Front Matter: Volume 11313

Bennett A. Landman, Ivana Išgum
2020 Medical Imaging 2020: Image Processing  
These two-number sets start with 00, 01, 02, 03, 04,  ...  The papers in this volume were part of the technical conference cited on the cover and title page. Papers were selected and subject to review by the editors and conference program committee.  ...  deformable registration of temporal chest radiographs to detect interval change [11313-104] 11313 2Y Weakly non-rigid MR-TRUS prostate registration using fully convolutional and recurrent neural networks  ... 
doi:10.1117/12.2570657 fatcat:be32besqknaybh6wibz7unuboa

The Rise of Deep Learning in Radiology: An Overview of Recent Research

Deya Chatterjee
2019 International Journal for Research in Applied Science and Engineering Technology  
, unsupervised methods of deep learning like auto-encoders and improving research on GANs in radiology.  ...  In this paper, the imaging modalities associated with this field and the application of different deep learning techniques to these have been discussed at length.  ...  [35] used pretrained CNN to detect bones and tissues as well as to segment the wrist/hand in radiographs of the hand and ultimately performed bone age assessment (BAA) on the data.  ... 
doi:10.22214/ijraset.2019.6397 fatcat:473bjftzdvhlpaqsatvzfn3bf4

An Overview of Deep Learning Approaches in Chest Radiograph

Anis Shazia, Khin Wee Lai, Joon Huang Chuah, Mohammad Ali Shoaib, Hamidreza Mohafez, Maryam Hadizadeh, Yan Ding, Zhi Chao Ong
2020 IEEE Access  
With the recent advances of deep learning and increased hardware computational power, researchers are working on various networks and algorithms to develop machines learning that can assists radiologists  ...  Chest X-ray (CXR) interpretations are conducted in hospitals and medical facilities on daily basis.  ...  The author has used the publicly available JSRT dataset to obtain the bone and rib suppression task.  ... 
doi:10.1109/access.2020.3028390 fatcat:22uaqapglbhnlipo5kdzh4rg34
« Previous Showing results 1 — 15 out of 112 results