Filters








182 Hits in 7.7 sec

PIMA-CT: Physical Model-Aware Cyclic Simulation and Denoising for Ultra-Low-Dose CT Restoration

Peng Liu, Linsong Xu, Garrett Fullerton, Yao Xiao, James-Bond Nguyen, Zhongyu Li, Izabella Barreto, Catherine Olguin, Ruogu Fang
<span title="2022-05-25">2022</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hkhkuggfhrdg3hgg7rq5q5355e" style="color: black;">Frontiers in Radiology</a> </i> &nbsp;
The results show that CSD outperforms one of the state-of-the-art denoising algorithms without using any labeled data (actual patients' low-dose CT scans) nor simulated low-dose CT scans.  ...  A body of studies has proposed to obtain high-quality images from low-dose and noisy Computed Tomography (CT) scans for radiation reduction.  ...  We also include the standard-dose (175 mAs) scans as the ground-truth. Each dose level of the phantom series produces 138 CT scans.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fradi.2022.904601">doi:10.3389/fradi.2022.904601</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ph3ntbnbojbvffll75wbcwqaoa">fatcat:ph3ntbnbojbvffll75wbcwqaoa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220526085959/https://fjfsdata01prod.blob.core.windows.net/articles/files/904601/pubmed-zip/.versions/1/.package-entries/fradi-02-904601/fradi-02-904601.pdf?sv=2018-03-28&amp;sr=b&amp;sig=Pi6aCPU6WKRYKr%2B1SBH%2FWUXVibD4OaXMDpaWVHas9NA%3D&amp;se=2022-05-26T09%3A00%3A28Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27fradi-02-904601.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/93/b9/93b94f111c1d1c12dfbdf011f49f30c024393e03.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fradi.2022.904601"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a>

Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement [article]

Mingrui Geng and Yun Deng and Qian Zhao and Qi Xie and Dong Zeng and Dong Zeng and Wangmeng Zuo and Deyu Meng
<span title="2018-08-08">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This may bring major limitations on these methods because the number of such low-dose/high-dose training sinogram pairs would affect the network's capability and sometimes the ground-truth sinograms are  ...  Most of them need large number of pre-collected ground-truth/high-dose sinograms with less noise, and train the network in a supervised end-to-end manner.  ...  For unsupervised CNN, we only used 50 LdCT sinograms as training set. For sup-CNN method, we used 50 low-dose/high-dose CT sinogram pairs as training set.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.02603v1">arXiv:1808.02603v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yfgojpodcrbgpipkwr6edhkktq">fatcat:yfgojpodcrbgpipkwr6edhkktq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191024220502/https://arxiv.org/pdf/1808.02603v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/42/31/4231431c4bbbb303dab7187238fa4a07f1a5caac.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.02603v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Editorial: Introduction to the Issue on Domain Enriched Learning for Medical Imaging

Vishal Monga, Scott T. Acton, Abd-Krim Seghouane, Arrate Munoz-Barrutia, Jong Chul Ye
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/aznf273kcvcbfjcdeghr3xjd6i" style="color: black;">IEEE Journal on Selected Topics in Signal Processing</a> </i> &nbsp;
Unsupervised learning for reconstruction is explored in: "Unsupervised Training Of Denoisers For Low-Dose CT Reconstruction Without Full-Dose Ground Truth".  ...  The proposed method outperforms stateof-the-art low-dose CT reconstruction methods without ground truth.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jstsp.2020.3021275">doi:10.1109/jstsp.2020.3021275</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v5tbzsx5rvbp7kcb67upumsskq">fatcat:v5tbzsx5rvbp7kcb67upumsskq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200925131244/https://ieeexplore.ieee.org/ielx7/4200690/9205183/09205331.pdf?tp=&amp;arnumber=9205331&amp;isnumber=9205183&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d0/2d/d02d4ce40d52b511608087f7d9e80bbb10552331.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jstsp.2020.3021275"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Dataset-free Deep learning Method for Low-Dose CT Image Reconstruction [article]

Qiaoqiao Ding, Hui Ji, Yuhui Quan, Xiaoqun Zhang
<span title="2022-05-01">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Low-dose CT (LDCT) imaging attracted a considerable interest for the reduction of the object's exposure to X-ray radiation.  ...  In recent years, supervised deep learning has been extensively studied for LDCT image reconstruction, which trains a network over a dataset containing many pairs of normal-dose and low-dose images.  ...  Acknowledgement This work was supported by the NSFC (grant no. 12090024) and the Sino-German Mobility Programme (M-0187) by Sino-German Center for Research Promotion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.00463v1">arXiv:2205.00463v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fu3yen6cdrfmfpiy6l3z4qqrgy">fatcat:fu3yen6cdrfmfpiy6l3z4qqrgy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220506181347/https://arxiv.org/pdf/2205.00463v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/50/c0/50c09ded71d2f86d19a7beb6f21c1b4b743e32e7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.00463v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Low-dose CT reconstruction by self-supervised learning in the projection domain [article]

Long Zhou, Xiaozhuang Wang, Min Hou, Ping Li, Chunlong Fu, Yanjun Ren, Tingting Shao, Xi Hu, Jihong Sun, Hongwei Ye
<span title="2022-03-14">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In the intention of minimizing excessive X-ray radiation administration to patients, low-dose computed tomography (LDCT) has become a distinct trend in radiology.  ...  We present a self-supervised learning model (Noise2Projection) that fully exploits the raw projection images to reduce noise and improve the quality of reconstructed LDCT images.  ...  On the other hand, the majority of previous deep learning approaches for LDCT denoising depend on supervised learning with the normal-dose CT (NDCT) image as a ground truth of LDCT images [7, 20, 18]  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.06824v1">arXiv:2203.06824v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o3q3founc5dl3ghzwwsvafc64a">fatcat:o3q3founc5dl3ghzwwsvafc64a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220316023438/https://arxiv.org/pdf/2203.06824v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0e/9f/0e9f018aa5b24a9eab441aff21ab82fbd2786b4b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.06824v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Image Denoising with Frequency Domain Knowledge [article]

Nahyun Kim, Donggon Jang, Sunhyeok Lee, Bomi Kim, Dae-Shik Kim
<span title="2021-11-29">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The use of unsupervised denoisers, on the other hand, necessitates a more detailed understanding of the underlying image statistics.  ...  Supervised learning-based methods yield robust denoising results, yet they are inherently limited by the need for large-scale clean/noisy paired datasets.  ...  For a fair comparison, we use only the noise set and their corresponding ground-truth when training other supervised learning-based methods. We select unsupervised methods, i.e.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.14362v1">arXiv:2111.14362v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/aoq7lx3uhrgpnkuu5okpdr7jei">fatcat:aoq7lx3uhrgpnkuu5okpdr7jei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211201010251/https://arxiv.org/pdf/2111.14362v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dd/d8/ddd892ad5feac7ad390748beba9381aae31ee2aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.14362v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Model-Based Unsupervised Deep Learning Method for Low-Dose CT Reconstruction

Kaichao Liang, Li Zhang, Hongkai Yang, Zhiqiang Chen, Yuxiang Xing
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
No NDCT images were used in the unsupervised training process. NDCT images were used as the ground-truth images to validate the reconstruction results during test.  ...  Maximum a posterior (MAP) estimation for LDCT The primary concern of LDCT unsupervised training is to find an appropriate loss function without NDCT images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3020406">doi:10.1109/access.2020.3020406</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/octizjcoanh4hezzojgcs57g7e">fatcat:octizjcoanh4hezzojgcs57g7e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902142250/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09180342.pdf?tp=&amp;arnumber=9180342&amp;isnumber=6514899&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/22/27/2227099b36c48073f5837c73a62b7030dfaf9e57.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3020406"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Simultaneous Denoising and Motion Estimation for Low-dose Gated PET using a Siamese Adversarial Network with Gate-to-Gate Consistency Learning [article]

Bo Zhou, Yu-Jung Tsai, Chi Liu
<span title="2020-09-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Comprehensive evaluations on a low dose gated PET dataset of 29 subjects demonstrate that our method can effectively recover the low dose gated PET volumes, with an average PSNR of 37.16 and SSIM of 0.97  ...  In the applications of low dose PET, however, reducing injection dose causes increased noise and reduces signal-to-noise ratio (SNR), subsequently corrupting the motion estimation/correction steps, causing  ...  The denoised low-dose gated volumes are then fed into the motion estimation network for robust motion estimation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.06757v1">arXiv:2009.06757v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/crzcxw5yireszfpky6rkoxtoim">fatcat:crzcxw5yireszfpky6rkoxtoim</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928043119/https://arxiv.org/pdf/2009.06757v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.06757v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy

Hossein Arabi, Habib Zaidi
<span title="2020-09-23">2020</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/upidv5cku5gcjgwcjjms7rouu4" style="color: black;">European Journal of Hybrid Imaging</a> </i> &nbsp;
and segmentation, image denoising (low-dose imaging), radiation dosimetry and computer-aided diagnosis, and outcome prediction are discussed.  ...  To this end, the applications of artificial intelligence in five generic fields of molecular imaging and radiation therapy, including PET instrumentation design, PET image reconstruction quantification  ...  in an unsupervised mode (no ground truth exists for the denoised PET images) (Cui et al. 2019 ).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s41824-020-00086-8">doi:10.1186/s41824-020-00086-8</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34191161">pmid:34191161</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6qp2s2jwebbglk5gi3pfvozpie">fatcat:6qp2s2jwebbglk5gi3pfvozpie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210427122515/https://archive-ouverte.unige.ch/files/downloads/0/0/1/4/3/4/9/8/unige_143498_attachment01.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/33/b5/33b5515a3023292cade53c5eba736763b0946dfb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s41824-020-00086-8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

Augmented noise learning framework for enhancing medical image denoising

Swati Rai, Jignesh S. Bhatt, S. K. Patra
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Comparative experiments with many state-of-the-arts on MRI and CT datasets (2D/3D) including low-dose CT (LDCT) are conducted on a GPU-based supercomputer.  ...  The proposed network is trained by adding different levels of Rician noise for MRI and Poisson noise for CT images considering different nature and statistical distribution of datasets.  ...  They also thank to a team of qualified technicians, including Vikas Patel, Gujarat, India, for providing practical information on medical imaging techniques and to Dr.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3106707">doi:10.1109/access.2021.3106707</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uzz5bw3ayvckvlnxzdly5rd3p4">fatcat:uzz5bw3ayvckvlnxzdly5rd3p4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210910064642/https://ieeexplore.ieee.org/ielx7/6287639/9312710/09520361.pdf?tp=&amp;arnumber=9520361&amp;isnumber=9312710&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f2/5e/f25ebfffd80a545cfb3d56cdc7ba7a3143accd3d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3106707"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Applications of Deep Learning to Neuro-Imaging Techniques

Guangming Zhu, Bin Jiang, Liz Tong, Yuan Xie, Greg Zaharchuk, Max Wintermark
<span title="2019-08-14">2019</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4kchoxo3jrfubkck3y7nfncina" style="color: black;">Frontiers in Neurology</a> </i> &nbsp;
/harmonizing images, improving image quality, lowering radiation and contrast dose, and shortening the duration of imaging studies.  ...  Many clinical applications based on deep learning and pertaining to radiology have been proposed and studied in radiology for classification, risk assessment, segmentation tasks, diagnosis, prognosis,  ...  Pre-contrast MRI and low-dose post-contrast MRI of training set were introduced as inputs, and full dose post-contrast MRI as Ground-truth.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fneur.2019.00869">doi:10.3389/fneur.2019.00869</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/31474928">pmid:31474928</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC6702308/">pmcid:PMC6702308</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yki64mb57jhafduasd3hohfkgi">fatcat:yki64mb57jhafduasd3hohfkgi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200211212822/https://fjfsdata01prod.blob.core.windows.net/articles/files/459874/pubmed-zip/.versions/1/.package-entries/fneur-10-00869/fneur-10-00869.pdf?sv=2015-12-11&amp;sr=b&amp;sig=EUDwgJJNqR%2FwXW8adc2eD4NVtj%2BNXLEXUqhp3yk1Z5A%3D&amp;se=2020-02-11T21%3A28%3A52Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27fneur-10-00869.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5a/38/5a387fa2abcf4e518757383e5d2d95de8113d7c2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fneur.2019.00869"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6702308" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Improving Reproducibility and Performance of Radiomics in Low Dose CT using Cycle GANs [article]

Junhua Chen, Leonard Wee, Andre Dekker, Inigo Bermejo
<span title="2021-09-16">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Two cycle GANs were trained: 1) from paired data, by simulating low dose CTs (i.e., introducing noise) from high dose CTs; and 2) from unpaired real low dose CTs.  ...  In this article, we investigate the possibility of denoising low dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets  ...  [28] used a 3D residual network as the denoising network architecture with a loss function based on differences between the ground truth residual image and reconstructed residual image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.07787v1">arXiv:2109.07787v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x5nbe6ukp5fe7nkj4ippbcgyaq">fatcat:x5nbe6ukp5fe7nkj4ippbcgyaq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210918163654/https://arxiv.org/ftp/arxiv/papers/2109/2109.07787.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ce/bd/cebd4a260adb5efb82e65091863da9ef71d6aa82.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.07787v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised PET Reconstruction from a Bayesian Perspective [article]

Chenyu Shen, Wenjun Xia, Hongwei Ye, Mingzheng Hou, Hu Chen, Yan Liu, Jiliu Zhou, Yi Zhang
<span title="2021-10-29">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this article, we leverage DeepRED from a Bayesian perspective to reconstruct PET images from a single corrupted sinogram without any supervised or auxiliary information.  ...  Positron emission tomography (PET) reconstruction has become an ill-posed inverse problem due to low-count projection data, and a robust algorithm is urgently required to improve imaging quality.  ...  usually appeared in plain networks. 2) Learn the mapping from low-dose or low-count images to their corresponding full-dose or full-count images [28] - [31] , which can be treated as image restoration  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.15568v1">arXiv:2110.15568v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jje7z7ordjcmbkkas5qqemvyca">fatcat:jje7z7ordjcmbkkas5qqemvyca</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211108065420/https://arxiv.org/pdf/2110.15568v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d6/f8/d6f81c7dba38d68303985efeccc9670351e22b22.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.15568v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Unsupervised Knowledge-Transfer for Learned Image Reconstruction [article]

Riccardo Barbano, Zeljko Kereta, Andreas Hauptmann, Simon R. Arridge, Bangti Jin
<span title="2021-07-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The first phase trains a reconstruction network with a set of ordered pairs comprising of ground truth images and measurement data.  ...  To circumvent this issue, we develop a novel unsupervised knowledge-transfer paradigm for learned iterative reconstruction within a Bayesian framework.  ...  FOR EACH METHOD, APPROXIMATE RUNTIME FOR BOTH LOW-DOSE CT AND SPARSE-VIEW CT, AND THE NUMBER OF LEARNABLE PARAMETERS ARE ALSO INDICATED.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.02572v1">arXiv:2107.02572v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/buhruvdudreihlroxnylszq5fa">fatcat:buhruvdudreihlroxnylszq5fa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210711012732/https://arxiv.org/pdf/2107.02572v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/17/2f/172f50d4163628febc507d10d6408d6f78e72222.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.02572v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

The Use of Artificial Intelligence in Computed Tomography Image Reconstruction: A Systematic Review

Theresa Lee, Medical Radiation Imaging and Radiation Sciences, Monash University, Melbourne, Australia, Euclid Seeram, Medical Radiation Imaging and Radiation Sciences, Monash University, Melbourne, Australia
<span title="2020-12-31">2020</span> <i title="Openventio Publishers"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rboaa3v33bdejlfd5ksdnhtcfq" style="color: black;">Radiology - Open Journal</a> </i> &nbsp;
Aim The aim of this review is to examine the use of AI in CT image reconstruction and its effectiveness in enabling further dose reductions through improvements in image quality of low-dose CT images.  ...  Hence, with the increasing need for radiation dose reductions in CT, the use of artificial intelligence (AI) in image reconstruction has been an area of growing interest.  ...  In the training phase, supervised training was performed which involved inputting low dose raw data through the DNN and comparing the output image to a ground-truth image which was a high dose version  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.17140/roj-4-129">doi:10.17140/roj-4-129</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/57gyl7nogvcgbazxm7uo7w2b6a">fatcat:57gyl7nogvcgbazxm7uo7w2b6a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210122112533/https://openventio.org/wp-content/uploads/The-Use-of-Artificial-Intelligence-in-Computed-Tomography-Image-Reconstruction-A-Systematic-Review-ROJ-4-129.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5d/e7/5de7f63847c5c1d7c7213dead2a696f13aa3fbd0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.17140/roj-4-129"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 182 results