Homodyned K-Distribution Parameter Estimation in Quantitative Ultrasound: Autoencoder and Bayesian Neural Network Approaches
Quantitative ultrasound (QUS) analyzes the ultrasound (US) backscattered data to find the properties of scatterers that correlate with the tissue microstructure. Statistics of the envelope of the backscattered radio frequency (RF) data can be utilized to estimate several QUS parameters. Different di...
Uložené v:
| Vydané v: | IEEE transactions on ultrasonics, ferroelectrics, and frequency control Ročník 71; číslo 3; s. 354 - 365 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
IEEE
01.03.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Predmet: | |
| ISSN: | 0885-3010, 1525-8955, 1525-8955 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Quantitative ultrasound (QUS) analyzes the ultrasound (US) backscattered data to find the properties of scatterers that correlate with the tissue microstructure. Statistics of the envelope of the backscattered radio frequency (RF) data can be utilized to estimate several QUS parameters. Different distributions have been proposed to model envelope data. The homodyned K-distribution (HK-distribution) is one of the most comprehensive distributions that can model US backscattered envelope data under diverse scattering conditions (varying scatterer number density and coherent scattering). The scatterer clustering parameter (<inline-formula> <tex-math notation="LaTeX">\alpha </tex-math></inline-formula>) and the ratio of the coherent to diffuse scattering power (<inline-formula> <tex-math notation="LaTeX">{k} </tex-math></inline-formula>) are the parameters of this distribution that have been used extensively for tissue characterization in diagnostic US. The estimation of these two parameters (which we refer to as HK parameters) is done using optimization algorithms in which statistical features such as the envelope point-wise signal-to-noise ratio (SNR), skewness, kurtosis, and the log-based moments have been utilized as input to such algorithms. The optimization methods minimize the difference between features and their theoretical value from the HK model. We propose that the true value of these statistical features is a hyperplane that covers a small portion of the feature space. In this article, we follow two approaches to reduce the effect of sample features' error. We propose a model projection neural network based on denoising autoencoders to project the noisy features into this space based on this assumption. We also investigate if the noise distribution can be learned by the deep estimators. We compare the proposed methods with conventional methods using simulations, an experimental phantom, and data from an in vivo animal model of hepatic steatosis. The network weight and a demo code are available online at ht.tp://code.sonography.ai. |
|---|---|
| AbstractList | Quantitative ultrasound (QUS) analyzes the ultrasound (US) backscattered data to find the properties of scatterers that correlate with the tissue microstructure. Statistics of the envelope of the backscattered radio frequency (RF) data can be utilized to estimate several QUS parameters. Different distributions have been proposed to model envelope data. The homodyned K-distribution (HK-distribution) is one of the most comprehensive distributions that can model US backscattered envelope data under diverse scattering conditions (varying scatterer number density and coherent scattering). The scatterer clustering parameter ( α ) and the ratio of the coherent to diffuse scattering power ( k ) are the parameters of this distribution that have been used extensively for tissue characterization in diagnostic US. The estimation of these two parameters (which we refer to as HK parameters) is done using optimization algorithms in which statistical features such as the envelope point-wise signal-to-noise ratio (SNR), skewness, kurtosis, and the log-based moments have been utilized as input to such algorithms. The optimization methods minimize the difference between features and their theoretical value from the HK model. We propose that the true value of these statistical features is a hyperplane that covers a small portion of the feature space. In this article, we follow two approaches to reduce the effect of sample features' error. We propose a model projection neural network based on denoising autoencoders to project the noisy features into this space based on this assumption. We also investigate if the noise distribution can be learned by the deep estimators. We compare the proposed methods with conventional methods using simulations, an experimental phantom, and data from an in vivo animal model of hepatic steatosis. The network weight and a demo code are available online at ht.tp://code.sonography.ai.Quantitative ultrasound (QUS) analyzes the ultrasound (US) backscattered data to find the properties of scatterers that correlate with the tissue microstructure. Statistics of the envelope of the backscattered radio frequency (RF) data can be utilized to estimate several QUS parameters. Different distributions have been proposed to model envelope data. The homodyned K-distribution (HK-distribution) is one of the most comprehensive distributions that can model US backscattered envelope data under diverse scattering conditions (varying scatterer number density and coherent scattering). The scatterer clustering parameter ( α ) and the ratio of the coherent to diffuse scattering power ( k ) are the parameters of this distribution that have been used extensively for tissue characterization in diagnostic US. The estimation of these two parameters (which we refer to as HK parameters) is done using optimization algorithms in which statistical features such as the envelope point-wise signal-to-noise ratio (SNR), skewness, kurtosis, and the log-based moments have been utilized as input to such algorithms. The optimization methods minimize the difference between features and their theoretical value from the HK model. We propose that the true value of these statistical features is a hyperplane that covers a small portion of the feature space. In this article, we follow two approaches to reduce the effect of sample features' error. We propose a model projection neural network based on denoising autoencoders to project the noisy features into this space based on this assumption. We also investigate if the noise distribution can be learned by the deep estimators. We compare the proposed methods with conventional methods using simulations, an experimental phantom, and data from an in vivo animal model of hepatic steatosis. The network weight and a demo code are available online at ht.tp://code.sonography.ai. Quantitative ultrasound (QUS) analyzes the ultrasound (US) backscattered data to find the properties of scatterers that correlate with the tissue microstructure. Statistics of the envelope of the backscattered radio frequency (RF) data can be utilized to estimate several QUS parameters. Different distributions have been proposed to model envelope data. The homodyned K-distribution (HK-distribution) is one of the most comprehensive distributions that can model US backscattered envelope data under diverse scattering conditions (varying scatterer number density and coherent scattering). The scatterer clustering parameter (<inline-formula> <tex-math notation="LaTeX">\alpha </tex-math></inline-formula>) and the ratio of the coherent to diffuse scattering power (<inline-formula> <tex-math notation="LaTeX">{k} </tex-math></inline-formula>) are the parameters of this distribution that have been used extensively for tissue characterization in diagnostic US. The estimation of these two parameters (which we refer to as HK parameters) is done using optimization algorithms in which statistical features such as the envelope point-wise signal-to-noise ratio (SNR), skewness, kurtosis, and the log-based moments have been utilized as input to such algorithms. The optimization methods minimize the difference between features and their theoretical value from the HK model. We propose that the true value of these statistical features is a hyperplane that covers a small portion of the feature space. In this article, we follow two approaches to reduce the effect of sample features' error. We propose a model projection neural network based on denoising autoencoders to project the noisy features into this space based on this assumption. We also investigate if the noise distribution can be learned by the deep estimators. We compare the proposed methods with conventional methods using simulations, an experimental phantom, and data from an in vivo animal model of hepatic steatosis. The network weight and a demo code are available online at ht.tp://code.sonography.ai. Quantitative ultrasound (QUS) analyzes the ultrasound (US) backscattered data to find the properties of scatterers that correlate with the tissue microstructure. Statistics of the envelope of the backscattered radio frequency (RF) data can be utilized to estimate several QUS parameters. Different distributions have been proposed to model envelope data. The homodyned K-distribution (HK-distribution) is one of the most comprehensive distributions that can model US backscattered envelope data under diverse scattering conditions (varying scatterer number density and coherent scattering). The scatterer clustering parameter ([Formula Omitted]) and the ratio of the coherent to diffuse scattering power ([Formula Omitted]) are the parameters of this distribution that have been used extensively for tissue characterization in diagnostic US. The estimation of these two parameters (which we refer to as HK parameters) is done using optimization algorithms in which statistical features such as the envelope point-wise signal-to-noise ratio (SNR), skewness, kurtosis, and the log-based moments have been utilized as input to such algorithms. The optimization methods minimize the difference between features and their theoretical value from the HK model. We propose that the true value of these statistical features is a hyperplane that covers a small portion of the feature space. In this article, we follow two approaches to reduce the effect of sample features’ error. We propose a model projection neural network based on denoising autoencoders to project the noisy features into this space based on this assumption. We also investigate if the noise distribution can be learned by the deep estimators. We compare the proposed methods with conventional methods using simulations, an experimental phantom, and data from an in vivo animal model of hepatic steatosis. The network weight and a demo code are available online at ht.tp://code.sonography.ai. Quantitative ultrasound (QUS) analyzes the ultrasound backscattered data to find the properties of scatterers that correlate with the tissue microstructure. Statistics of the envelope of the backscattered radiofrequency (RF) data can be utilized to estimate several QUS parameters. Different distributions have been proposed to model envelope data. The homodyned K-distribution (HK-distribution) is one of the most comprehensive distributions that can model ultrasound backscattered envelope data under diverse scattering conditions (varying scatterer number density and coherent scattering). The scatterer clustering parameter (α) and the ratio of the coherent to diffuse scattering power (k) are the parameters of this distribution that have been used extensively for tissue characterization in diagnostic ultrasound. The estimation of these two parameters (which we refer to as HK parameters) is done using optimization algorithms in which statistical features such as the envelope point-wise signal-to-noise ratio (SNR), skewness, kurtosis, and the log-based moments have been utilized as input to such algorithms. The optimization methods minimize the difference between features and their theoretical value from the HK model. We propose that the true value of these statistical features is a hyperplane that covers a small portion of the feature space. In this paper, we follow two approaches to reduce the effect of sample features' error. We propose a model projection neural network based on denoising autoencoders to project the noisy features into this space based on this assumption. We also investigate if the noise distribution can be learned by the deep estimators. We compare the proposed methods with conventional methods using simulations, an experimental phantom, and data from an in vivo animal model of hepatic steatosis. The network weight and a demo code are available online at http://code.sonography.ai. |
| Author | Tehrani, Ali K. Z. Tang, An Cloutier, Guy Rosado-Mendez, Ivan M. Rivaz, Hassan |
| Author_xml | – sequence: 1 givenname: Ali K. Z. orcidid: 0000-0002-2686-8989 surname: Tehrani fullname: Tehrani, Ali K. Z. email: A_Kafaei@encs.concordia.ca organization: Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada – sequence: 2 givenname: Guy orcidid: 0000-0002-4957-4844 surname: Cloutier fullname: Cloutier, Guy email: guy.cloutier@umontreal.ca organization: Department of Radiology, Radio-Oncology and Nuclear Medicine, Institute of Biomedical Engineering, University of Montreal, Montreal, Canada – sequence: 3 givenname: An orcidid: 0000-0001-8967-5503 surname: Tang fullname: Tang, An email: an.tang@umontreal.ca organization: Department of Radiology, Radio-Oncology and Nuclear Medicine, University of Montreal, Montreal, Canada – sequence: 4 givenname: Ivan M. orcidid: 0000-0003-0778-1260 surname: Rosado-Mendez fullname: Rosado-Mendez, Ivan M. email: rosadomendez@wisc.edu organization: Department of Medical Physics and Radiology, University of Wisconsin, Madison, WI, USA – sequence: 5 givenname: Hassan orcidid: 0000-0001-5800-3034 surname: Rivaz fullname: Rivaz, Hassan email: hrivaz@ece.concordia.ca organization: Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38252581$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kUtvEzEURi1URNPCH0AIjcSmmwl-TjzsQmgoouIhNeuRx74jXGbs4AcoUn88bhIQ6oLVla1zfK3vO0MnzjtA6DnBc0Jw-_pms16v5hRTPmdMLDiTj9CMCCpq2QpxgmZYSlEzTPApOovxFmPCeUufoFMmacEkmaG7Kz95s3Ngqo_1OxtTsH1O1rvqiwpqggShuozJTmp_aV31NSuXbCrnn1BtxhRU9NmZN9UyJw9Oe1MU5Uz1Vu0gWuWqT5CDGstIv3z4Xi232-CV_gbxKXo8qDHCs-M8R5v15c3qqr7-_P7DanldayZoqsmgmsXQKymY1rzpzaAoEEYZBsH7oTdyAA4NMYJxJU3PG6mHHoZWSE5BK3aOLg7vlsU_MsTUTTZqGEflwOfY0ZYsZLMgTBT01QP01ufgyu8KxahoWMNZoV4eqdxPYLptKAGFXfcn1wLQA6CDjzHA8BchuLsvr9uX192X1x3LK5J8IOl9zt6VkO34f_XFQbUA8M8uTkgrGPsNzYup0Q |
| CODEN | ITUCER |
| CitedBy_id | crossref_primary_10_1109_TUFFC_2024_3384815 crossref_primary_10_1016_j_ultrasmedbio_2025_05_014 crossref_primary_10_1016_j_cmpb_2024_108374 crossref_primary_10_1016_j_slast_2025_100297 crossref_primary_10_1016_j_ultsonch_2024_106910 |
| Cites_doi | 10.1109/TUFFC.2018.2851846 10.1186/s13244-021-01071-w 10.1016/j.ultrasmedbio.2022.10.018 10.1121/10.0007047 10.1109/TUFFC.2023.3263119 10.1117/12.2651583 10.21037/qims.2019.08.03 10.1177/016173469001200105 10.1145/1390156.1390294 10.1016/j.ultrasmedbio.2022.11.019 10.1155/2022/1633858 10.1109/T-SU.1983.31404 10.1109/TUFFC.2015.2513958 10.1016/j.ultras.2022.106744 10.1109/ISBI53787.2023.10230797 10.1148/radiol.14140318 10.1109/ULTSYM.2019.8925666 10.1109/TUFFC.2009.1334 10.1007/978-3-031-21987-0_7 10.1016/j.ultrasmedbio.2020.03.005 10.1109/TUFFC.2016.2547341 10.4324/9780203734797-4 10.1109/TMI.2015.2479455 10.1137/120875727 10.1016/j.ultras.2020.106308 10.1109/TUFFC.2016.2532932 10.1109/ICASSP39728.2021.9413652 10.1109/TUFFC.2020.3042942 10.1109/TUFFC.2018.2869810 10.1177/016173469501700401 10.1109/TUFFC.2022.3166448 10.1016/j.ultrasmedbio.2019.10.024 10.3390/diagnostics10080557 10.1016/j.ultras.2019.106001 10.1109/ULTSYM.2007.200 10.1371/journal.pone.0262291 10.1177/0161734612464451 10.1016/j.psj.2021.101076 10.1109/TUFFC.2020.2973047 10.1016/j.ultras.2023.106987 10.1118/1.4962928 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SP 7U5 8FD F28 FR3 L7M 7X8 |
| DOI | 10.1109/TUFFC.2024.3357438 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef PubMed Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Advanced Technologies Database with Aerospace MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Solid State and Superconductivity Abstracts Engineering Research Database Technology Research Database Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Electronics & Communications Abstracts MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic Solid State and Superconductivity Abstracts PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Physics |
| EISSN | 1525-8955 |
| EndPage | 365 |
| ExternalDocumentID | 38252581 10_1109_TUFFC_2024_3357438 10411953 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: Fonds de Recherche du Québec under Audace Grant grantid: #2019-AUDC-263591 funderid: 10.13039/501100020951 – fundername: Natural Sciences and Engineering Research Council of Canada (NSERC) funderid: 10.13039/501100000038 – fundername: Fonds de Recherche du Québec-Santé (FRQS) grantid: 34939 funderid: 10.13039/501100000156 |
| GroupedDBID | --- -~X .GJ 0R~ 186 29I 3EH 4.4 53G 5GY 5RE 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 TWZ UKR VH1 ZXP ZY4 AAYXX CITATION NPM Z5M 7SP 7U5 8FD F28 FR3 L7M 7X8 |
| ID | FETCH-LOGICAL-c352t-1fa67fba853cc46bdfa2e13230e54bfbd8fe4e61d534a8db468cfbef95842eca3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 8 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001177955500002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0885-3010 1525-8955 |
| IngestDate | Mon Sep 29 05:30:03 EDT 2025 Mon Jun 30 16:36:10 EDT 2025 Wed Feb 19 02:09:23 EST 2025 Sat Nov 29 03:07:29 EST 2025 Tue Nov 18 20:52:05 EST 2025 Wed Aug 27 02:17:10 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c352t-1fa67fba853cc46bdfa2e13230e54bfbd8fe4e61d534a8db468cfbef95842eca3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-2686-8989 0000-0003-0778-1260 0000-0002-4957-4844 0000-0001-8967-5503 0000-0001-5800-3034 |
| PMID | 38252581 |
| PQID | 2932563643 |
| PQPubID | 85455 |
| PageCount | 12 |
| ParticipantIDs | crossref_primary_10_1109_TUFFC_2024_3357438 proquest_journals_2932563643 crossref_citationtrail_10_1109_TUFFC_2024_3357438 ieee_primary_10411953 proquest_miscellaneous_2917867135 pubmed_primary_38252581 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-03-01 |
| PublicationDateYYYYMMDD | 2024-03-01 |
| PublicationDate_xml | – month: 03 year: 2024 text: 2024-03-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE transactions on ultrasonics, ferroelectrics, and frequency control |
| PublicationTitleAbbrev | T-UFFC |
| PublicationTitleAlternate | IEEE Trans Ultrason Ferroelectr Freq Control |
| PublicationYear | 2024 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 ref31 ref30 ref11 ref33 ref10 McDonald (ref39) 2009; 2 ref2 ref1 ref17 Ladjal (ref32) 2019 ref16 ref38 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref42 ref41 ref22 ref21 ref43 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 |
| References_xml | – ident: ref38 doi: 10.1109/TUFFC.2018.2851846 – ident: ref43 doi: 10.1186/s13244-021-01071-w – ident: ref25 doi: 10.1016/j.ultrasmedbio.2022.10.018 – ident: ref42 doi: 10.1121/10.0007047 – ident: ref7 doi: 10.1109/TUFFC.2023.3263119 – ident: ref37 doi: 10.1117/12.2651583 – ident: ref17 doi: 10.21037/qims.2019.08.03 – ident: ref5 doi: 10.1177/016173469001200105 – ident: ref31 doi: 10.1145/1390156.1390294 – ident: ref28 doi: 10.1016/j.ultrasmedbio.2022.11.019 – ident: ref20 doi: 10.1155/2022/1633858 – ident: ref2 doi: 10.1109/T-SU.1983.31404 – ident: ref1 doi: 10.1109/TUFFC.2015.2513958 – ident: ref21 doi: 10.1016/j.ultras.2022.106744 – ident: ref30 doi: 10.1109/ISBI53787.2023.10230797 – ident: ref23 doi: 10.1148/radiol.14140318 – ident: ref19 doi: 10.1109/ULTSYM.2019.8925666 – volume: 2 volume-title: Handbook of Biological Statistics year: 2009 ident: ref39 – ident: ref26 doi: 10.1109/TUFFC.2009.1334 – ident: ref12 doi: 10.1007/978-3-031-21987-0_7 – ident: ref40 doi: 10.1016/j.ultrasmedbio.2020.03.005 – ident: ref11 doi: 10.1109/TUFFC.2016.2547341 – ident: ref35 doi: 10.4324/9780203734797-4 – ident: ref14 doi: 10.1109/TMI.2015.2479455 – ident: ref27 doi: 10.1137/120875727 – ident: ref29 doi: 10.1016/j.ultras.2020.106308 – year: 2019 ident: ref32 article-title: A PCA-like autoencoder publication-title: arXiv:1904.01277 – ident: ref6 doi: 10.1109/TUFFC.2016.2532932 – ident: ref8 doi: 10.1109/ICASSP39728.2021.9413652 – ident: ref3 doi: 10.1109/TUFFC.2020.3042942 – ident: ref4 doi: 10.1109/TUFFC.2018.2869810 – ident: ref13 doi: 10.1177/016173469501700401 – ident: ref10 doi: 10.1109/TUFFC.2022.3166448 – ident: ref22 doi: 10.1016/j.ultrasmedbio.2019.10.024 – ident: ref16 doi: 10.3390/diagnostics10080557 – ident: ref18 doi: 10.1016/j.ultras.2019.106001 – ident: ref41 doi: 10.1109/ULTSYM.2007.200 – ident: ref15 doi: 10.1371/journal.pone.0262291 – ident: ref34 doi: 10.1177/0161734612464451 – ident: ref36 doi: 10.1016/j.psj.2021.101076 – ident: ref9 doi: 10.1109/TUFFC.2020.2973047 – ident: ref33 doi: 10.1016/j.ultras.2023.106987 – ident: ref24 doi: 10.1118/1.4962928 |
| SSID | ssj0014492 |
| Score | 2.46546 |
| Snippet | Quantitative ultrasound (QUS) analyzes the ultrasound (US) backscattered data to find the properties of scatterers that correlate with the tissue... Quantitative ultrasound (QUS) analyzes the ultrasound backscattered data to find the properties of scatterers that correlate with the tissue microstructure.... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 354 |
| SubjectTerms | Algorithms Autoencoder Backscattering Clustering Coherent scattering deep learning (DL) homodyned K-distribution Hyperplanes In vivo methods and tests K-distribution Kurtosis Mathematical models Neural networks Noise reduction Optimization Optimization methods Parameter estimation quantitative ultrasound (QUS) Radio frequency Scattering Signal to noise ratio Ultrasonic imaging |
| Title | Homodyned K-Distribution Parameter Estimation in Quantitative Ultrasound: Autoencoder and Bayesian Neural Network Approaches |
| URI | https://ieeexplore.ieee.org/document/10411953 https://www.ncbi.nlm.nih.gov/pubmed/38252581 https://www.proquest.com/docview/2932563643 https://www.proquest.com/docview/2917867135 |
| Volume | 71 |
| WOSCitedRecordID | wos001177955500002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 1525-8955 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014492 issn: 0885-3010 databaseCode: RIE dateStart: 19860101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3daxQxEA-2KOiDH7XqaS0RfJOtu9lkN_HtrD0KwlGhB_e25GMChXZXbneFgn-8k2TvqA8VfFtIsgn7m2RmNjO_IeSjMV5Z5l2WaxAZ5yoWcjeZsSw3YEwllInFJurlUq7X6mJKVo-5MAAQg8_gJDzGu3zX2TH8KsMdzgNDWblH9uq6SslauysDnIclk1FkKLX5NkMmV58vV4vFKfqCjJ-UpUCdGar0legbMSGLvxRSrLByv7EZlc7i2X8u9zl5OlmXdJ7E4QV5AO0BeXKHc_CAPIoxn7Z_SX6fdzedu8Vzln7PvgUC3an2Fb3QIWQLvzg9wxMgJTfSq5b-GHUbk9LwiKSr62Gj-1CV6Qudj0MXGDEdDtGto1_1LYTsTBq4P3BByxRsTucTgzn0h2S1OLs8Pc-mYgyZRRttyAqvq9objerdWkTTec0AXdkyB8GNN0564FAVTpRcS2d4Ja034BVaOAysLl-R_bZr4Q2hSihZaygMZ44zREMybyVamiU6Q-jVzkixRaSxE1N5KJhx3USPJVdNBLQJgDYToDPyaTfmZ-Lp-GfvwwDXnZ4JqRk52iLfTHu5b9AgQrsQ14bNH3bNuAvD1YpuoRtDn6IOTIGlmJHXSWJ2L98K2tt7Jn1HHoe1pcC2I7I_bEZ4Tx7aX8NVvzlGUV_L4yjqfwD9E_m8 |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB1BAQEHPtoCCwWMxA2lJI69m3BbSleLWlZF2pV6i_wxliqVBG0SpEr8eMaOd1UOReIWKXZi5Y3tmXjmPYD3WrvScGeTVKFMhCiDkLtOtOGpRq3HstRBbGKyWBTn5-VZLFYPtTCIGJLP8NBfhrN825je_yqjGS48Q1l-G-546axYrrU9NKA38cFplAnZbbqpkUnLj8vVbHZE0SAXh3kuadf0On05RUdcFtlfW1LQWLnZ3Qzbzuzxfw74CTyK_iWbDgbxFG5hvQsPr7EO7sK9kPVp2j34PW9-NPaKVlp2knzxFLpR_YqdKZ-0Rd-cHdMaMJQ3souafe9VHcrSaJFkq8turVqvy_SJTfuu8ZyYlrqo2rLP6gp9fSbz7B80oMWQbs6mkcMc231YzY6XR_MkyjEkhry0LsmcGk-cVrTBG0N4Wqc4UjCbpyiFdtoWDgWOMytzoQqrxbgwTqMrycfhaFT-DHbqpsYXwEpZFhOFmRbcCk5oFNyZgnzNnMIhimtHkG0QqUzkKveSGZdViFnSsgqAVh7QKgI6gg_bPj8Hpo5_tt73cF1rOSA1goMN8lWczW1FLhF5hjQ2uv1ue5vmoT9cUTU2vW-TTTxXYC5H8HywmO3DN4b28oaXvoX78-W30-r06-LkFTzw4xzS3A5gp1v3-Bruml_dRbt-Ewz-D0AA_B0 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Homodyned+K-Distribution+Parameter+Estimation+in+Quantitative+Ultrasound%3A+Autoencoder+and+Bayesian+Neural+Network+Approaches&rft.jtitle=IEEE+transactions+on+ultrasonics%2C+ferroelectrics%2C+and+frequency+control&rft.au=Tehrani%2C+Ali+K.+Z.&rft.au=Cloutier%2C+Guy&rft.au=Tang%2C+An&rft.au=Rosado-Mendez%2C+Ivan+M.&rft.date=2024-03-01&rft.pub=IEEE&rft.issn=0885-3010&rft.volume=71&rft.issue=3&rft.spage=354&rft.epage=365&rft_id=info:doi/10.1109%2FTUFFC.2024.3357438&rft_id=info%3Apmid%2F38252581&rft.externalDocID=10411953 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0885-3010&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0885-3010&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0885-3010&client=summon |