No Cover Image

Conference Paper/Proceeding/Abstract 968 views 320 downloads

MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)

Omniah Nagoor, J. Whittle, Jingjing Deng, Benjamin Mora Orcid Logo, Mark Jones Orcid Logo, Joss O. Whittle Orcid Logo

2020 25th International Conference on Pattern Recognition (ICPR)

Swansea University Authors: Omniah Nagoor, Jingjing Deng, Benjamin Mora Orcid Logo, Mark Jones Orcid Logo, Joss O. Whittle Orcid Logo

  • 2020_MedZip_ICPR.pdf

    PDF | Accepted Manuscript

    Copyright information Available here; https://conferences.ieeeauthorcenter.ieee.org/get-published/post-your-paper/

    Download (178.42KB)

DOI (Published version): 10.1109/icpr48806.2021.9413341

Abstract

As scanners produce higher-resolution and more densely sampled images, this raises the challenge of data storage, transmission and communication within healthcare systems. Since the quality of medical images plays a crucial role in diagnosis accuracy, medical imaging compression techniques are desir...

Full description

Published in: 2020 25th International Conference on Pattern Recognition (ICPR)
ISBN: 9781728188089
Published: IEEE 2021
Online Access: http://dx.doi.org/10.1109/icpr48806.2021.9413341
URI: https://cronfa.swan.ac.uk/Record/cronfa55395
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2020-10-12T09:22:48Z
last_indexed 2021-09-25T03:17:22Z
id cronfa55395
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-09-24T10:46:58.4864569</datestamp><bib-version>v2</bib-version><id>55395</id><entry>2020-10-11</entry><title>MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)</title><swanseaauthors><author><sid>ad8a0ed9b747350e0d626fe4398a9fe0</sid><firstname>Omniah</firstname><surname>Nagoor</surname><name>Omniah Nagoor</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>6f6d01d585363d6dc1622640bb4fcb3f</sid><firstname>Jingjing</firstname><surname>Deng</surname><name>Jingjing Deng</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>557f93dfae240600e5bd4398bf203821</sid><ORCID>0000-0002-2945-3519</ORCID><firstname>Benjamin</firstname><surname>Mora</surname><name>Benjamin Mora</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>2e1030b6e14fc9debd5d5ae7cc335562</sid><ORCID>0000-0001-8991-1190</ORCID><firstname>Mark</firstname><surname>Jones</surname><name>Mark Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>2ffb82878e554c1b90ebc37971872fa7</sid><ORCID>NULL</ORCID><firstname>Joss O.</firstname><surname>Whittle</surname><name>Joss O. Whittle</name><active>true</active><ethesisStudent>true</ethesisStudent></author></swanseaauthors><date>2020-10-11</date><deptcode>SCS</deptcode><abstract>As scanners produce higher-resolution and more densely sampled images, this raises the challenge of data storage, transmission and communication within healthcare systems. Since the quality of medical images plays a crucial role in diagnosis accuracy, medical imaging compression techniques are desired to reduce scan bitrate while guaranteeing lossless reconstruction. This paper presents a lossless compression method that integrates a Recurrent Neural Network (RNN) as a 3D sequence prediction model. The aim is to learn the long dependencies of the voxel's neighbourhood in 3D using Long Short-Term Memory (LSTM) network then compress the residual error using arithmetic coding. Experiential results reveal that our method obtains a higher compression ratio achieving 15% saving compared to the state-of-the-art lossless compression standards, including JPEG-LS, JPEG2000, JP3D, HEVC, and PPMd. Our evaluation demonstrates that the proposed method generalizes well to unseen modalities CT and MRI for the lossless compression scheme. To the best of our knowledge, this is the first lossless compression method that uses LSTM neural network for 16-bit volumetric medical image compression.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>2020 25th International Conference on Pattern Recognition (ICPR)</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>IEEE</publisher><placeOfPublication/><isbnPrint/><isbnElectronic>9781728188089</isbnElectronic><issnPrint/><issnElectronic/><keywords/><publishedDay>10</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-01-10</publishedDate><doi>10.1109/icpr48806.2021.9413341</doi><url>http://dx.doi.org/10.1109/icpr48806.2021.9413341</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-09-24T10:46:58.4864569</lastEdited><Created>2020-10-11T09:49:46.1295788</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Omniah</firstname><surname>Nagoor</surname><order>1</order></author><author><firstname>J.</firstname><surname>Whittle</surname><order>2</order></author><author><firstname>Jingjing</firstname><surname>Deng</surname><order>3</order></author><author><firstname>Benjamin</firstname><surname>Mora</surname><orcid>0000-0002-2945-3519</orcid><order>4</order></author><author><firstname>Mark</firstname><surname>Jones</surname><orcid>0000-0001-8991-1190</orcid><order>5</order></author><author><firstname>Joss O.</firstname><surname>Whittle</surname><orcid>NULL</orcid><order>6</order></author></authors><documents><document><filename>55395__18418__e5422e1a83334b39b601c095faf8c110.pdf</filename><originalFilename>2020_MedZip_ICPR.pdf</originalFilename><uploaded>2020-10-14T09:34:45.0888534</uploaded><type>Output</type><contentLength>182707</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright information Available here; https://conferences.ieeeauthorcenter.ieee.org/get-published/post-your-paper/</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2021-09-24T10:46:58.4864569 v2 55395 2020-10-11 MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM) ad8a0ed9b747350e0d626fe4398a9fe0 Omniah Nagoor Omniah Nagoor true false 6f6d01d585363d6dc1622640bb4fcb3f Jingjing Deng Jingjing Deng true false 557f93dfae240600e5bd4398bf203821 0000-0002-2945-3519 Benjamin Mora Benjamin Mora true false 2e1030b6e14fc9debd5d5ae7cc335562 0000-0001-8991-1190 Mark Jones Mark Jones true false 2ffb82878e554c1b90ebc37971872fa7 NULL Joss O. Whittle Joss O. Whittle true true 2020-10-11 SCS As scanners produce higher-resolution and more densely sampled images, this raises the challenge of data storage, transmission and communication within healthcare systems. Since the quality of medical images plays a crucial role in diagnosis accuracy, medical imaging compression techniques are desired to reduce scan bitrate while guaranteeing lossless reconstruction. This paper presents a lossless compression method that integrates a Recurrent Neural Network (RNN) as a 3D sequence prediction model. The aim is to learn the long dependencies of the voxel's neighbourhood in 3D using Long Short-Term Memory (LSTM) network then compress the residual error using arithmetic coding. Experiential results reveal that our method obtains a higher compression ratio achieving 15% saving compared to the state-of-the-art lossless compression standards, including JPEG-LS, JPEG2000, JP3D, HEVC, and PPMd. Our evaluation demonstrates that the proposed method generalizes well to unseen modalities CT and MRI for the lossless compression scheme. To the best of our knowledge, this is the first lossless compression method that uses LSTM neural network for 16-bit volumetric medical image compression. Conference Paper/Proceeding/Abstract 2020 25th International Conference on Pattern Recognition (ICPR) IEEE 9781728188089 10 1 2021 2021-01-10 10.1109/icpr48806.2021.9413341 http://dx.doi.org/10.1109/icpr48806.2021.9413341 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2021-09-24T10:46:58.4864569 2020-10-11T09:49:46.1295788 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Omniah Nagoor 1 J. Whittle 2 Jingjing Deng 3 Benjamin Mora 0000-0002-2945-3519 4 Mark Jones 0000-0001-8991-1190 5 Joss O. Whittle NULL 6 55395__18418__e5422e1a83334b39b601c095faf8c110.pdf 2020_MedZip_ICPR.pdf 2020-10-14T09:34:45.0888534 Output 182707 application/pdf Accepted Manuscript true Copyright information Available here; https://conferences.ieeeauthorcenter.ieee.org/get-published/post-your-paper/ true eng
title MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)
spellingShingle MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)
Omniah Nagoor
Jingjing Deng
Benjamin Mora
Mark Jones
Joss O. Whittle
title_short MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)
title_full MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)
title_fullStr MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)
title_full_unstemmed MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)
title_sort MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)
author_id_str_mv ad8a0ed9b747350e0d626fe4398a9fe0
6f6d01d585363d6dc1622640bb4fcb3f
557f93dfae240600e5bd4398bf203821
2e1030b6e14fc9debd5d5ae7cc335562
2ffb82878e554c1b90ebc37971872fa7
author_id_fullname_str_mv ad8a0ed9b747350e0d626fe4398a9fe0_***_Omniah Nagoor
6f6d01d585363d6dc1622640bb4fcb3f_***_Jingjing Deng
557f93dfae240600e5bd4398bf203821_***_Benjamin Mora
2e1030b6e14fc9debd5d5ae7cc335562_***_Mark Jones
2ffb82878e554c1b90ebc37971872fa7_***_Joss O. Whittle
author Omniah Nagoor
Jingjing Deng
Benjamin Mora
Mark Jones
Joss O. Whittle
author2 Omniah Nagoor
J. Whittle
Jingjing Deng
Benjamin Mora
Mark Jones
Joss O. Whittle
format Conference Paper/Proceeding/Abstract
container_title 2020 25th International Conference on Pattern Recognition (ICPR)
publishDate 2021
institution Swansea University
isbn 9781728188089
doi_str_mv 10.1109/icpr48806.2021.9413341
publisher IEEE
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.1109/icpr48806.2021.9413341
document_store_str 1
active_str 0
description As scanners produce higher-resolution and more densely sampled images, this raises the challenge of data storage, transmission and communication within healthcare systems. Since the quality of medical images plays a crucial role in diagnosis accuracy, medical imaging compression techniques are desired to reduce scan bitrate while guaranteeing lossless reconstruction. This paper presents a lossless compression method that integrates a Recurrent Neural Network (RNN) as a 3D sequence prediction model. The aim is to learn the long dependencies of the voxel's neighbourhood in 3D using Long Short-Term Memory (LSTM) network then compress the residual error using arithmetic coding. Experiential results reveal that our method obtains a higher compression ratio achieving 15% saving compared to the state-of-the-art lossless compression standards, including JPEG-LS, JPEG2000, JP3D, HEVC, and PPMd. Our evaluation demonstrates that the proposed method generalizes well to unseen modalities CT and MRI for the lossless compression scheme. To the best of our knowledge, this is the first lossless compression method that uses LSTM neural network for 16-bit volumetric medical image compression.
published_date 2021-01-10T04:09:34Z
_version_ 1763753668771840000
score 11.035634

Similar Items