Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts
Motivation: High resolution 2D whole slide imaging provides rich information about the tissue structure. This information can be a lot richer if these 2D images can be stacked into a 3D tissue volume. A 3D analysis, however, requires accurate reconstruction of the tissue volume from the 2D image sta...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Paknezhad, Mahsa Loh, Sheng Yang Michael Choudhury, Yukti Koh, Valerie Koh Cui Yong, TimothyTay Kwang Tan, Hui Shan Kanesvaran, Ravindran Tan, Puay Hoon Peng, John Yuen Shyi Yu, Weimiao Tan, Yongcheng Benjamin Loy, Yong Zhen Tan, Min-Han Lee, Hwee Kuan |
description | Motivation: High resolution 2D whole slide imaging provides rich information
about the tissue structure. This information can be a lot richer if these 2D
images can be stacked into a 3D tissue volume. A 3D analysis, however, requires
accurate reconstruction of the tissue volume from the 2D image stack. This task
is not trivial due to the distortions that each individual tissue slice
experiences while cutting and mounting the tissue on the glass slide.
Performing registration for the whole tissue slices may be adversely affected
by the deformed tissue regions. Consequently, regional registration is found to
be more effective. In this paper, we propose an accurate and robust regional
registration algorithm for whole slide images which incrementally focuses
registration on the area around the region of interest. Results: Using mean
similarity index as the metric, the proposed algorithm (mean $\pm$ std: $0.84
\pm 0.11$) followed by a fine registration algorithm ($0.86 \pm 0.08$)
outperformed the state-of-the-art linear whole tissue registration algorithm
($0.74 \pm 0.19$) and the regional version of this algorithm ($0.81 \pm 0.15$).
The proposed algorithm also outperforms the state-of-the-art nonlinear
registration algorithm (original : $0.82 \pm 0.12$, regional : $0.77 \pm 0.22$)
for whole slide images and a recently proposed patch-based registration
algorithm (patch size 256: $0.79 \pm 0.16$ , patch size 512: $0.77 \pm 0.16$)
for medical images. Availability: The C++ implementation code is available
online at the github repository:
https://github.com/MahsaPaknezhad/WSIRegistration |
doi_str_mv | 10.48550/arxiv.2002.12588 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2002_12588</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2002_12588</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-5200eb0585d4986c711829a99b5ca610444dd1c3a2fb27c55274fa628bbe284d3</originalsourceid><addsrcrecordid>eNotj8tOwzAURL1hgQofwAr_QILt2ImzrMKjlSpVggqW0fUrtXBi5FiI_j1pYTVnNqM5CN1RUnIpBHmA9OO_S0YIKykTUl6j91c7-DhBwGeYc4K8VBwd_jjGYPFb8Mbi7QjDwhn054y7OGXwk58GvPHDMZzwo3UxjdbgdcrWgc7zDbpyEGZ7-58rdHh-OnSbYrd_2XbrXQF1IwuxPLGKCCkMb2WtG0ola6FtldBQU8I5N4bqCphTrNFCsIY7qJlUyjLJTbVC93-zF7H-K_kR0qk_C_YXweoX8zdK9A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts</title><source>arXiv.org</source><creator>Paknezhad, Mahsa ; Loh, Sheng Yang Michael ; Choudhury, Yukti ; Koh, Valerie Koh Cui ; Yong, TimothyTay Kwang ; Tan, Hui Shan ; Kanesvaran, Ravindran ; Tan, Puay Hoon ; Peng, John Yuen Shyi ; Yu, Weimiao ; Tan, Yongcheng Benjamin ; Loy, Yong Zhen ; Tan, Min-Han ; Lee, Hwee Kuan</creator><creatorcontrib>Paknezhad, Mahsa ; Loh, Sheng Yang Michael ; Choudhury, Yukti ; Koh, Valerie Koh Cui ; Yong, TimothyTay Kwang ; Tan, Hui Shan ; Kanesvaran, Ravindran ; Tan, Puay Hoon ; Peng, John Yuen Shyi ; Yu, Weimiao ; Tan, Yongcheng Benjamin ; Loy, Yong Zhen ; Tan, Min-Han ; Lee, Hwee Kuan</creatorcontrib><description>Motivation: High resolution 2D whole slide imaging provides rich information
about the tissue structure. This information can be a lot richer if these 2D
images can be stacked into a 3D tissue volume. A 3D analysis, however, requires
accurate reconstruction of the tissue volume from the 2D image stack. This task
is not trivial due to the distortions that each individual tissue slice
experiences while cutting and mounting the tissue on the glass slide.
Performing registration for the whole tissue slices may be adversely affected
by the deformed tissue regions. Consequently, regional registration is found to
be more effective. In this paper, we propose an accurate and robust regional
registration algorithm for whole slide images which incrementally focuses
registration on the area around the region of interest. Results: Using mean
similarity index as the metric, the proposed algorithm (mean $\pm$ std: $0.84
\pm 0.11$) followed by a fine registration algorithm ($0.86 \pm 0.08$)
outperformed the state-of-the-art linear whole tissue registration algorithm
($0.74 \pm 0.19$) and the regional version of this algorithm ($0.81 \pm 0.15$).
The proposed algorithm also outperforms the state-of-the-art nonlinear
registration algorithm (original : $0.82 \pm 0.12$, regional : $0.77 \pm 0.22$)
for whole slide images and a recently proposed patch-based registration
algorithm (patch size 256: $0.79 \pm 0.16$ , patch size 512: $0.77 \pm 0.16$)
for medical images. Availability: The C++ implementation code is available
online at the github repository:
https://github.com/MahsaPaknezhad/WSIRegistration</description><identifier>DOI: 10.48550/arxiv.2002.12588</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning</subject><creationdate>2020-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2002.12588$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2002.12588$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Paknezhad, Mahsa</creatorcontrib><creatorcontrib>Loh, Sheng Yang Michael</creatorcontrib><creatorcontrib>Choudhury, Yukti</creatorcontrib><creatorcontrib>Koh, Valerie Koh Cui</creatorcontrib><creatorcontrib>Yong, TimothyTay Kwang</creatorcontrib><creatorcontrib>Tan, Hui Shan</creatorcontrib><creatorcontrib>Kanesvaran, Ravindran</creatorcontrib><creatorcontrib>Tan, Puay Hoon</creatorcontrib><creatorcontrib>Peng, John Yuen Shyi</creatorcontrib><creatorcontrib>Yu, Weimiao</creatorcontrib><creatorcontrib>Tan, Yongcheng Benjamin</creatorcontrib><creatorcontrib>Loy, Yong Zhen</creatorcontrib><creatorcontrib>Tan, Min-Han</creatorcontrib><creatorcontrib>Lee, Hwee Kuan</creatorcontrib><title>Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts</title><description>Motivation: High resolution 2D whole slide imaging provides rich information
about the tissue structure. This information can be a lot richer if these 2D
images can be stacked into a 3D tissue volume. A 3D analysis, however, requires
accurate reconstruction of the tissue volume from the 2D image stack. This task
is not trivial due to the distortions that each individual tissue slice
experiences while cutting and mounting the tissue on the glass slide.
Performing registration for the whole tissue slices may be adversely affected
by the deformed tissue regions. Consequently, regional registration is found to
be more effective. In this paper, we propose an accurate and robust regional
registration algorithm for whole slide images which incrementally focuses
registration on the area around the region of interest. Results: Using mean
similarity index as the metric, the proposed algorithm (mean $\pm$ std: $0.84
\pm 0.11$) followed by a fine registration algorithm ($0.86 \pm 0.08$)
outperformed the state-of-the-art linear whole tissue registration algorithm
($0.74 \pm 0.19$) and the regional version of this algorithm ($0.81 \pm 0.15$).
The proposed algorithm also outperforms the state-of-the-art nonlinear
registration algorithm (original : $0.82 \pm 0.12$, regional : $0.77 \pm 0.22$)
for whole slide images and a recently proposed patch-based registration
algorithm (patch size 256: $0.79 \pm 0.16$ , patch size 512: $0.77 \pm 0.16$)
for medical images. Availability: The C++ implementation code is available
online at the github repository:
https://github.com/MahsaPaknezhad/WSIRegistration</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAURL1hgQofwAr_QILt2ImzrMKjlSpVggqW0fUrtXBi5FiI_j1pYTVnNqM5CN1RUnIpBHmA9OO_S0YIKykTUl6j91c7-DhBwGeYc4K8VBwd_jjGYPFb8Mbi7QjDwhn054y7OGXwk58GvPHDMZzwo3UxjdbgdcrWgc7zDbpyEGZ7-58rdHh-OnSbYrd_2XbrXQF1IwuxPLGKCCkMb2WtG0ola6FtldBQU8I5N4bqCphTrNFCsIY7qJlUyjLJTbVC93-zF7H-K_kR0qk_C_YXweoX8zdK9A</recordid><startdate>20200228</startdate><enddate>20200228</enddate><creator>Paknezhad, Mahsa</creator><creator>Loh, Sheng Yang Michael</creator><creator>Choudhury, Yukti</creator><creator>Koh, Valerie Koh Cui</creator><creator>Yong, TimothyTay Kwang</creator><creator>Tan, Hui Shan</creator><creator>Kanesvaran, Ravindran</creator><creator>Tan, Puay Hoon</creator><creator>Peng, John Yuen Shyi</creator><creator>Yu, Weimiao</creator><creator>Tan, Yongcheng Benjamin</creator><creator>Loy, Yong Zhen</creator><creator>Tan, Min-Han</creator><creator>Lee, Hwee Kuan</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200228</creationdate><title>Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts</title><author>Paknezhad, Mahsa ; Loh, Sheng Yang Michael ; Choudhury, Yukti ; Koh, Valerie Koh Cui ; Yong, TimothyTay Kwang ; Tan, Hui Shan ; Kanesvaran, Ravindran ; Tan, Puay Hoon ; Peng, John Yuen Shyi ; Yu, Weimiao ; Tan, Yongcheng Benjamin ; Loy, Yong Zhen ; Tan, Min-Han ; Lee, Hwee Kuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-5200eb0585d4986c711829a99b5ca610444dd1c3a2fb27c55274fa628bbe284d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Paknezhad, Mahsa</creatorcontrib><creatorcontrib>Loh, Sheng Yang Michael</creatorcontrib><creatorcontrib>Choudhury, Yukti</creatorcontrib><creatorcontrib>Koh, Valerie Koh Cui</creatorcontrib><creatorcontrib>Yong, TimothyTay Kwang</creatorcontrib><creatorcontrib>Tan, Hui Shan</creatorcontrib><creatorcontrib>Kanesvaran, Ravindran</creatorcontrib><creatorcontrib>Tan, Puay Hoon</creatorcontrib><creatorcontrib>Peng, John Yuen Shyi</creatorcontrib><creatorcontrib>Yu, Weimiao</creatorcontrib><creatorcontrib>Tan, Yongcheng Benjamin</creatorcontrib><creatorcontrib>Loy, Yong Zhen</creatorcontrib><creatorcontrib>Tan, Min-Han</creatorcontrib><creatorcontrib>Lee, Hwee Kuan</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Paknezhad, Mahsa</au><au>Loh, Sheng Yang Michael</au><au>Choudhury, Yukti</au><au>Koh, Valerie Koh Cui</au><au>Yong, TimothyTay Kwang</au><au>Tan, Hui Shan</au><au>Kanesvaran, Ravindran</au><au>Tan, Puay Hoon</au><au>Peng, John Yuen Shyi</au><au>Yu, Weimiao</au><au>Tan, Yongcheng Benjamin</au><au>Loy, Yong Zhen</au><au>Tan, Min-Han</au><au>Lee, Hwee Kuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts</atitle><date>2020-02-28</date><risdate>2020</risdate><abstract>Motivation: High resolution 2D whole slide imaging provides rich information
about the tissue structure. This information can be a lot richer if these 2D
images can be stacked into a 3D tissue volume. A 3D analysis, however, requires
accurate reconstruction of the tissue volume from the 2D image stack. This task
is not trivial due to the distortions that each individual tissue slice
experiences while cutting and mounting the tissue on the glass slide.
Performing registration for the whole tissue slices may be adversely affected
by the deformed tissue regions. Consequently, regional registration is found to
be more effective. In this paper, we propose an accurate and robust regional
registration algorithm for whole slide images which incrementally focuses
registration on the area around the region of interest. Results: Using mean
similarity index as the metric, the proposed algorithm (mean $\pm$ std: $0.84
\pm 0.11$) followed by a fine registration algorithm ($0.86 \pm 0.08$)
outperformed the state-of-the-art linear whole tissue registration algorithm
($0.74 \pm 0.19$) and the regional version of this algorithm ($0.81 \pm 0.15$).
The proposed algorithm also outperforms the state-of-the-art nonlinear
registration algorithm (original : $0.82 \pm 0.12$, regional : $0.77 \pm 0.22$)
for whole slide images and a recently proposed patch-based registration
algorithm (patch size 256: $0.79 \pm 0.16$ , patch size 512: $0.77 \pm 0.16$)
for medical images. Availability: The C++ implementation code is available
online at the github repository:
https://github.com/MahsaPaknezhad/WSIRegistration</abstract><doi>10.48550/arxiv.2002.12588</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2002.12588 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2002_12588 |
source | arXiv.org |
subjects | Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning |
title | Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A52%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Regional%20Registration%20of%20Whole%20Slide%20Image%20Stacks%20Containing%20Highly%20Deformed%20Artefacts&rft.au=Paknezhad,%20Mahsa&rft.date=2020-02-28&rft_id=info:doi/10.48550/arxiv.2002.12588&rft_dat=%3Carxiv_GOX%3E2002_12588%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |