Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images
Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully...
Ausführliche Beschreibung
Autor*in: |
Jin, Zhihao [verfasserIn] |
---|
Format: |
Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2022 |
---|
Schlagwörter: |
---|
Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
---|
Übergeordnetes Werk: |
Enthalten in: Neural computing & applications - Springer London, 1993, 34(2022), 24 vom: 22. Aug., Seite 22357-22366 |
---|---|
Übergeordnetes Werk: |
volume:34 ; year:2022 ; number:24 ; day:22 ; month:08 ; pages:22357-22366 |
Links: |
---|
DOI / URN: |
10.1007/s00521-022-07719-y |
---|
Katalog-ID: |
OLC207992592X |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | OLC207992592X | ||
003 | DE-627 | ||
005 | 20230506084603.0 | ||
007 | tu | ||
008 | 230131s2022 xx ||||| 00| ||eng c | ||
024 | 7 | |a 10.1007/s00521-022-07719-y |2 doi | |
035 | |a (DE-627)OLC207992592X | ||
035 | |a (DE-He213)s00521-022-07719-y-p | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 004 |q VZ |
100 | 1 | |a Jin, Zhihao |e verfasserin |4 aut | |
245 | 1 | 0 | |a Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
500 | |a © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. | ||
520 | |a Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. | ||
650 | 4 | |a Thyroid nodule | |
650 | 4 | |a Segmentation | |
650 | 4 | |a Boundary | |
700 | 1 | |a Li, Xuechen |4 aut | |
700 | 1 | |a Zhang, Yudi |4 aut | |
700 | 1 | |a Shen, LinLin |0 (orcid)0000-0003-1420-0815 |4 aut | |
700 | 1 | |a Lai, Zhihui |4 aut | |
700 | 1 | |a Kong, Heng |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Neural computing & applications |d Springer London, 1993 |g 34(2022), 24 vom: 22. Aug., Seite 22357-22366 |w (DE-627)165669608 |w (DE-600)1136944-9 |w (DE-576)032873050 |x 0941-0643 |7 nnns |
773 | 1 | 8 | |g volume:34 |g year:2022 |g number:24 |g day:22 |g month:08 |g pages:22357-22366 |
856 | 4 | 1 | |u https://doi.org/10.1007/s00521-022-07719-y |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_OLC | ||
912 | |a SSG-OLC-MAT | ||
912 | |a GBV_ILN_2018 | ||
912 | |a GBV_ILN_4277 | ||
951 | |a AR | ||
952 | |d 34 |j 2022 |e 24 |b 22 |c 08 |h 22357-22366 |
author_variant |
z j zj x l xl y z yz l s ls z l zl h k hk |
---|---|
matchkey_str |
article:09410643:2022----::onayersinaerenuantokotyodoueemn |
hierarchy_sort_str |
2022 |
publishDate |
2022 |
allfields |
10.1007/s00521-022-07719-y doi (DE-627)OLC207992592X (DE-He213)s00521-022-07719-y-p DE-627 ger DE-627 rakwb eng 004 VZ Jin, Zhihao verfasserin aut Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. Thyroid nodule Segmentation Boundary Li, Xuechen aut Zhang, Yudi aut Shen, LinLin (orcid)0000-0003-1420-0815 aut Lai, Zhihui aut Kong, Heng aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 24 vom: 22. Aug., Seite 22357-22366 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:24 day:22 month:08 pages:22357-22366 https://doi.org/10.1007/s00521-022-07719-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 24 22 08 22357-22366 |
spelling |
10.1007/s00521-022-07719-y doi (DE-627)OLC207992592X (DE-He213)s00521-022-07719-y-p DE-627 ger DE-627 rakwb eng 004 VZ Jin, Zhihao verfasserin aut Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. Thyroid nodule Segmentation Boundary Li, Xuechen aut Zhang, Yudi aut Shen, LinLin (orcid)0000-0003-1420-0815 aut Lai, Zhihui aut Kong, Heng aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 24 vom: 22. Aug., Seite 22357-22366 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:24 day:22 month:08 pages:22357-22366 https://doi.org/10.1007/s00521-022-07719-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 24 22 08 22357-22366 |
allfields_unstemmed |
10.1007/s00521-022-07719-y doi (DE-627)OLC207992592X (DE-He213)s00521-022-07719-y-p DE-627 ger DE-627 rakwb eng 004 VZ Jin, Zhihao verfasserin aut Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. Thyroid nodule Segmentation Boundary Li, Xuechen aut Zhang, Yudi aut Shen, LinLin (orcid)0000-0003-1420-0815 aut Lai, Zhihui aut Kong, Heng aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 24 vom: 22. Aug., Seite 22357-22366 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:24 day:22 month:08 pages:22357-22366 https://doi.org/10.1007/s00521-022-07719-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 24 22 08 22357-22366 |
allfieldsGer |
10.1007/s00521-022-07719-y doi (DE-627)OLC207992592X (DE-He213)s00521-022-07719-y-p DE-627 ger DE-627 rakwb eng 004 VZ Jin, Zhihao verfasserin aut Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. Thyroid nodule Segmentation Boundary Li, Xuechen aut Zhang, Yudi aut Shen, LinLin (orcid)0000-0003-1420-0815 aut Lai, Zhihui aut Kong, Heng aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 24 vom: 22. Aug., Seite 22357-22366 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:24 day:22 month:08 pages:22357-22366 https://doi.org/10.1007/s00521-022-07719-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 24 22 08 22357-22366 |
allfieldsSound |
10.1007/s00521-022-07719-y doi (DE-627)OLC207992592X (DE-He213)s00521-022-07719-y-p DE-627 ger DE-627 rakwb eng 004 VZ Jin, Zhihao verfasserin aut Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. Thyroid nodule Segmentation Boundary Li, Xuechen aut Zhang, Yudi aut Shen, LinLin (orcid)0000-0003-1420-0815 aut Lai, Zhihui aut Kong, Heng aut Enthalten in Neural computing & applications Springer London, 1993 34(2022), 24 vom: 22. Aug., Seite 22357-22366 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2022 number:24 day:22 month:08 pages:22357-22366 https://doi.org/10.1007/s00521-022-07719-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2022 24 22 08 22357-22366 |
language |
English |
source |
Enthalten in Neural computing & applications 34(2022), 24 vom: 22. Aug., Seite 22357-22366 volume:34 year:2022 number:24 day:22 month:08 pages:22357-22366 |
sourceStr |
Enthalten in Neural computing & applications 34(2022), 24 vom: 22. Aug., Seite 22357-22366 volume:34 year:2022 number:24 day:22 month:08 pages:22357-22366 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Thyroid nodule Segmentation Boundary |
dewey-raw |
004 |
isfreeaccess_bool |
false |
container_title |
Neural computing & applications |
authorswithroles_txt_mv |
Jin, Zhihao @@aut@@ Li, Xuechen @@aut@@ Zhang, Yudi @@aut@@ Shen, LinLin @@aut@@ Lai, Zhihui @@aut@@ Kong, Heng @@aut@@ |
publishDateDaySort_date |
2022-08-22T00:00:00Z |
hierarchy_top_id |
165669608 |
dewey-sort |
14 |
id |
OLC207992592X |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC207992592X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506084603.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230131s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-022-07719-y</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC207992592X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-022-07719-y-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jin, Zhihao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Thyroid nodule</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Segmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Boundary</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Xuechen</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Yudi</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shen, LinLin</subfield><subfield code="0">(orcid)0000-0003-1420-0815</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lai, Zhihui</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kong, Heng</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural computing & applications</subfield><subfield code="d">Springer London, 1993</subfield><subfield code="g">34(2022), 24 vom: 22. Aug., Seite 22357-22366</subfield><subfield code="w">(DE-627)165669608</subfield><subfield code="w">(DE-600)1136944-9</subfield><subfield code="w">(DE-576)032873050</subfield><subfield code="x">0941-0643</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:24</subfield><subfield code="g">day:22</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:22357-22366</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-022-07719-y</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2022</subfield><subfield code="e">24</subfield><subfield code="b">22</subfield><subfield code="c">08</subfield><subfield code="h">22357-22366</subfield></datafield></record></collection>
|
author |
Jin, Zhihao |
spellingShingle |
Jin, Zhihao ddc 004 misc Thyroid nodule misc Segmentation misc Boundary Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images |
authorStr |
Jin, Zhihao |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)165669608 |
format |
Article |
dewey-ones |
004 - Data processing & computer science |
delete_txt_mv |
keep |
author_role |
aut aut aut aut aut aut |
collection |
OLC |
remote_str |
false |
illustrated |
Not Illustrated |
issn |
0941-0643 |
topic_title |
004 VZ Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images Thyroid nodule Segmentation Boundary |
topic |
ddc 004 misc Thyroid nodule misc Segmentation misc Boundary |
topic_unstemmed |
ddc 004 misc Thyroid nodule misc Segmentation misc Boundary |
topic_browse |
ddc 004 misc Thyroid nodule misc Segmentation misc Boundary |
format_facet |
Aufsätze Gedruckte Aufsätze |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
nc |
hierarchy_parent_title |
Neural computing & applications |
hierarchy_parent_id |
165669608 |
dewey-tens |
000 - Computer science, knowledge & systems |
hierarchy_top_title |
Neural computing & applications |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 |
title |
Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images |
ctrlnum |
(DE-627)OLC207992592X (DE-He213)s00521-022-07719-y-p |
title_full |
Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images |
author_sort |
Jin, Zhihao |
journal |
Neural computing & applications |
journalStr |
Neural computing & applications |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
000 - Computer science, information & general works |
recordtype |
marc |
publishDateSort |
2022 |
contenttype_str_mv |
txt |
container_start_page |
22357 |
author_browse |
Jin, Zhihao Li, Xuechen Zhang, Yudi Shen, LinLin Lai, Zhihui Kong, Heng |
container_volume |
34 |
class |
004 VZ |
format_se |
Aufsätze |
author-letter |
Jin, Zhihao |
doi_str_mv |
10.1007/s00521-022-07719-y |
normlink |
(ORCID)0000-0003-1420-0815 |
normlink_prefix_str_mv |
(orcid)0000-0003-1420-0815 |
dewey-full |
004 |
title_sort |
boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images |
title_auth |
Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images |
abstract |
Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
abstractGer |
Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
abstract_unstemmed |
Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 |
container_issue |
24 |
title_short |
Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images |
url |
https://doi.org/10.1007/s00521-022-07719-y |
remote_bool |
false |
author2 |
Li, Xuechen Zhang, Yudi Shen, LinLin Lai, Zhihui Kong, Heng |
author2Str |
Li, Xuechen Zhang, Yudi Shen, LinLin Lai, Zhihui Kong, Heng |
ppnlink |
165669608 |
mediatype_str_mv |
n |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1007/s00521-022-07719-y |
up_date |
2024-07-04T02:26:31.474Z |
_version_ |
1803613625622986752 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC207992592X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506084603.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">230131s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-022-07719-y</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC207992592X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-022-07719-y-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Jin, Zhihao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Boundary regression-based reep neural network for thyroid nodule segmentation in ultrasound images</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Due to the noises captured in ultrasound device and image reconstruction process, the edges of thyroid nodule are usually not distinctive and it is very difficult for existing approaches to well segment them in ultrasound images. While deep neural networks like U-Net have been successfully applied in many medical image segmentation tasks, their segmentation performances on ultrasound images are still not satisfactory. To address this issue, we propose in this paper a boundary field regression branch to provide useful boundary information to help improve the segmentation performance of existing networks. Without requirement of additional labeling costs, our approach firstly generates boundary field heatmap from available segmentation masks, which are then used as a supervision to train the regression branch. As a general architecture, our branch can be integrated with all encoder-decoder like segmentation networks. A dataset consisting of 3169 images from 2004 patients is used for experiments. We integrate our branch with U-Net, Attention U-Net, U-Net++ and DeepLabv3+; consistent improvements of Dice metrics were observed. The memory and computation costs required by adding our branch are marginal as well.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Thyroid nodule</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Segmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Boundary</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Xuechen</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Yudi</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shen, LinLin</subfield><subfield code="0">(orcid)0000-0003-1420-0815</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lai, Zhihui</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kong, Heng</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural computing & applications</subfield><subfield code="d">Springer London, 1993</subfield><subfield code="g">34(2022), 24 vom: 22. Aug., Seite 22357-22366</subfield><subfield code="w">(DE-627)165669608</subfield><subfield code="w">(DE-600)1136944-9</subfield><subfield code="w">(DE-576)032873050</subfield><subfield code="x">0941-0643</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:24</subfield><subfield code="g">day:22</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:22357-22366</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-022-07719-y</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2022</subfield><subfield code="e">24</subfield><subfield code="b">22</subfield><subfield code="c">08</subfield><subfield code="h">22357-22366</subfield></datafield></record></collection>
|
score |
7.399581 |