DAC-Net: A light-weight U-shaped network based efficient convolution and attention for thyroid nodule segmentation

Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Soph...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Computers in biology and medicine Ročník 180; s. 108972
Hlavní autori:	Yang, Yingwei, Huang, Haiguang, Shao, Yingsheng, Chen, Beilei
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States Elsevier Ltd 01.09.2024 Elsevier Limited
Predmet:	Algorithms Attention mechanism Clinical medicine Complexity Computation Convolution Deep learning Design parameters Feature extraction Feature maps Humans Image Interpretation, Computer-Assisted - methods Information processing Internal Medicine Light-weight model Modules Neural Networks, Computer Nodules Other Segmentation Source code Thyroid Thyroid gland Thyroid Nodule - diagnostic imaging Thyroid nodule segmentation U-shaped network Weight reduction Light-weight model Deep learning Attention mechanism Convolution Thyroid nodule segmentation U-shaped network
ISSN:	0010-4825, 1879-0534, 1879-0534
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Sophisticated models have difficulties in being implemented in clinical medicine platforms because of limited resources. DAC-Net is a Lightweight U-shaped network created to achieve high performance in segmenting thyroid nodules. Our method consists of three main components: DWSE, which combines depthwise convolution and squeeze-excitation block to enhance feature extraction and connections between samples; ADA, which includes Split Atrous and Dual Attention to extract global and local feature information from various viewpoints; and CSSC, which involves channel- scale and spatial-scale connections. This module enables the fusing of multi-stage features at global and local levels, producing feature maps at different channel and geographical scales, delivering a streamlined integration of multi-scale information. Combining these three components in our U- shaped design allows us to achieve competitive performance while also decreasing the number of parameters and computing complexity. Several experiments were conducted on the DDTI and TN3K datasets. The experimental results demonstrate that our model outperforms state-of-the-art thyroid nodule segmentation architectures in terms of segmentation performance. Our model not only reduces the number of parameters and computing expenses by 73x and 56x, respectively, but also exceeds TransUNet in segmentation performance. The source code is accessible at https://github.com/Phil-y/DAC-Net. •The paper provides open-source project code and utilizes public datasets, engaging hospitals, which notably enhance the credibility of the experimental results.•The experimental design not only focuses on performance optimization, but also successfully reduces the number of model parameters and computational complexity, contributing to the model’s practical application significance.•The experimental protocol demonstrates a comprehensive approach, including comparative experiments, qualitative analyses, ROC curve comparisons, ablation experiments, and analyses of hyperparameters. Various metrics were used, ensuring the experiments’ thoroughness and reliability.•The article is well structured and the diagrams are beautifully drawn.
AbstractList	AbstractRecently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Sophisticated models have difficulties in being implemented in clinical medicine platforms because of limited resources. DAC-Net is a Lightweight U-shaped network created to achieve high performance in segmenting thyroid nodules. Our method consists of three main components: DWSE, which combines depthwise convolution and squeeze-excitation block to enhance feature extraction and connections between samples; ADA, which includes Split Atrous and Dual Attention to extract global and local feature information from various viewpoints; and CSSC, which involves channel- scale and spatial-scale connections. This module enables the fusing of multi-stage features at global and local levels, producing feature maps at different channel and geographical scales, delivering a streamlined integration of multi-scale information. Combining these three components in our U- shaped design allows us to achieve competitive performance while also decreasing the number of parameters and computing complexity. Several experiments were conducted on the DDTI and TN3K datasets. The experimental results demonstrate that our model outperforms state-of-the-art thyroid nodule segmentation architectures in terms of segmentation performance. Our model not only reduces the number of parameters and computing expenses by 73x and 56x, respectively, but also exceeds TransUNet in segmentation performance. The source code is accessible at https://github.com/Phil-y/DAC-Net. Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Sophisticated models have difficulties in being implemented in clinical medicine platforms because of limited resources. DAC-Net is a Lightweight U-shaped network created to achieve high performance in segmenting thyroid nodules. Our method consists of three main components: DWSE, which combines depthwise convolution and squeeze-excitation block to enhance feature extraction and connections between samples; ADA, which includes Split Atrous and Dual Attention to extract global and local feature information from various viewpoints; and CSSC, which involves channel- scale and spatial-scale connections. This module enables the fusing of multi-stage features at global and local levels, producing feature maps at different channel and geographical scales, delivering a streamlined integration of multi-scale information. Combining these three components in our U- shaped design allows us to achieve competitive performance while also decreasing the number of parameters and computing complexity. Several experiments were conducted on the DDTI and TN3K datasets. The experimental results demonstrate that our model outperforms state-of-the-art thyroid nodule segmentation architectures in terms of segmentation performance. Our model not only reduces the number of parameters and computing expenses by 73x and 56x, respectively, but also exceeds TransUNet in segmentation performance. The source code is accessible at https://github.com/Phil-y/DAC-Net. Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Sophisticated models have difficulties in being implemented in clinical medicine platforms because of limited resources. DAC-Net is a Lightweight U-shaped network created to achieve high performance in segmenting thyroid nodules. Our method consists of three main components: DWSE, which combines depthwise convolution and squeeze-excitation block to enhance feature extraction and connections between samples; ADA, which includes Split Atrous and Dual Attention to extract global and local feature information from various viewpoints; and CSSC, which involves channel- scale and spatial-scale connections. This module enables the fusing of multi-stage features at global and local levels, producing feature maps at different channel and geographical scales, delivering a streamlined integration of multi-scale information. Combining these three components in our U- shaped design allows us to achieve competitive performance while also decreasing the number of parameters and computing complexity. Several experiments were conducted on the DDTI and TN3K datasets. The experimental results demonstrate that our model outperforms state-of-the-art thyroid nodule segmentation architectures in terms of segmentation performance. Our model not only reduces the number of parameters and computing expenses by 73x and 56x, respectively, but also exceeds TransUNet in segmentation performance. The source code is accessible at https://github.com/Phil-y/DAC-Net. •The paper provides open-source project code and utilizes public datasets, engaging hospitals, which notably enhance the credibility of the experimental results.•The experimental design not only focuses on performance optimization, but also successfully reduces the number of model parameters and computational complexity, contributing to the model’s practical application significance.•The experimental protocol demonstrates a comprehensive approach, including comparative experiments, qualitative analyses, ROC curve comparisons, ablation experiments, and analyses of hyperparameters. Various metrics were used, ensuring the experiments’ thoroughness and reliability.•The article is well structured and the diagrams are beautifully drawn. Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Sophisticated models have difficulties in being implemented in clinical medicine platforms because of limited resources. DAC-Net is a Lightweight U-shaped network created to achieve high performance in segmenting thyroid nodules. Our method consists of three main components: DWSE, which combines depthwise convolution and squeeze-excitation block to enhance feature extraction and connections between samples; ADA, which includes Split Atrous and Dual Attention to extract global and local feature information from various viewpoints; and CSSC, which involves channel- scale and spatial-scale connections. This module enables the fusing of multi-stage features at global and local levels, producing feature maps at different channel and geographical scales, delivering a streamlined integration of multi-scale information. Combining these three components in our U- shaped design allows us to achieve competitive performance while also decreasing the number of parameters and computing complexity. Several experiments were conducted on the DDTI and TN3K datasets. The experimental results demonstrate that our model outperforms state-of-the-art thyroid nodule segmentation architectures in terms of segmentation performance. Our model not only reduces the number of parameters and computing expenses by 73x and 56x, respectively, but also exceeds TransUNet in segmentation performance. The source code is accessible at https://github.com/Phil-y/DAC-Net.Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of increasingly complex modules, such as the Transformer, leading to models with a higher number of parameters and computing requirements. Sophisticated models have difficulties in being implemented in clinical medicine platforms because of limited resources. DAC-Net is a Lightweight U-shaped network created to achieve high performance in segmenting thyroid nodules. Our method consists of three main components: DWSE, which combines depthwise convolution and squeeze-excitation block to enhance feature extraction and connections between samples; ADA, which includes Split Atrous and Dual Attention to extract global and local feature information from various viewpoints; and CSSC, which involves channel- scale and spatial-scale connections. This module enables the fusing of multi-stage features at global and local levels, producing feature maps at different channel and geographical scales, delivering a streamlined integration of multi-scale information. Combining these three components in our U- shaped design allows us to achieve competitive performance while also decreasing the number of parameters and computing complexity. Several experiments were conducted on the DDTI and TN3K datasets. The experimental results demonstrate that our model outperforms state-of-the-art thyroid nodule segmentation architectures in terms of segmentation performance. Our model not only reduces the number of parameters and computing expenses by 73x and 56x, respectively, but also exceeds TransUNet in segmentation performance. The source code is accessible at https://github.com/Phil-y/DAC-Net.
ArticleNumber	108972
Author	Yang, Yingwei Huang, Haiguang Shao, Yingsheng Chen, Beilei
Author_xml	– sequence: 1 givenname: Yingwei orcidid: 0009-0003-7163-9143 surname: Yang fullname: Yang, Yingwei organization: College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325000, China – sequence: 2 givenname: Haiguang orcidid: 0000-0002-8843-6145 surname: Huang fullname: Huang, Haiguang email: haiguang2000@wzu.edu.cn organization: College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325000, China – sequence: 3 givenname: Yingsheng surname: Shao fullname: Shao, Yingsheng organization: College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325000, China – sequence: 4 givenname: Beilei surname: Chen fullname: Chen, Beilei organization: Department of Ultrasonic Imaging, Wenzhou Central Hospital, Wenzhou 325000, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/39126790$$D View this record in MEDLINE/PubMed
BookMark	eNqNUsFuEzEQtVARTQu_gCxx4bKp7V3v2hwqQqCAVMEBera89mzjdLNObW-r_D1epQUpElJOY8-8eZ55z2foZPADIIQpmVNC64v13PjNtnV-A3bOCKtyWsiGvUAzKhpZEF5WJ2hGCCVFJRg_RWcxrgkhFSnJK3RaSsrqRpIZCp8Xy-IHpA94gXt3u0rFI0wB3xRxpbdg8QDp0Yc73OqYb9B1zjgYEjZ-ePD9mJwfsB4s1inl9HTrfMBptQve5W5vxx5whNtNruqp_hq97HQf4c1TPEc3V19-L78V1z-_fl8urgtTMZmKlulGMNo2XMoaNEjbaJ6XbwwFoVtrmaktrwUvuWhboB2XdQcGKssst5qV5-j9nncb_P0IMamNiwb6Xg_gx6hKklUQghKZoe8OoGs_hiFPN6HqmjdUiox6-4Qa2yy82ga30WGnntXMgMs9wAQfY4BOGbffOQXtekWJmuxTa_XPPjXZp_b2ZQJxQPD8xhGtn_atkCV9cBBUnHwyYF0Ak5T17hiSywMS07vBGd3fwQ7iX1GoikwR9Wv6YNP_YlU-8KbOBB__T3DcDH8AjIfmdw
CitedBy_id	crossref_primary_10_1016_j_iot_2025_101598 crossref_primary_10_1109_LSP_2025_3541989
Cites_doi	10.1016/j.cmpb.2020.105329 10.1016/S2213-8587(22)00101-2 10.1016/j.cmpb.2017.06.005 10.1109/CVPR.2019.00326 10.1016/j.neunet.2019.08.025 10.1016/j.compbiomed.2022.106389 10.1109/ACCESS.2022.3211501 10.1609/aaai.v36i3.20144 10.1016/j.compbiomed.2023.106659 10.1016/j.knosys.2019.04.025 10.1016/j.cmpb.2021.106268 10.1016/j.compbiomed.2022.105618 10.1109/ICCV48922.2021.00986 10.1109/TIFS.2023.3285045 10.1016/j.compbiomed.2020.103776 10.3390/diagnostics11081374 10.1109/TCSVT.2022.3157828 10.1007/s00371-022-02705-w 10.1007/s11042-021-11835-7 10.1016/j.compbiomed.2020.103871 10.1109/CVPR.2015.7298965 10.1109/ACCESS.2019.2953934 10.1016/j.compbiomed.2022.106172 10.1109/CVPR.2018.00745 10.1109/ICCVW.2019.00052
ContentType	Journal Article
Copyright	2024 Elsevier Ltd Elsevier Ltd Copyright © 2024 Elsevier Ltd. All rights reserved. 2024. Elsevier Ltd
Copyright_xml	– notice: 2024 Elsevier Ltd – notice: Elsevier Ltd – notice: Copyright © 2024 Elsevier Ltd. All rights reserved. – notice: 2024. Elsevier Ltd
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 8FD FR3 JQ2 K9. M7Z NAPCQ P64 7X8
DOI	10.1016/j.compbiomed.2024.108972
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Technology Research Database Engineering Research Database ProQuest Computer Science Collection ProQuest Health & Medical Complete (Alumni) Biochemistry Abstracts 1 Nursing & Allied Health Premium Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Nursing & Allied Health Premium Technology Research Database ProQuest Computer Science Collection Biochemistry Abstracts 1 ProQuest Health & Medical Complete (Alumni) Engineering Research Database Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitleList	MEDLINE Nursing & Allied Health Premium MEDLINE - Academic
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: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine
EISSN	1879-0534
EndPage	108972
ExternalDocumentID	39126790 10_1016_j_compbiomed_2024_108972 S0010482524010576 1_s2_0_S0010482524010576
Genre	Journal Article
GroupedDBID	--- --K --M --Z -~X .1- .55 .DC .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29F 4.4 457 4G. 53G 5GY 5VS 7-5 71M 77I 7RV 7X7 88E 8AO 8FE 8FG 8FH 8FI 8FJ 8G5 8P~ 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABMZM ABOCM ABUWG ABWVN ABXDB ACDAQ ACGFS ACIEU ACIUM ACIWK ACLOT ACNNM ACPRK ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO AEBSH AEIPS AEKER AENEX AEUPX AEVXI AFJKZ AFKRA AFPUW AFRAH AFRHN AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AHMBA AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX AOUOD APXCP ARAPS ASPBG AVWKF AXJTR AZFZN AZQEC BBNVY BENPR BGLVJ BHPHI BKEYQ BKOJK BLXMC BNPGV BPHCQ BVXVI CCPQU CS3 DU5 DWQXO EBS EFJIC EFKBS EFLBG EJD EMOBN EO8 EO9 EP2 EP3 EX3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN FYUFA G-2 G-Q GBLVA GBOLZ GNUQQ GUQSH HCIFZ HLZ HMCUK HMK HMO HVGLF HZ~ IHE J1W K6V K7- KOM LK8 LX9 M1P M29 M2O M41 M7P MO0 N9A NAPCQ O-L O9- OAUVE OZT P-8 P-9 P2P P62 PC. PHGZM PHGZT PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO Q38 R2- ROL RPZ RXW SAE SBC SCC SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSV SSZ SV3 T5K TAE UAP UKHRP WOW WUQ X7M XPP Z5R ZGI ~G- ~HD 3V. AACTN AFCTW AFKWA AJOXV ALIPV AMFUW M0N RIG 9DU AAYXX AFFHD CITATION AGCQF AGRNS CGR CUY CVF ECM EIF NPM 8FD FR3 JQ2 K9. M7Z P64 7X8
ID	FETCH-LOGICAL-c429t-b2a7821b75996eae9d7a50167c1e8abdd2c6d5685358bbe1f596fece4d2d5da23
ISSN	0010-4825 1879-0534
IngestDate	Thu Oct 02 07:17:33 EDT 2025 Tue Oct 07 06:38:18 EDT 2025 Fri Jun 27 02:10:36 EDT 2025 Tue Nov 18 21:08:17 EST 2025 Sat Nov 29 05:31:49 EST 2025 Sat Sep 28 16:19:42 EDT 2024 Tue Feb 25 20:01:49 EST 2025 Tue Oct 14 19:37:59 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Keywords	Light-weight model Deep learning Attention mechanism Convolution Thyroid nodule segmentation U-shaped network
Language	English
License	Copyright © 2024 Elsevier Ltd. All rights reserved.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c429t-b2a7821b75996eae9d7a50167c1e8abdd2c6d5685358bbe1f596fece4d2d5da23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0009-0003-7163-9143 0000-0002-8843-6145
PMID	39126790
PQID	3096657198
PQPubID	1226355
PageCount	1
ParticipantIDs	proquest_miscellaneous_3091288109 proquest_journals_3096657198 pubmed_primary_39126790 crossref_citationtrail_10_1016_j_compbiomed_2024_108972 crossref_primary_10_1016_j_compbiomed_2024_108972 elsevier_sciencedirect_doi_10_1016_j_compbiomed_2024_108972 elsevier_clinicalkeyesjournals_1_s2_0_S0010482524010576 elsevier_clinicalkey_doi_10_1016_j_compbiomed_2024_108972
PublicationCentury	2000
PublicationDate	2024-09-01
PublicationDateYYYYMMDD	2024-09-01
PublicationDate_xml	– month: 09 year: 2024 text: 2024-09-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: Oxford
PublicationTitle	Computers in biology and medicine
PublicationTitleAlternate	Comput Biol Med
PublicationYear	2024
Publisher	Elsevier Ltd Elsevier Limited
Publisher_xml	– name: Elsevier Ltd – name: Elsevier Limited
References	Jonathan Long, Evan Shelhamer, Trevor Darrell, Fully convolutional networks for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3431–3440. Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Zhai, Unterthiner, Dehghani, Minderer, Heigold, Gelly (b10) 2020 Azad, Al-Antary, Heidari, Merhof (b38) 2022; 10 Sun, Pan, Kong, Xu, Ma, Racharak, Nguyen (b50) 2023 Wang, Min, Shi, Jin, Nawrin, Yu, Nagatomi (b32) 2022 Gong, Chen, Chen, Li, Li, Chen (b20) 2023; 155 Bikas, Burman (b1) 2019 Alexander, Cibas (b2) 2022; 10 Chen, Feng, Zheng, Zhou, Liu, Liu, Chen (b26) 2023; 155 Ma, Tan, Luo, Liao, Li, Li (b18) 2022; 32 Zhou, Rahman Siddiquee, Tajbakhsh, Liang (b39) 2018 Fresilli, David, Pacini, Del Gaudio, Dolcetti, Lucarelli, Di Leo, Bellini, D’Andrea, Sorrenti (b4) 2021; 11 Ruan, Xie, Gao, Liu, Fu (b44) 2023 Jin, Zhao (b25) 2023 Haonan Wang, Peng Cao, Jiaqi Wang, Osmar R. Zaiane, Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, 2022, pp. 2441–2449. Jin, Meng, Pham, Chen, Wei, Su (b30) 2019; 178 Chen, You, Li (b8) 2020; 185 Su, Zhao, Elmannai, Heidari, Bourouis, Wu, Cai, Gui, Chen (b23) 2022; 146 Kan, Shi, Zhao, Wang, Han, An, Wang, Wang (b36) 2022 Wang, Lv, Wang, Shi (b31) 2021; 208 Cao, Wang, Chen, Jiang, Zhang, Tian, Wang (b12) 2022 Zhang, Liu, Hu (b33) 2021 Chen, Lu, Yu, Luo, Adeli, Wang, Lu, Yuille, Zhou (b11) 2021 Valanarasu, Patel (b49) 2022 Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10012–10022. Ronneberger, Fischer, Brox (b7) 2015 Song, Meng, Rodriguez-Paton, Li, Zheng, Wang (b42) 2019; 7 Azad, Aghdam, Rauland, Jia, Avval, Bozorgpour, Karimijafarbigloo, Cohen, Adeli, Merhof (b5) 2022 Gulame, Dixit, Suresh (b3) 2021; 45 Ibtehaz, Kihara (b48) 2023 Zhang, Higashita, Fu, Xu, Zhang, Liu, Zhang, Liu (b34) 2021 Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, Hanqing Lu, Dual attention network for scene segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3146–3154. Koundal, Sharma, Guo (b19) 2020; 121 Huang, Lin, Tong, Hu, Zhang, Iwamoto, Han, Chen, Wu (b40) 2020 Abdolali, Kapur, Jaremko, Noga, Hareendranathan, Punithakumar (b15) 2020; 122 Huang, Yang, Hu, Yang, Qi, Zhang, Zheng (b24) 2023 Shi, Li, Xu, Fan (b29) 2022; 81 Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b9) 2017; 30 Deng, Han, Wei, Chang (b16) 2022; 150 Qiao, Liu, Shi, Zhao, Kan, Wang, An, Xiao, Wang (b37) 2022 Gong, Chen, Wang, Xie, Mao, Yu, Chen, Li (b17) 2021 Ibtehaz, Rahman (b41) 2020; 121 Ruan, Xie, Xiang, Liu, Fu (b51) 2022 Huang, Deng, Li, Yuan (b47) 2021 Jianyuan Guo, Kai Han, Han Wu, Chang Xu, Yehui Tang, Chunjing Xu, Yunhe Wang, Cmt: Convolutional neural networks meet vision transformers. 2022 IEEE, in: CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 12165–12175. Poudel, Illanes, Arens, Hansen, Friebe (b21) 2017; Vol. 10138 Xia, Chen, Li, Zhou, Chen, Cai, Fang, Zhou (b14) 2017; 147 Qian, Huang, Xia, Li, Zhou (b27) 2023; 39 Reza Azad, Maryam Asadi-Aghbolaghi, Mahmood Fathy, Sergio Escalera, Bi-directional ConvLSTM U-Net with densley connected convolutions, in: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019. Ying, Yu, Yu, Li, Yu, Zhao, Liu (b22) 2018 Jie Hu, Li Shen, Gang Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141. Ronneberger (10.1016/j.compbiomed.2024.108972_b7) 2015 10.1016/j.compbiomed.2024.108972_b28 Huang (10.1016/j.compbiomed.2024.108972_b24) 2023 Zhang (10.1016/j.compbiomed.2024.108972_b33) 2021 Abdolali (10.1016/j.compbiomed.2024.108972_b15) 2020; 122 Dosovitskiy (10.1016/j.compbiomed.2024.108972_b10) 2020 Koundal (10.1016/j.compbiomed.2024.108972_b19) 2020; 121 Huang (10.1016/j.compbiomed.2024.108972_b47) 2021 Sun (10.1016/j.compbiomed.2024.108972_b50) 2023 10.1016/j.compbiomed.2024.108972_b35 Chen (10.1016/j.compbiomed.2024.108972_b11) 2021 Shi (10.1016/j.compbiomed.2024.108972_b29) 2022; 81 Deng (10.1016/j.compbiomed.2024.108972_b16) 2022; 150 Ying (10.1016/j.compbiomed.2024.108972_b22) 2018 Jin (10.1016/j.compbiomed.2024.108972_b30) 2019; 178 Ibtehaz (10.1016/j.compbiomed.2024.108972_b41) 2020; 121 Kan (10.1016/j.compbiomed.2024.108972_b36) 2022 Ma (10.1016/j.compbiomed.2024.108972_b18) 2022; 32 Valanarasu (10.1016/j.compbiomed.2024.108972_b49) 2022 Huang (10.1016/j.compbiomed.2024.108972_b40) 2020 Zhang (10.1016/j.compbiomed.2024.108972_b34) 2021 Ibtehaz (10.1016/j.compbiomed.2024.108972_b48) 2023 Qian (10.1016/j.compbiomed.2024.108972_b27) 2023; 39 Alexander (10.1016/j.compbiomed.2024.108972_b2) 2022; 10 Azad (10.1016/j.compbiomed.2024.108972_b5) 2022 Xia (10.1016/j.compbiomed.2024.108972_b14) 2017; 147 Azad (10.1016/j.compbiomed.2024.108972_b38) 2022; 10 Jin (10.1016/j.compbiomed.2024.108972_b25) 2023 Gong (10.1016/j.compbiomed.2024.108972_b17) 2021 Su (10.1016/j.compbiomed.2024.108972_b23) 2022; 146 10.1016/j.compbiomed.2024.108972_b43 10.1016/j.compbiomed.2024.108972_b46 10.1016/j.compbiomed.2024.108972_b45 Ruan (10.1016/j.compbiomed.2024.108972_b51) 2022 Gulame (10.1016/j.compbiomed.2024.108972_b3) 2021; 45 Gong (10.1016/j.compbiomed.2024.108972_b20) 2023; 155 Ruan (10.1016/j.compbiomed.2024.108972_b44) 2023 10.1016/j.compbiomed.2024.108972_b6 Cao (10.1016/j.compbiomed.2024.108972_b12) 2022 Poudel (10.1016/j.compbiomed.2024.108972_b21) 2017; Vol. 10138 Qiao (10.1016/j.compbiomed.2024.108972_b37) 2022 10.1016/j.compbiomed.2024.108972_b13 Bikas (10.1016/j.compbiomed.2024.108972_b1) 2019 Wang (10.1016/j.compbiomed.2024.108972_b32) 2022 Song (10.1016/j.compbiomed.2024.108972_b42) 2019; 7 Chen (10.1016/j.compbiomed.2024.108972_b26) 2023; 155 Vaswani (10.1016/j.compbiomed.2024.108972_b9) 2017; 30 Wang (10.1016/j.compbiomed.2024.108972_b31) 2021; 208 Zhou (10.1016/j.compbiomed.2024.108972_b39) 2018 Chen (10.1016/j.compbiomed.2024.108972_b8) 2020; 185 Fresilli (10.1016/j.compbiomed.2024.108972_b4) 2021; 11
References_xml	– volume: 147 start-page: 37 year: 2017 end-page: 49 ident: b14 article-title: Ultrasound-based differentiation of malignant and benign thyroid Nodules: An extreme learning machine approach publication-title: Comput. Methods Programs Biomed. – volume: 39 start-page: 5953 year: 2023 end-page: 5969 ident: b27 article-title: Automatic segmentation method using FCN with multi-scale dilated convolution for medical ultrasound image publication-title: Vis. Comput. – volume: 11 start-page: 1374 year: 2021 ident: b4 article-title: Thyroid nodule characterization: How to assess the malignancy risk. update of the literature publication-title: Diagnostics – start-page: 4749 year: 2022 end-page: 4753 ident: b37 article-title: FcTC-UNet: Fine-grained combination of transformer and CNN for thoracic organs segmentation publication-title: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society – start-page: 541 year: 2019 end-page: 547 ident: b1 article-title: Epidemiology of thyroid cancer publication-title: Thyroid Dis.: Compr. Guide Clin. – year: 2023 ident: b24 article-title: DNA synthetic steganography based on conditional probability adaptive coding publication-title: IEEE Trans. Inf. Forensics Secur. – volume: 7 start-page: 166823 year: 2019 end-page: 166832 ident: b42 article-title: U-Next: A novel convolution neural network with an aggregation U-Net architecture for gallstone segmentation in CT images publication-title: IEEE Access – volume: 32 start-page: 6113 year: 2022 end-page: 6124 ident: b18 article-title: A novel deep learning framework for automatic recognition of thyroid gland and tissues of neck in ultrasound image publication-title: IEEE Trans. Circuits Syst. Video Technol. – year: 2020 ident: b10 article-title: An image is worth 16x16 words: Transformers for image recognition at scale – volume: 30 year: 2017 ident: b9 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – start-page: 257 year: 2021 end-page: 261 ident: b17 article-title: Multi-task learning for thyroid nodule segmentation with thyroid region prior publication-title: 2021 IEEE 18th International Symposium on Biomedical Imaging – start-page: 692 year: 2023 end-page: 702 ident: b48 article-title: ACC-UNet: A completely convolutional UNet model for the 2020s publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – reference: Reza Azad, Maryam Asadi-Aghbolaghi, Mahmood Fathy, Sergio Escalera, Bi-directional ConvLSTM U-Net with densley connected convolutions, in: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019. – start-page: 99 year: 2021 end-page: 108 ident: b34 article-title: A multi-branch hybrid transformer network for corneal endothelial cell segmentation publication-title: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24 – start-page: 23 year: 2022 end-page: 33 ident: b49 article-title: Unext: Mlp-based rapid medical image segmentation network publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – volume: 185 year: 2020 ident: b8 article-title: A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images publication-title: Comput. Methods Programs Biomed. – reference: Jonathan Long, Evan Shelhamer, Trevor Darrell, Fully convolutional networks for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3431–3440. – reference: Haonan Wang, Peng Cao, Jiaqi Wang, Osmar R. Zaiane, Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, 2022, pp. 2441–2449. – volume: 10 start-page: 108205 year: 2022 end-page: 108215 ident: b38 article-title: Transnorm: Transformer provides a strong spatial normalization mechanism for a deep segmentation model publication-title: IEEE Access – volume: 155 year: 2023 ident: b26 article-title: LDANet: Automatic lung parenchyma segmentation from CT images publication-title: Comput. Biol. Med. – volume: 178 start-page: 149 year: 2019 end-page: 162 ident: b30 article-title: DUNet: A deformable network for retinal vessel segmentation publication-title: Knowl.-Based Syst. – reference: Jie Hu, Li Shen, Gang Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141. – start-page: 14 year: 2021 end-page: 24 ident: b33 article-title: Transfuse: Fusing transformers and cnns for medical image segmentation publication-title: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24 – start-page: 2123 year: 2022 end-page: 2127 ident: b36 article-title: Itunet: Integration of transformers and unet for organs-at-risk segmentation publication-title: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society – reference: Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, Hanqing Lu, Dual attention network for scene segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 3146–3154. – start-page: 1 year: 2023 end-page: 12 ident: b25 article-title: Bert-based graph unlinked embedding for sentiment analysis publication-title: Complex Intell. Syst. – volume: 146 year: 2022 ident: b23 article-title: Multilevel threshold image segmentation for COVID-19 chest radiography: A framework using horizontal and vertical multiverse optimization publication-title: Comput. Biol. Med. – volume: 10 start-page: 533 year: 2022 end-page: 539 ident: b2 article-title: Diagnosis of thyroid nodules publication-title: Lancet Diabetes Endocrinol. – volume: 122 year: 2020 ident: b15 article-title: Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks publication-title: Comput. Biol. Med. – start-page: 373 year: 2018 end-page: 384 ident: b22 article-title: Thyroid nodule segmentation in ultrasound images based on cascaded convolutional neural network publication-title: Neural Information Processing: 25th International Conference, ICONIP 2018, Siem Reap, Cambodia, December 13–16, 2018, Proceedings, Part VI 25 – start-page: 481 year: 2023 end-page: 490 ident: b44 article-title: Ege-unet: an efficient group enhanced unet for skin lesion segmentation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 205 year: 2022 end-page: 218 ident: b12 article-title: Swin-unet: Unet-like pure transformer for medical image segmentation publication-title: European Conference on Computer Vision – volume: 150 year: 2022 ident: b16 article-title: Automatic classification of thyroid nodules in ultrasound images using a multi-task attention network guided by clinical knowledge publication-title: Comput. Biol. Med. – volume: 121 start-page: 74 year: 2020 end-page: 87 ident: b41 article-title: MultiResUNet: Rethinking the U-net architecture for multimodal biomedical image segmentation publication-title: Neural Netw. – year: 2021 ident: b47 article-title: Missformer: An effective medical image segmentation transformer – year: 2023 ident: b50 article-title: DA-TransUNet: Integrating spatial and channel dual attention with transformer U-Net for medical image segmentation – volume: 155 year: 2023 ident: b20 article-title: Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules publication-title: Comput. Biol. Med. – reference: Jianyuan Guo, Kai Han, Han Wu, Chang Xu, Yehui Tang, Chunjing Xu, Yunhe Wang, Cmt: Convolutional neural networks meet vision transformers. 2022 IEEE, in: CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 12165–12175. – start-page: 234 year: 2015 end-page: 241 ident: b7 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 – year: 2022 ident: b51 article-title: MEW-UNet: Multi-axis representation learning in frequency domain for medical image segmentation – year: 2022 ident: b5 article-title: Medical image segmentation review: The success of u-net – reference: Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10012–10022. – volume: 81 start-page: 6497 year: 2022 end-page: 6511 ident: b29 article-title: Fine-grained histopathological cell segmentation through residual attention with prior embedding publication-title: Multimedia Tools Appl. – volume: Vol. 10138 year: 2017 ident: b21 article-title: Active contours extension and similarity indicators for improved 3D segmentation of thyroid ultrasound images publication-title: Medical Imaging 2017: Imaging Informatics for Healthcare, Research, and Applications – start-page: 517 year: 2022 end-page: 526 ident: b32 article-title: SMESwin Unet: Merging CNN and transformer for medical image segmentation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 3 year: 2018 end-page: 11 ident: b39 article-title: Unet++: A nested u-net architecture for medical image segmentation publication-title: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4 – volume: 208 year: 2021 ident: b31 article-title: SAR-U-Net: Squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography publication-title: Comput. Methods Programs Biomed. – volume: 121 year: 2020 ident: b19 article-title: Intuitionistic based segmentation of thyroid nodules in ultrasound images publication-title: Comput. Biol. Med. – year: 2021 ident: b11 article-title: Transunet: Transformers make strong encoders for medical image segmentation – volume: 45 start-page: 2270 year: 2021 end-page: 2276 ident: b3 article-title: Thyroid nodules segmentation methods in clinical ultrasound images: A review publication-title: Mater. Today: Proc. – start-page: 1055 year: 2020 end-page: 1059 ident: b40 article-title: Unet 3+: A full-scale connected unet for medical image segmentation publication-title: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing – start-page: 14 year: 2021 ident: 10.1016/j.compbiomed.2024.108972_b33 article-title: Transfuse: Fusing transformers and cnns for medical image segmentation – ident: 10.1016/j.compbiomed.2024.108972_b28 – start-page: 692 year: 2023 ident: 10.1016/j.compbiomed.2024.108972_b48 article-title: ACC-UNet: A completely convolutional UNet model for the 2020s – year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b5 – volume: 30 year: 2017 ident: 10.1016/j.compbiomed.2024.108972_b9 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – year: 2021 ident: 10.1016/j.compbiomed.2024.108972_b47 – start-page: 541 year: 2019 ident: 10.1016/j.compbiomed.2024.108972_b1 article-title: Epidemiology of thyroid cancer publication-title: Thyroid Dis.: Compr. Guide Clin. – year: 2020 ident: 10.1016/j.compbiomed.2024.108972_b10 – volume: 185 year: 2020 ident: 10.1016/j.compbiomed.2024.108972_b8 article-title: A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2020.105329 – start-page: 4749 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b37 article-title: FcTC-UNet: Fine-grained combination of transformer and CNN for thoracic organs segmentation – volume: 10 start-page: 533 issue: 7 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b2 article-title: Diagnosis of thyroid nodules publication-title: Lancet Diabetes Endocrinol. doi: 10.1016/S2213-8587(22)00101-2 – start-page: 257 year: 2021 ident: 10.1016/j.compbiomed.2024.108972_b17 article-title: Multi-task learning for thyroid nodule segmentation with thyroid region prior – volume: 147 start-page: 37 year: 2017 ident: 10.1016/j.compbiomed.2024.108972_b14 article-title: Ultrasound-based differentiation of malignant and benign thyroid Nodules: An extreme learning machine approach publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2017.06.005 – start-page: 234 year: 2015 ident: 10.1016/j.compbiomed.2024.108972_b7 article-title: U-net: Convolutional networks for biomedical image segmentation – start-page: 481 year: 2023 ident: 10.1016/j.compbiomed.2024.108972_b44 article-title: Ege-unet: an efficient group enhanced unet for skin lesion segmentation – ident: 10.1016/j.compbiomed.2024.108972_b46 doi: 10.1109/CVPR.2019.00326 – year: 2023 ident: 10.1016/j.compbiomed.2024.108972_b50 – year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b51 – volume: 121 start-page: 74 year: 2020 ident: 10.1016/j.compbiomed.2024.108972_b41 article-title: MultiResUNet: Rethinking the U-net architecture for multimodal biomedical image segmentation publication-title: Neural Netw. doi: 10.1016/j.neunet.2019.08.025 – volume: 155 year: 2023 ident: 10.1016/j.compbiomed.2024.108972_b20 article-title: Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2022.106389 – volume: 10 start-page: 108205 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b38 article-title: Transnorm: Transformer provides a strong spatial normalization mechanism for a deep segmentation model publication-title: IEEE Access doi: 10.1109/ACCESS.2022.3211501 – volume: Vol. 10138 year: 2017 ident: 10.1016/j.compbiomed.2024.108972_b21 article-title: Active contours extension and similarity indicators for improved 3D segmentation of thyroid ultrasound images – volume: 45 start-page: 2270 year: 2021 ident: 10.1016/j.compbiomed.2024.108972_b3 article-title: Thyroid nodules segmentation methods in clinical ultrasound images: A review publication-title: Mater. Today: Proc. – start-page: 517 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b32 article-title: SMESwin Unet: Merging CNN and transformer for medical image segmentation – start-page: 1 year: 2023 ident: 10.1016/j.compbiomed.2024.108972_b25 article-title: Bert-based graph unlinked embedding for sentiment analysis publication-title: Complex Intell. Syst. – ident: 10.1016/j.compbiomed.2024.108972_b35 doi: 10.1609/aaai.v36i3.20144 – volume: 155 year: 2023 ident: 10.1016/j.compbiomed.2024.108972_b26 article-title: LDANet: Automatic lung parenchyma segmentation from CT images publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2023.106659 – volume: 178 start-page: 149 year: 2019 ident: 10.1016/j.compbiomed.2024.108972_b30 article-title: DUNet: A deformable network for retinal vessel segmentation publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2019.04.025 – volume: 208 year: 2021 ident: 10.1016/j.compbiomed.2024.108972_b31 article-title: SAR-U-Net: Squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2021.106268 – volume: 146 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b23 article-title: Multilevel threshold image segmentation for COVID-19 chest radiography: A framework using horizontal and vertical multiverse optimization publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2022.105618 – ident: 10.1016/j.compbiomed.2024.108972_b13 doi: 10.1109/ICCV48922.2021.00986 – year: 2023 ident: 10.1016/j.compbiomed.2024.108972_b24 article-title: DNA synthetic steganography based on conditional probability adaptive coding publication-title: IEEE Trans. Inf. Forensics Secur. doi: 10.1109/TIFS.2023.3285045 – volume: 121 year: 2020 ident: 10.1016/j.compbiomed.2024.108972_b19 article-title: Intuitionistic based segmentation of thyroid nodules in ultrasound images publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2020.103776 – volume: 11 start-page: 1374 issue: 8 year: 2021 ident: 10.1016/j.compbiomed.2024.108972_b4 article-title: Thyroid nodule characterization: How to assess the malignancy risk. update of the literature publication-title: Diagnostics doi: 10.3390/diagnostics11081374 – volume: 32 start-page: 6113 issue: 9 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b18 article-title: A novel deep learning framework for automatic recognition of thyroid gland and tissues of neck in ultrasound image publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2022.3157828 – start-page: 373 year: 2018 ident: 10.1016/j.compbiomed.2024.108972_b22 article-title: Thyroid nodule segmentation in ultrasound images based on cascaded convolutional neural network – volume: 39 start-page: 5953 issue: 11 year: 2023 ident: 10.1016/j.compbiomed.2024.108972_b27 article-title: Automatic segmentation method using FCN with multi-scale dilated convolution for medical ultrasound image publication-title: Vis. Comput. doi: 10.1007/s00371-022-02705-w – year: 2021 ident: 10.1016/j.compbiomed.2024.108972_b11 – start-page: 23 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b49 article-title: Unext: Mlp-based rapid medical image segmentation network – start-page: 3 year: 2018 ident: 10.1016/j.compbiomed.2024.108972_b39 article-title: Unet++: A nested u-net architecture for medical image segmentation – volume: 81 start-page: 6497 issue: 5 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b29 article-title: Fine-grained histopathological cell segmentation through residual attention with prior embedding publication-title: Multimedia Tools Appl. doi: 10.1007/s11042-021-11835-7 – volume: 122 year: 2020 ident: 10.1016/j.compbiomed.2024.108972_b15 article-title: Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2020.103871 – start-page: 2123 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b36 article-title: Itunet: Integration of transformers and unet for organs-at-risk segmentation – ident: 10.1016/j.compbiomed.2024.108972_b6 doi: 10.1109/CVPR.2015.7298965 – start-page: 205 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b12 article-title: Swin-unet: Unet-like pure transformer for medical image segmentation – start-page: 1055 year: 2020 ident: 10.1016/j.compbiomed.2024.108972_b40 article-title: Unet 3+: A full-scale connected unet for medical image segmentation – volume: 7 start-page: 166823 year: 2019 ident: 10.1016/j.compbiomed.2024.108972_b42 article-title: U-Next: A novel convolution neural network with an aggregation U-Net architecture for gallstone segmentation in CT images publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2953934 – volume: 150 year: 2022 ident: 10.1016/j.compbiomed.2024.108972_b16 article-title: Automatic classification of thyroid nodules in ultrasound images using a multi-task attention network guided by clinical knowledge publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2022.106172 – start-page: 99 year: 2021 ident: 10.1016/j.compbiomed.2024.108972_b34 article-title: A multi-branch hybrid transformer network for corneal endothelial cell segmentation – ident: 10.1016/j.compbiomed.2024.108972_b45 doi: 10.1109/CVPR.2018.00745 – ident: 10.1016/j.compbiomed.2024.108972_b43 doi: 10.1109/ICCVW.2019.00052
SSID	ssj0004030
Score	2.4011886
Snippet	Recently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the development of... AbstractRecently, there has been a focused effort to improve the efficiency of thyroid nodule segmentation algorithms. This endeavor has resulted in the...
SourceID	proquest pubmed crossref elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	108972
SubjectTerms	Algorithms Attention mechanism Clinical medicine Complexity Computation Convolution Deep learning Design parameters Feature extraction Feature maps Humans Image Interpretation, Computer-Assisted - methods Information processing Internal Medicine Light-weight model Modules Neural Networks, Computer Nodules Other Segmentation Source code Thyroid Thyroid gland Thyroid Nodule - diagnostic imaging Thyroid nodule segmentation U-shaped network Weight reduction
Title	DAC-Net: A light-weight U-shaped network based efficient convolution and attention for thyroid nodule segmentation
URI	https://www.clinicalkey.com/#!/content/1-s2.0-S0010482524010576 https://www.clinicalkey.es/playcontent/1-s2.0-S0010482524010576 https://dx.doi.org/10.1016/j.compbiomed.2024.108972 https://www.ncbi.nlm.nih.gov/pubmed/39126790 https://www.proquest.com/docview/3096657198 https://www.proquest.com/docview/3091288109
Volume	180
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: ScienceDirect Freedom Collection - Elsevier customDbUrl: eissn: 1879-0534 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004030 issn: 0010-4825 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6DiFeEHcKYzISb1VQ7OZiw1MpQwNBhcQmdU-WEztrp5JWTTvGH-B3cxw7F41OKkK8RFEcx5a_Lz7Hx-ccI_SKSZnJjBJvkMFKJwgD7YHWGngJIxlIa5Ype2rJ53g8ZpMJ_9rp_KpiYS7ncZ6zqyu-_K9QwzMA24TO_gXc9UfhAdwD6HAF2OG6E_DvhyNvrK3Frz8v84T8KO2f_VOvmMql2e-3vt99I8KUcemYlWGRpQu665tN4rpeO29I64z4c7WYQe2F2sx1v9Dn313gUt5WcatzIkpH23aOp-vb-GfOVH0G0hN62BDMPT-Ws3NzXxuBpnJRvV9MdVMwchEm7zRMcbO2HYMGtaOWM65VATaNN1M5YYOYCJiNjW4mbH_r5G_tEBcGu6VNXvDaNGTcKLk9H-haau1vZXYi-DqoNea842gP7dM45KyL9ocfjyafmghbf2CDmVx3nE-Y9RTc3t5Nis5NC5lSoTm5h-66lQgeWgbdRx2dP0C3vziQHqKVI9IbPMRtGuGKRtjRCJc0wjWNcItGGIDHNY0w0Ag7GmFLI9ym0SN0-uHoZHTsuRM6vBT0mLWXUAkaJklik-RHS81VLEMT2JISzWSiFE0jFUagEoYsSTTJQh5lOtWBoipUkg4eo26-yPVThE2EdEwTyokOYBGtWah0lugkpYqA3Il6KK6GU6Qufb05RWUuKj_FC9EAIQwQwgLRQ6SuubQpXHaowyvERBWiDEJVANV2qBtvq6sLN0kUgoiCCl_8Qb8eelvXdAqwVWx3bPegopaomxr43OytEs566GVdDCLE7AvKXC825TugpTLi8x56YilZD9QAiqKY-8_-YUCeozvND3-AuuvVRr9At9LL9axYHaK9eMIO3Q_3Gx1i_UY
linkProvider	Elsevier
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=DAC-Net%3A+A+light-weight+U-shaped+network+based+efficient+convolution+and+attention+for+thyroid+nodule+segmentation&rft.jtitle=Computers+in+biology+and+medicine&rft.au=Yang%2C+Yingwei&rft.au=Huang%2C+Haiguang&rft.au=Shao%2C+Yingsheng&rft.au=Chen%2C+Beilei&rft.date=2024-09-01&rft.pub=Elsevier+Ltd&rft.issn=0010-4825&rft.volume=180&rft_id=info:doi/10.1016%2Fj.compbiomed.2024.108972&rft.externalDocID=S0010482524010576
thumbnail_m	http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F00104825%2FS0010482524X00128%2Fcov150h.gif