A fully automatic deep learning-based method for segmenting regions of interest and predicting renal function in pediatric dynamic renal scintigraphy
Objective Accurate delineation of renal regions of interest (ROIs) is critical for the assessment of renal function in pediatric dynamic renal scintigraphy (DRS). The purpose of this study was to develop and evaluate a deep learning (DL) model that can fully automatically delineate renal ROIs and ca...
Gespeichert in:
| Veröffentlicht in: | Annals of nuclear medicine 2024-05, Vol.38 (5), p.382-390 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 390 |
|---|---|
| container_issue | 5 |
| container_start_page | 382 |
| container_title | Annals of nuclear medicine |
| container_volume | 38 |
| creator | Ji, Xueli Zhu, Guohui Gou, Jinyu Chen, Suyun Zhao, Wenyu Sun, Zhanquan Fu, Hongliang Wang, Hui |
| description | Objective
Accurate delineation of renal regions of interest (ROIs) is critical for the assessment of renal function in pediatric dynamic renal scintigraphy (DRS). The purpose of this study was to develop and evaluate a deep learning (DL) model that can fully automatically delineate renal ROIs and calculate renal function in pediatric
99m
Technetium-ethylenedicysteine (
99m
Tc-EC) DRS.
Methods
This study retrospectively analyzed 1,283 pediatric DRS data at a single center from January to December 2018. These patients were divided into training set (
n
= 1027), validation set (
n
= 128), and testing set (
n
= 128). A fully automatic segmentation of ROIs (FASR) model was developed and evaluated. The pixel values of the automatically segmented ROIs were calculated to predict renal blood perfusion rate (BPR) and differential renal function (DRF). Precision, recall rate, intersection over union (IOU), and Dice similarity coefficient (DSC) were used to evaluate the performance of FASR model. Intraclass correlation (ICC) and Pearson correlation analysis were used to compare the consistency of automatic and manual method in assessing the renal function parameters in the testing set.
Results
The FASR model achieved a precision of 0.88, recall rate of 0.94, IOU of 0.83, and DSC of 0.91. In the testing set, the r values of BPR and DRF calculated by the two methods were 0.94 (
P
|
| doi_str_mv | 10.1007/s12149-024-01907-7 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2928852735</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2928852735</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-eead4684f85adf58cc0884ffb310ea66fbdd82c0de9dcf9e3c31b4f4d6eea89e3</originalsourceid><addsrcrecordid>eNp9kc1u1TAQhS1ERW8LL8ACWWLTjcF_cZxlVUGpVIkNrC3HHqepEjvYyeI-CO-L21xAYsFqNDrfnDPSQegtox8Ype3HwjiTHaFcEso62pL2BTowrSRRUoiX6EA7JknLdHuOLkp5pJTrRvNX6Fxo0SrFuwP6eY3DNk1HbLc1zXYdHfYAC57A5jjGgfS2gMczrA_J45AyLjDMENeq4QzDmGLBKeAxrpChrNhGj5cMfnQnJNqpRsS6plgxvFTNrvkp6BjtXOfOFFc9xiHb5eH4Gp0FOxV4c5qX6PvnT99uvpD7r7d3N9f3xAmuVgJgvVRaBt1YHxrtHNV1C71gFKxSofdec0c9dN6FDoQTrJdBelUvdd0v0dXuu-T0Y6vvm3ksDqbJRkhbMbzjWje8FU1F3_-DPqYt18eLEVRoxRomaaX4TrmcSskQzJLH2eajYdQ8lWb20kwtzTyXZtp69O5kvfUz-D8nv1uqgNiBUqU4QP6b_R_bX2uIpt8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3038615140</pqid></control><display><type>article</type><title>A fully automatic deep learning-based method for segmenting regions of interest and predicting renal function in pediatric dynamic renal scintigraphy</title><source>MEDLINE</source><source>SpringerNature Journals</source><creator>Ji, Xueli ; Zhu, Guohui ; Gou, Jinyu ; Chen, Suyun ; Zhao, Wenyu ; Sun, Zhanquan ; Fu, Hongliang ; Wang, Hui</creator><creatorcontrib>Ji, Xueli ; Zhu, Guohui ; Gou, Jinyu ; Chen, Suyun ; Zhao, Wenyu ; Sun, Zhanquan ; Fu, Hongliang ; Wang, Hui</creatorcontrib><description>Objective
Accurate delineation of renal regions of interest (ROIs) is critical for the assessment of renal function in pediatric dynamic renal scintigraphy (DRS). The purpose of this study was to develop and evaluate a deep learning (DL) model that can fully automatically delineate renal ROIs and calculate renal function in pediatric
99m
Technetium-ethylenedicysteine (
99m
Tc-EC) DRS.
Methods
This study retrospectively analyzed 1,283 pediatric DRS data at a single center from January to December 2018. These patients were divided into training set (
n
= 1027), validation set (
n
= 128), and testing set (
n
= 128). A fully automatic segmentation of ROIs (FASR) model was developed and evaluated. The pixel values of the automatically segmented ROIs were calculated to predict renal blood perfusion rate (BPR) and differential renal function (DRF). Precision, recall rate, intersection over union (IOU), and Dice similarity coefficient (DSC) were used to evaluate the performance of FASR model. Intraclass correlation (ICC) and Pearson correlation analysis were used to compare the consistency of automatic and manual method in assessing the renal function parameters in the testing set.
Results
The FASR model achieved a precision of 0.88, recall rate of 0.94, IOU of 0.83, and DSC of 0.91. In the testing set, the r values of BPR and DRF calculated by the two methods were 0.94 (
P
< 0.01) and 0.97 (
P
< 0.01), and the ICCs (95% confidence interval CI) were 0.94 (0.90—0.96) and 0.94 (0.91—0.96).
Conclusion
We propose a reliable and stable DL model that can fully automatically segment ROIs and accurately predict renal function in pediatric
99m
Tc-EC DRS.</description><identifier>ISSN: 0914-7187</identifier><identifier>EISSN: 1864-6433</identifier><identifier>DOI: 10.1007/s12149-024-01907-7</identifier><identifier>PMID: 38376629</identifier><language>eng</language><publisher>Singapore: Springer Nature Singapore</publisher><subject>Child ; Correlation analysis ; Deep Learning ; Humans ; Imaging ; Kidney - diagnostic imaging ; Kidney Function Tests - methods ; Medicine ; Medicine & Public Health ; Nuclear Medicine ; Original Article ; Pediatrics ; Performance evaluation ; Radiology ; Radionuclide Imaging ; Recall ; Renal function ; Retrospective Studies ; Scintigraphy</subject><ispartof>Annals of nuclear medicine, 2024-05, Vol.38 (5), p.382-390</ispartof><rights>The Author(s) under exclusive licence to The Japanese Society of Nuclear Medicine 2024. Springer Nature or its licensor (e.g. a society or other partner) 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.</rights><rights>2024. The Author(s) under exclusive licence to The Japanese Society of Nuclear Medicine.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c326t-eead4684f85adf58cc0884ffb310ea66fbdd82c0de9dcf9e3c31b4f4d6eea89e3</cites><orcidid>0000-0001-5109-8691</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s12149-024-01907-7$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s12149-024-01907-7$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38376629$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Ji, Xueli</creatorcontrib><creatorcontrib>Zhu, Guohui</creatorcontrib><creatorcontrib>Gou, Jinyu</creatorcontrib><creatorcontrib>Chen, Suyun</creatorcontrib><creatorcontrib>Zhao, Wenyu</creatorcontrib><creatorcontrib>Sun, Zhanquan</creatorcontrib><creatorcontrib>Fu, Hongliang</creatorcontrib><creatorcontrib>Wang, Hui</creatorcontrib><title>A fully automatic deep learning-based method for segmenting regions of interest and predicting renal function in pediatric dynamic renal scintigraphy</title><title>Annals of nuclear medicine</title><addtitle>Ann Nucl Med</addtitle><addtitle>Ann Nucl Med</addtitle><description>Objective
Accurate delineation of renal regions of interest (ROIs) is critical for the assessment of renal function in pediatric dynamic renal scintigraphy (DRS). The purpose of this study was to develop and evaluate a deep learning (DL) model that can fully automatically delineate renal ROIs and calculate renal function in pediatric
99m
Technetium-ethylenedicysteine (
99m
Tc-EC) DRS.
Methods
This study retrospectively analyzed 1,283 pediatric DRS data at a single center from January to December 2018. These patients were divided into training set (
n
= 1027), validation set (
n
= 128), and testing set (
n
= 128). A fully automatic segmentation of ROIs (FASR) model was developed and evaluated. The pixel values of the automatically segmented ROIs were calculated to predict renal blood perfusion rate (BPR) and differential renal function (DRF). Precision, recall rate, intersection over union (IOU), and Dice similarity coefficient (DSC) were used to evaluate the performance of FASR model. Intraclass correlation (ICC) and Pearson correlation analysis were used to compare the consistency of automatic and manual method in assessing the renal function parameters in the testing set.
Results
The FASR model achieved a precision of 0.88, recall rate of 0.94, IOU of 0.83, and DSC of 0.91. In the testing set, the r values of BPR and DRF calculated by the two methods were 0.94 (
P
< 0.01) and 0.97 (
P
< 0.01), and the ICCs (95% confidence interval CI) were 0.94 (0.90—0.96) and 0.94 (0.91—0.96).
Conclusion
We propose a reliable and stable DL model that can fully automatically segment ROIs and accurately predict renal function in pediatric
99m
Tc-EC DRS.</description><subject>Child</subject><subject>Correlation analysis</subject><subject>Deep Learning</subject><subject>Humans</subject><subject>Imaging</subject><subject>Kidney - diagnostic imaging</subject><subject>Kidney Function Tests - methods</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Nuclear Medicine</subject><subject>Original Article</subject><subject>Pediatrics</subject><subject>Performance evaluation</subject><subject>Radiology</subject><subject>Radionuclide Imaging</subject><subject>Recall</subject><subject>Renal function</subject><subject>Retrospective Studies</subject><subject>Scintigraphy</subject><issn>0914-7187</issn><issn>1864-6433</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kc1u1TAQhS1ERW8LL8ACWWLTjcF_cZxlVUGpVIkNrC3HHqepEjvYyeI-CO-L21xAYsFqNDrfnDPSQegtox8Ype3HwjiTHaFcEso62pL2BTowrSRRUoiX6EA7JknLdHuOLkp5pJTrRvNX6Fxo0SrFuwP6eY3DNk1HbLc1zXYdHfYAC57A5jjGgfS2gMczrA_J45AyLjDMENeq4QzDmGLBKeAxrpChrNhGj5cMfnQnJNqpRsS6plgxvFTNrvkp6BjtXOfOFFc9xiHb5eH4Gp0FOxV4c5qX6PvnT99uvpD7r7d3N9f3xAmuVgJgvVRaBt1YHxrtHNV1C71gFKxSofdec0c9dN6FDoQTrJdBelUvdd0v0dXuu-T0Y6vvm3ksDqbJRkhbMbzjWje8FU1F3_-DPqYt18eLEVRoxRomaaX4TrmcSskQzJLH2eajYdQ8lWb20kwtzTyXZtp69O5kvfUz-D8nv1uqgNiBUqU4QP6b_R_bX2uIpt8</recordid><startdate>20240501</startdate><enddate>20240501</enddate><creator>Ji, Xueli</creator><creator>Zhu, Guohui</creator><creator>Gou, Jinyu</creator><creator>Chen, Suyun</creator><creator>Zhao, Wenyu</creator><creator>Sun, Zhanquan</creator><creator>Fu, Hongliang</creator><creator>Wang, Hui</creator><general>Springer Nature Singapore</general><general>Springer Nature B.V</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QP</scope><scope>7TK</scope><scope>K9.</scope><scope>NAPCQ</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-5109-8691</orcidid></search><sort><creationdate>20240501</creationdate><title>A fully automatic deep learning-based method for segmenting regions of interest and predicting renal function in pediatric dynamic renal scintigraphy</title><author>Ji, Xueli ; Zhu, Guohui ; Gou, Jinyu ; Chen, Suyun ; Zhao, Wenyu ; Sun, Zhanquan ; Fu, Hongliang ; Wang, Hui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-eead4684f85adf58cc0884ffb310ea66fbdd82c0de9dcf9e3c31b4f4d6eea89e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Child</topic><topic>Correlation analysis</topic><topic>Deep Learning</topic><topic>Humans</topic><topic>Imaging</topic><topic>Kidney - diagnostic imaging</topic><topic>Kidney Function Tests - methods</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Nuclear Medicine</topic><topic>Original Article</topic><topic>Pediatrics</topic><topic>Performance evaluation</topic><topic>Radiology</topic><topic>Radionuclide Imaging</topic><topic>Recall</topic><topic>Renal function</topic><topic>Retrospective Studies</topic><topic>Scintigraphy</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ji, Xueli</creatorcontrib><creatorcontrib>Zhu, Guohui</creatorcontrib><creatorcontrib>Gou, Jinyu</creatorcontrib><creatorcontrib>Chen, Suyun</creatorcontrib><creatorcontrib>Zhao, Wenyu</creatorcontrib><creatorcontrib>Sun, Zhanquan</creatorcontrib><creatorcontrib>Fu, Hongliang</creatorcontrib><creatorcontrib>Wang, Hui</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Premium</collection><collection>MEDLINE - Academic</collection><jtitle>Annals of nuclear medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ji, Xueli</au><au>Zhu, Guohui</au><au>Gou, Jinyu</au><au>Chen, Suyun</au><au>Zhao, Wenyu</au><au>Sun, Zhanquan</au><au>Fu, Hongliang</au><au>Wang, Hui</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A fully automatic deep learning-based method for segmenting regions of interest and predicting renal function in pediatric dynamic renal scintigraphy</atitle><jtitle>Annals of nuclear medicine</jtitle><stitle>Ann Nucl Med</stitle><addtitle>Ann Nucl Med</addtitle><date>2024-05-01</date><risdate>2024</risdate><volume>38</volume><issue>5</issue><spage>382</spage><epage>390</epage><pages>382-390</pages><issn>0914-7187</issn><eissn>1864-6433</eissn><abstract>Objective
Accurate delineation of renal regions of interest (ROIs) is critical for the assessment of renal function in pediatric dynamic renal scintigraphy (DRS). The purpose of this study was to develop and evaluate a deep learning (DL) model that can fully automatically delineate renal ROIs and calculate renal function in pediatric
99m
Technetium-ethylenedicysteine (
99m
Tc-EC) DRS.
Methods
This study retrospectively analyzed 1,283 pediatric DRS data at a single center from January to December 2018. These patients were divided into training set (
n
= 1027), validation set (
n
= 128), and testing set (
n
= 128). A fully automatic segmentation of ROIs (FASR) model was developed and evaluated. The pixel values of the automatically segmented ROIs were calculated to predict renal blood perfusion rate (BPR) and differential renal function (DRF). Precision, recall rate, intersection over union (IOU), and Dice similarity coefficient (DSC) were used to evaluate the performance of FASR model. Intraclass correlation (ICC) and Pearson correlation analysis were used to compare the consistency of automatic and manual method in assessing the renal function parameters in the testing set.
Results
The FASR model achieved a precision of 0.88, recall rate of 0.94, IOU of 0.83, and DSC of 0.91. In the testing set, the r values of BPR and DRF calculated by the two methods were 0.94 (
P
< 0.01) and 0.97 (
P
< 0.01), and the ICCs (95% confidence interval CI) were 0.94 (0.90—0.96) and 0.94 (0.91—0.96).
Conclusion
We propose a reliable and stable DL model that can fully automatically segment ROIs and accurately predict renal function in pediatric
99m
Tc-EC DRS.</abstract><cop>Singapore</cop><pub>Springer Nature Singapore</pub><pmid>38376629</pmid><doi>10.1007/s12149-024-01907-7</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0001-5109-8691</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0914-7187 |
| ispartof | Annals of nuclear medicine, 2024-05, Vol.38 (5), p.382-390 |
| issn | 0914-7187 1864-6433 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2928852735 |
| source | MEDLINE; SpringerNature Journals |
| subjects | Child Correlation analysis Deep Learning Humans Imaging Kidney - diagnostic imaging Kidney Function Tests - methods Medicine Medicine & Public Health Nuclear Medicine Original Article Pediatrics Performance evaluation Radiology Radionuclide Imaging Recall Renal function Retrospective Studies Scintigraphy |
| title | A fully automatic deep learning-based method for segmenting regions of interest and predicting renal function in pediatric dynamic renal scintigraphy |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T22%3A39%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20fully%20automatic%20deep%20learning-based%20method%20for%20segmenting%20regions%20of%20interest%20and%20predicting%20renal%20function%20in%20pediatric%20dynamic%20renal%20scintigraphy&rft.jtitle=Annals%20of%20nuclear%20medicine&rft.au=Ji,%20Xueli&rft.date=2024-05-01&rft.volume=38&rft.issue=5&rft.spage=382&rft.epage=390&rft.pages=382-390&rft.issn=0914-7187&rft.eissn=1864-6433&rft_id=info:doi/10.1007/s12149-024-01907-7&rft_dat=%3Cproquest_cross%3E2928852735%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3038615140&rft_id=info:pmid/38376629&rfr_iscdi=true |