Two-Stage Cascaded CNN Model for 3D Mitochondria EM Segmentation

Mitochondria are the organelles that generate energy for the cells. Many studies have suggested that mitochondrial dysfunction or impairment may be related to cancer and other neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases. Therefore, morphologically detailed alterations in...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Electronics (Basel) 2023-02, Vol.12 (4), p.928
Hauptverfasser: Guo, Jing-Ming, Seshathiri, Sankarasrinivasan, Liu, Jia-Hao, Hsu, Wei-Wen
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 4
container_start_page 928
container_title Electronics (Basel)
container_volume 12
creator Guo, Jing-Ming
Seshathiri, Sankarasrinivasan
Liu, Jia-Hao
Hsu, Wei-Wen
description Mitochondria are the organelles that generate energy for the cells. Many studies have suggested that mitochondrial dysfunction or impairment may be related to cancer and other neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases. Therefore, morphologically detailed alterations in mitochondria and 3D reconstruction of mitochondria are highly demanded research problems in the performance of clinical diagnosis. Nevertheless, manual mitochondria segmentation over 3D electron microscopy volumes is not a trivial task. This study proposes a two-stage cascaded CNN architecture to achieve automated 3D mitochondria segmentation, combining the merits of top-down and bottom-up approaches. For top-down approaches, the segmentation is conducted on objects’ localization so that the delineations of objects’ contours can be more precise. However, the combinations of 2D segmentation from the top-down approaches are inadequate to perform proper 3D segmentation without the information on connectivity among frames. On the other hand, the bottom-up approach finds coherent groups of pixels and takes the information of 3D connectivity into account in segmentation to avoid the drawbacks of the 2D top-down approach. However, many small areas that share similar pixel properties with mitochondria become false positives due to insufficient information on objects’ localization. In the proposed method, the detection of mitochondria is carried out with multi-slice fusion in the first stage, forming the segmentation cues. Subsequently, the second stage is to perform 3D CNN segmentation that learns the pixel properties and the information of 3D connectivity under the supervision of cues from the detection stage. Experimental results show that the proposed structure alleviates the problems in both the top-down and bottom-up approaches, which significantly accomplishes better performance in segmentation and expedites clinical analysis.
doi_str_mv 10.3390/electronics12040928
format Article
fullrecord <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2779528528</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A743140193</galeid><sourcerecordid>A743140193</sourcerecordid><originalsourceid>FETCH-LOGICAL-c339t-d7bb35552a694085032586afd63f64fb17f234ec5da9ebd262fae97f292b96943</originalsourceid><addsrcrecordid>eNptUdlKAzEUDaJg0X6BLwGfp2aZLW-WsS7Q1ofW55DJUlNmJjVJEf_elAoq9HLhXg7n3IUDwA1GE0oZutOdltG7wcqACcoRI_UZGBFUsYwRRs7_9JdgHMIWpWCY1hSNwP3602WrKDYaNiJIobSCzXIJF07pDhrnIX2ACxudfHeD8lbA2QKu9KbXQxTRuuEaXBjRBT3-qVfg7XG2bp6z-evTSzOdZzIdGTNVtS0tioKIkuWoLhAlRV0Ko0pqyty0uDKE5loWSjDdKlISIzRLICMtSxJ6BW6Pc3fefex1iHzr9n5IKzmpKlaQOuUvayM6ze1gXPRC9jZIPq1yinOEGU2syQmWOHzfW-kGbWzC_wnoUSC9C8Frw3fe9sJ_cYz4wQR-wgT6DeoReXA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2779528528</pqid></control><display><type>article</type><title>Two-Stage Cascaded CNN Model for 3D Mitochondria EM Segmentation</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Guo, Jing-Ming ; Seshathiri, Sankarasrinivasan ; Liu, Jia-Hao ; Hsu, Wei-Wen</creator><creatorcontrib>Guo, Jing-Ming ; Seshathiri, Sankarasrinivasan ; Liu, Jia-Hao ; Hsu, Wei-Wen</creatorcontrib><description>Mitochondria are the organelles that generate energy for the cells. Many studies have suggested that mitochondrial dysfunction or impairment may be related to cancer and other neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases. Therefore, morphologically detailed alterations in mitochondria and 3D reconstruction of mitochondria are highly demanded research problems in the performance of clinical diagnosis. Nevertheless, manual mitochondria segmentation over 3D electron microscopy volumes is not a trivial task. This study proposes a two-stage cascaded CNN architecture to achieve automated 3D mitochondria segmentation, combining the merits of top-down and bottom-up approaches. For top-down approaches, the segmentation is conducted on objects’ localization so that the delineations of objects’ contours can be more precise. However, the combinations of 2D segmentation from the top-down approaches are inadequate to perform proper 3D segmentation without the information on connectivity among frames. On the other hand, the bottom-up approach finds coherent groups of pixels and takes the information of 3D connectivity into account in segmentation to avoid the drawbacks of the 2D top-down approach. However, many small areas that share similar pixel properties with mitochondria become false positives due to insufficient information on objects’ localization. In the proposed method, the detection of mitochondria is carried out with multi-slice fusion in the first stage, forming the segmentation cues. Subsequently, the second stage is to perform 3D CNN segmentation that learns the pixel properties and the information of 3D connectivity under the supervision of cues from the detection stage. Experimental results show that the proposed structure alleviates the problems in both the top-down and bottom-up approaches, which significantly accomplishes better performance in segmentation and expedites clinical analysis.</description><identifier>ISSN: 2079-9292</identifier><identifier>EISSN: 2079-9292</identifier><identifier>DOI: 10.3390/electronics12040928</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Algorithms ; Alzheimer's disease ; Cancer ; Datasets ; Diagnostic imaging ; Electron microscopes ; Image reconstruction ; Image segmentation ; Localization ; Medical examination ; Microscopy ; Mitochondria ; Morphology ; Neural networks ; Object recognition ; Organelles ; Pixels ; Segmentation ; Three dimensional models</subject><ispartof>Electronics (Basel), 2023-02, Vol.12 (4), p.928</ispartof><rights>COPYRIGHT 2023 MDPI AG</rights><rights>2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c339t-d7bb35552a694085032586afd63f64fb17f234ec5da9ebd262fae97f292b96943</cites><orcidid>0000-0002-8041-6326 ; 0000-0002-8554-1265</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Guo, Jing-Ming</creatorcontrib><creatorcontrib>Seshathiri, Sankarasrinivasan</creatorcontrib><creatorcontrib>Liu, Jia-Hao</creatorcontrib><creatorcontrib>Hsu, Wei-Wen</creatorcontrib><title>Two-Stage Cascaded CNN Model for 3D Mitochondria EM Segmentation</title><title>Electronics (Basel)</title><description>Mitochondria are the organelles that generate energy for the cells. Many studies have suggested that mitochondrial dysfunction or impairment may be related to cancer and other neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases. Therefore, morphologically detailed alterations in mitochondria and 3D reconstruction of mitochondria are highly demanded research problems in the performance of clinical diagnosis. Nevertheless, manual mitochondria segmentation over 3D electron microscopy volumes is not a trivial task. This study proposes a two-stage cascaded CNN architecture to achieve automated 3D mitochondria segmentation, combining the merits of top-down and bottom-up approaches. For top-down approaches, the segmentation is conducted on objects’ localization so that the delineations of objects’ contours can be more precise. However, the combinations of 2D segmentation from the top-down approaches are inadequate to perform proper 3D segmentation without the information on connectivity among frames. On the other hand, the bottom-up approach finds coherent groups of pixels and takes the information of 3D connectivity into account in segmentation to avoid the drawbacks of the 2D top-down approach. However, many small areas that share similar pixel properties with mitochondria become false positives due to insufficient information on objects’ localization. In the proposed method, the detection of mitochondria is carried out with multi-slice fusion in the first stage, forming the segmentation cues. Subsequently, the second stage is to perform 3D CNN segmentation that learns the pixel properties and the information of 3D connectivity under the supervision of cues from the detection stage. Experimental results show that the proposed structure alleviates the problems in both the top-down and bottom-up approaches, which significantly accomplishes better performance in segmentation and expedites clinical analysis.</description><subject>Algorithms</subject><subject>Alzheimer's disease</subject><subject>Cancer</subject><subject>Datasets</subject><subject>Diagnostic imaging</subject><subject>Electron microscopes</subject><subject>Image reconstruction</subject><subject>Image segmentation</subject><subject>Localization</subject><subject>Medical examination</subject><subject>Microscopy</subject><subject>Mitochondria</subject><subject>Morphology</subject><subject>Neural networks</subject><subject>Object recognition</subject><subject>Organelles</subject><subject>Pixels</subject><subject>Segmentation</subject><subject>Three dimensional models</subject><issn>2079-9292</issn><issn>2079-9292</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNptUdlKAzEUDaJg0X6BLwGfp2aZLW-WsS7Q1ofW55DJUlNmJjVJEf_elAoq9HLhXg7n3IUDwA1GE0oZutOdltG7wcqACcoRI_UZGBFUsYwRRs7_9JdgHMIWpWCY1hSNwP3602WrKDYaNiJIobSCzXIJF07pDhrnIX2ACxudfHeD8lbA2QKu9KbXQxTRuuEaXBjRBT3-qVfg7XG2bp6z-evTSzOdZzIdGTNVtS0tioKIkuWoLhAlRV0Ko0pqyty0uDKE5loWSjDdKlISIzRLICMtSxJ6BW6Pc3fefex1iHzr9n5IKzmpKlaQOuUvayM6ze1gXPRC9jZIPq1yinOEGU2syQmWOHzfW-kGbWzC_wnoUSC9C8Frw3fe9sJ_cYz4wQR-wgT6DeoReXA</recordid><startdate>20230201</startdate><enddate>20230201</enddate><creator>Guo, Jing-Ming</creator><creator>Seshathiri, Sankarasrinivasan</creator><creator>Liu, Jia-Hao</creator><creator>Hsu, Wei-Wen</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>COVID</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L7M</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><orcidid>https://orcid.org/0000-0002-8041-6326</orcidid><orcidid>https://orcid.org/0000-0002-8554-1265</orcidid></search><sort><creationdate>20230201</creationdate><title>Two-Stage Cascaded CNN Model for 3D Mitochondria EM Segmentation</title><author>Guo, Jing-Ming ; Seshathiri, Sankarasrinivasan ; Liu, Jia-Hao ; Hsu, Wei-Wen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c339t-d7bb35552a694085032586afd63f64fb17f234ec5da9ebd262fae97f292b96943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Alzheimer's disease</topic><topic>Cancer</topic><topic>Datasets</topic><topic>Diagnostic imaging</topic><topic>Electron microscopes</topic><topic>Image reconstruction</topic><topic>Image segmentation</topic><topic>Localization</topic><topic>Medical examination</topic><topic>Microscopy</topic><topic>Mitochondria</topic><topic>Morphology</topic><topic>Neural networks</topic><topic>Object recognition</topic><topic>Organelles</topic><topic>Pixels</topic><topic>Segmentation</topic><topic>Three dimensional models</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Guo, Jing-Ming</creatorcontrib><creatorcontrib>Seshathiri, Sankarasrinivasan</creatorcontrib><creatorcontrib>Liu, Jia-Hao</creatorcontrib><creatorcontrib>Hsu, Wei-Wen</creatorcontrib><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>Proquest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>Coronavirus Research Database</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><jtitle>Electronics (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Guo, Jing-Ming</au><au>Seshathiri, Sankarasrinivasan</au><au>Liu, Jia-Hao</au><au>Hsu, Wei-Wen</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Two-Stage Cascaded CNN Model for 3D Mitochondria EM Segmentation</atitle><jtitle>Electronics (Basel)</jtitle><date>2023-02-01</date><risdate>2023</risdate><volume>12</volume><issue>4</issue><spage>928</spage><pages>928-</pages><issn>2079-9292</issn><eissn>2079-9292</eissn><abstract>Mitochondria are the organelles that generate energy for the cells. Many studies have suggested that mitochondrial dysfunction or impairment may be related to cancer and other neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases. Therefore, morphologically detailed alterations in mitochondria and 3D reconstruction of mitochondria are highly demanded research problems in the performance of clinical diagnosis. Nevertheless, manual mitochondria segmentation over 3D electron microscopy volumes is not a trivial task. This study proposes a two-stage cascaded CNN architecture to achieve automated 3D mitochondria segmentation, combining the merits of top-down and bottom-up approaches. For top-down approaches, the segmentation is conducted on objects’ localization so that the delineations of objects’ contours can be more precise. However, the combinations of 2D segmentation from the top-down approaches are inadequate to perform proper 3D segmentation without the information on connectivity among frames. On the other hand, the bottom-up approach finds coherent groups of pixels and takes the information of 3D connectivity into account in segmentation to avoid the drawbacks of the 2D top-down approach. However, many small areas that share similar pixel properties with mitochondria become false positives due to insufficient information on objects’ localization. In the proposed method, the detection of mitochondria is carried out with multi-slice fusion in the first stage, forming the segmentation cues. Subsequently, the second stage is to perform 3D CNN segmentation that learns the pixel properties and the information of 3D connectivity under the supervision of cues from the detection stage. Experimental results show that the proposed structure alleviates the problems in both the top-down and bottom-up approaches, which significantly accomplishes better performance in segmentation and expedites clinical analysis.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/electronics12040928</doi><orcidid>https://orcid.org/0000-0002-8041-6326</orcidid><orcidid>https://orcid.org/0000-0002-8554-1265</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2079-9292
ispartof Electronics (Basel), 2023-02, Vol.12 (4), p.928
issn 2079-9292
2079-9292
language eng
recordid cdi_proquest_journals_2779528528
source MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals
subjects Algorithms
Alzheimer's disease
Cancer
Datasets
Diagnostic imaging
Electron microscopes
Image reconstruction
Image segmentation
Localization
Medical examination
Microscopy
Mitochondria
Morphology
Neural networks
Object recognition
Organelles
Pixels
Segmentation
Three dimensional models
title Two-Stage Cascaded CNN Model for 3D Mitochondria EM Segmentation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T17%3A35%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Two-Stage%20Cascaded%20CNN%20Model%20for%203D%20Mitochondria%20EM%20Segmentation&rft.jtitle=Electronics%20(Basel)&rft.au=Guo,%20Jing-Ming&rft.date=2023-02-01&rft.volume=12&rft.issue=4&rft.spage=928&rft.pages=928-&rft.issn=2079-9292&rft.eissn=2079-9292&rft_id=info:doi/10.3390/electronics12040928&rft_dat=%3Cgale_proqu%3EA743140193%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2779528528&rft_id=info:pmid/&rft_galeid=A743140193&rfr_iscdi=true