000162724 001__ 162724
000162724 005__ 20250523100555.0
000162724 0247_ $$2doi$$a10.1016/j.neuroimage.2021.118464
000162724 0247_ $$2pmid$$apmid:34389442
000162724 0247_ $$2pmc$$apmc:PMC8473894
000162724 0247_ $$2ISSN$$a1053-8119
000162724 0247_ $$2ISSN$$a1095-9572
000162724 0247_ $$2altmetric$$aaltmetric:111630964
000162724 037__ $$aDZNE-2021-01381
000162724 041__ $$aEnglish
000162724 082__ $$a610
000162724 1001_ $$0P:(DE-2719)2812449$$aEstrada Leon, Edgar Santiago$$b0$$eFirst author$$udzne
000162724 245__ $$aAutomated olfactory bulb segmentation on high resolutional T2-weighted MRI.
000162724 260__ $$aOrlando, Fla.$$bAcademic Press$$c2021
000162724 3367_ $$2DRIVER$$aarticle
000162724 3367_ $$2DataCite$$aOutput Types/Journal article
000162724 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1747926282_14718
000162724 3367_ $$2BibTeX$$aARTICLE
000162724 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000162724 3367_ $$00$$2EndNote$$aJournal Article
000162724 500__ $$aCC BY
000162724 520__ $$aThe neuroimage analysis community has neglected the automated segmentation of the olfactory bulb (OB) despite its crucial role in olfactory function. The lack of an automatic processing method for the OB can be explained by its challenging properties (small size, location, and poor visibility on traditional MRI scans). Nonetheless, recent advances in MRI acquisition techniques and resolution have allowed raters to generate more reliable manual annotations. Furthermore, the high accuracy of deep learning methods for solving semantic segmentation problems provides us with an option to reliably assess even small structures. In this work, we introduce a novel, fast, and fully automated deep learning pipeline to accurately segment OB tissue on sub-millimeter T2-weighted (T2w) whole-brain MR images. To this end, we designed a three-stage pipeline: (1) Localization of a region containing both OBs using FastSurferCNN, (2) Segmentation of OB tissue within the localized region through four independent AttFastSurferCNN - a novel deep learning architecture with a self-attention mechanism to improve modeling of contextual information, and (3) Ensemble of the predicted label maps. For this work, both OBs were manually annotated in a total of 620 T2w images for training (n=357) and testing. The OB pipeline exhibits high performance in terms of boundary delineation, OB localization, and volume estimation across a wide range of ages in 203 participants of the Rhineland Study (Dice Score (Dice): 0.852, Volume Similarity (VS): 0.910, and Average Hausdorff Distance (AVD): 0.215 mm). Moreover, it also generalizes to scans of an independent dataset never encountered during training, the Human Connectome Project (HCP), with different acquisition parameters and demographics, evaluated in 30 cases at the native 0.7 mm HCP resolution (Dice: 0.738, VS: 0.790, and AVD: 0.340 mm), and the default 0.8 mm pipeline resolution (Dice: 0.782, VS: 0.858, and AVD: 0.268 mm). We extensively validated our pipeline not only with respect to segmentation accuracy but also to known OB volume effects, where it can sensitively replicate age effects (β=-0.232, p<.01). Furthermore, our method can analyze a 3D volume in less than a minute (GPU) in an end-to-end fashion, providing a validated, efficient, and scalable solution for automatically assessing OB volumes.
000162724 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0
000162724 588__ $$aDataset connected to CrossRef, PubMed, , Journals: pub.dzne.de
000162724 650_7 $$2Other$$aConvolutional neural networks
000162724 650_7 $$2Other$$aDeep learning
000162724 650_7 $$2Other$$aOlfactory bulb
000162724 650_7 $$2Other$$aSemantic segmentation
000162724 650_2 $$2MeSH$$aAdult
000162724 650_2 $$2MeSH$$aAged
000162724 650_2 $$2MeSH$$aDeep Learning
000162724 650_2 $$2MeSH$$aFemale
000162724 650_2 $$2MeSH$$aHumans
000162724 650_2 $$2MeSH$$aImage Processing, Computer-Assisted: methods
000162724 650_2 $$2MeSH$$aMagnetic Resonance Imaging: methods
000162724 650_2 $$2MeSH$$aMale
000162724 650_2 $$2MeSH$$aMiddle Aged
000162724 650_2 $$2MeSH$$aNeural Networks, Computer
000162724 650_2 $$2MeSH$$aOlfactory Bulb: diagnostic imaging
000162724 693__ $$0EXP:(DE-2719)Rhineland Study-20190321$$5EXP:(DE-2719)Rhineland Study-20190321$$eRhineland Study / Bonn$$x0
000162724 7001_ $$0P:(DE-2719)2811646$$aLu, Ran$$b1$$udzne
000162724 7001_ $$0P:(DE-2719)2812059$$aDiers, Kersten$$b2$$udzne
000162724 7001_ $$0P:(DE-2719)9000827$$aZeng, Weiyi$$b3$$udzne
000162724 7001_ $$0P:(DE-2719)2812222$$aEhses, Philipp$$b4$$udzne
000162724 7001_ $$0P:(DE-2719)2810538$$aStöcker, Tony$$b5$$udzne
000162724 7001_ $$0P:(DE-2719)2810403$$aBreteler, Monique$$b6$$udzne
000162724 7001_ $$0P:(DE-2719)2812134$$aReuter, Martin$$b7$$eLast author$$udzne
000162724 773__ $$0PERI:(DE-600)1471418-8$$a10.1016/j.neuroimage.2021.118464$$gVol. 242, p. 118464 -$$p118464$$tNeuroImage$$v242$$x1053-8119$$y2021
000162724 8564_ $$uhttps://pub.dzne.de/record/162724/files/DZNE-2021-01381.pdf$$yOpenAccess
000162724 8564_ $$uhttps://pub.dzne.de/record/162724/files/DZNE-2021-01381.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000162724 909CO $$ooai:pub.dzne.de:162724$$popenaire$$pdnbdelivery$$pdriver$$pVDB$$popen_access
000162724 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812449$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b0$$kDZNE
000162724 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2811646$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b1$$kDZNE
000162724 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812059$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b2$$kDZNE
000162724 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9000827$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b3$$kDZNE
000162724 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812222$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b4$$kDZNE
000162724 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2810538$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b5$$kDZNE
000162724 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2810403$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b6$$kDZNE
000162724 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812134$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b7$$kDZNE
000162724 9131_ $$0G:(DE-HGF)POF4-354$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Prevention and Healthy Aging$$x0
000162724 9141_ $$y2021
000162724 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-01-29
000162724 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2021-01-29
000162724 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-01-29
000162724 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2021-01-29
000162724 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000162724 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2021-01-29
000162724 915__ $$0LIC:(DE-HGF)CCBYNCNDNV$$2V:(DE-HGF)$$aCreative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND (No Version)$$bDOAJ$$d2021-01-29
000162724 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2022-11-12$$wger
000162724 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNEUROIMAGE : 2021$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2022-09-27T20:29:23Z
000162724 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2022-09-27T20:29:23Z
000162724 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2022-09-27T20:29:23Z
000162724 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2022-11-12
000162724 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bNEUROIMAGE : 2021$$d2022-11-12
000162724 9201_ $$0I:(DE-2719)1012001$$kAG Breteler$$lPopulation Health Sciences$$x0
000162724 9201_ $$0I:(DE-2719)1040310$$kAG Reuter$$lArtificial Intelligence in Medicine$$x1
000162724 9201_ $$0I:(DE-2719)1013026$$kAG Stöcker$$lMR Physics$$x2
000162724 980__ $$ajournal
000162724 980__ $$aVDB
000162724 980__ $$aI:(DE-2719)1012001
000162724 980__ $$aI:(DE-2719)1040310
000162724 980__ $$aI:(DE-2719)1013026
000162724 980__ $$aUNRESTRICTED
000162724 9801_ $$aFullTexts