دورية أكاديمية
أعرض في EDS

DBSegment: Fast and robust segmentation of deep brain structures considering domain generalization.

التفاصيل البيبلوغرافية
العنوان: DBSegment: Fast and robust segmentation of deep brain structures considering domain generalization.
المؤلفون: Baniasadi M; National Department of Neurosurgery, Centre Hospitalier de, Luxembourg Center for Systems Biomedicine, University of Luxembourg, Esch-sur-Alzette, Luxembourg., Petersen MV; Department of Clinical Medicine, Center of Functionally Integrative Neuroscience, University of Aarhus, Aarhus, Denmark., Gonçalves J; Luxembourg Center for Systems Biomedicine, University of Luxembourg, Esch-sur-Alzette, Luxembourg., Horn A; Neuromodulation and Movement Disorders Unit, Department of Neurology, Charité-Universitätsmedizin Berlin, Berlin, Germany.; MGH Neurosurgery and Center for Neurotechnology and Neurorecovery at MGH Neurology Massachusetts General Hospital, Harvard Medical School, Boston, USA.; Center for Brain Circuit Therapeutics, Department of Neurology, Brigham and Women's Hospital, Harvard Medical School, Boston, USA., Vlasov V; Luxembourg Center for Systems Biomedicine, University of Luxembourg, Esch-sur-Alzette, Luxembourg., Hertel F; National Department of Neurosurgery, Centre Hospitalier de Luxembourg, Luxembourg., Husch A; Luxembourg Center for Systems Biomedicine, University of Luxembourg, Esch-sur-Alzette, Luxembourg.
المصدر: Human brain mapping [Hum Brain Mapp] 2023 Feb 01; Vol. 44 (2), pp. 762-778. Date of Electronic Publication: 2022 Oct 17.
نوع المنشور: Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't
اللغة: English
بيانات الدورية: Publisher: Wiley Country of Publication: United States NLM ID: 9419065 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1097-0193 (Electronic) Linking ISSN: 10659471 NLM ISO Abbreviation: Hum Brain Mapp Subsets: MEDLINE
أسماء مطبوعة: Publication: New York : Wiley
Original Publication: New York : Wiley-Liss, c1993-
مواضيع طبية MeSH: Image Processing, Computer-Assisted*/methods , Brain*/diagnostic imaging, Humans ; Reproducibility of Results ; Neural Networks, Computer ; Magnetic Resonance Imaging/methods
مستخلص: Segmenting deep brain structures from magnetic resonance images is important for patient diagnosis, surgical planning, and research. Most current state-of-the-art solutions follow a segmentation-by-registration approach, where subject magnetic resonance imaging (MRIs) are mapped to a template with well-defined segmentations. However, registration-based pipelines are time-consuming, thus, limiting their clinical use. This paper uses deep learning to provide a one-step, robust, and efficient deep brain segmentation solution directly in the native space. The method consists of a preprocessing step to conform all MRI images to the same orientation, followed by a convolutional neural network using the nnU-Net framework. We use a total of 14 datasets from both research and clinical collections. Of these, seven were used for training and validation and seven were retained for testing. We trained the network to segment 30 deep brain structures, as well as a brain mask, using labels generated from a registration-based approach. We evaluated the generalizability of the network by performing a leave-one-dataset-out cross-validation, and independent testing on unseen datasets. Furthermore, we assessed cross-domain transportability by evaluating the results separately on different domains. We achieved an average dice score similarity of 0.89 ± 0.04 on the test datasets when compared to the registration-based gold standard. On our test system, the computation time decreased from 43 min for a reference registration-based pipeline to 1.3 min. Our proposed method is fast, robust, and generalizes with high reliability. It can be extended to the segmentation of other brain structures. It is publicly available on GitHub, and as a pip package for convenient usage.
(© 2022 The Authors. Human Brain Mapping published by Wiley Periodicals LLC.)
References: Neuroimage. 2020 Oct 1;219:117012. (PMID: 32526386)
IEEE Trans Med Imaging. 2012 Feb;31(2):276-86. (PMID: 21937346)
Brain Connect. 2012;2(6):345-55. (PMID: 23075313)
Med Image Anal. 2001 Jun;5(2):143-56. (PMID: 11516708)
Annu Rev Biomed Eng. 2000;2:315-37. (PMID: 11701515)
Neuroimage. 2002 Oct;17(2):825-41. (PMID: 12377157)
AJNR Am J Neuroradiol. 2009 Nov;30(10):1914-21. (PMID: 19713324)
Neuroimage. 2019 Jan 1;184:293-316. (PMID: 30179717)
Neural Netw. 2020 May;125:233-244. (PMID: 32151914)
Sci Data. 2018 Apr 17;5:180063. (PMID: 29664465)
Brain Stimul. 2018 Jul - Aug;11(4):863-866. (PMID: 29429953)
Neuroimage. 2013 Apr 15;70:33-6. (PMID: 23274184)
Neurotherapeutics. 2014 Jul;11(3):465-74. (PMID: 24833244)
Front Neuroinform. 2014 Feb 06;8:7. (PMID: 24567717)
Neuroimage. 2011 Apr 1;55(3):954-67. (PMID: 21216294)
J Neurosci. 2013 Mar 13;33(11):4896-900. (PMID: 23486960)
Hum Brain Mapp. 2023 Feb 1;44(2):762-778. (PMID: 36250712)
Acad Radiol. 2005 Oct;12(10):1232-40. (PMID: 16179200)
Neuroradiology. 2018 Mar;60(3):303-309. (PMID: 29307012)
Comput Methods Programs Biomed. 2011 Dec;104(3):e158-77. (PMID: 21871688)
Neuroimage. 2019 Feb 1;186:713-727. (PMID: 30502445)
J Neural Eng. 2018 Apr;15(2):026005. (PMID: 29235446)
Sci Data. 2017 Mar 14;4:170010. (PMID: 28291247)
Neuroimage. 2019 Jul 1;194:272-282. (PMID: 30894331)
Neuroimage. 2018 Apr 15;170:271-282. (PMID: 28536045)
Neurol Sci. 2018 Nov;39(11):1971-1976. (PMID: 30109466)
Alzheimers Dement. 2005 Jul;1(1):55-66. (PMID: 17476317)
Med Image Anal. 2011 Aug;15(4):622-39. (PMID: 20688559)
Neuroimage. 2010 May 15;51(1):221-7. (PMID: 20114079)
Artif Intell Med. 2016 Oct;73:45-69. (PMID: 27926381)
Curr Opin Neurobiol. 2003 Dec;13(6):696-706. (PMID: 14662371)
Nat Methods. 2021 Feb;18(2):203-211. (PMID: 33288961)
Neuroimage Clin. 2020;27:102271. (PMID: 32446242)
Sci Data. 2016 Dec 06;3:160110. (PMID: 27922632)
J Digit Imaging. 2017 Aug;30(4):449-459. (PMID: 28577131)
Biol Psychiatry. 2005 Mar 1;57(5):510-6. (PMID: 15737666)
Nat Commun. 2020 Jul 22;11(1):3673. (PMID: 32699250)
Int J Comput Assist Radiol Surg. 2018 Jul;13(7):1117-1128. (PMID: 29557997)
World Neurosurg. 2017 Jul;103:531-537. (PMID: 28427973)
Magn Reson Imaging. 2017 Jun;39:110-122. (PMID: 28188873)
Neuroimage. 2009 Oct 15;48(1):63-72. (PMID: 19573611)
Oper Neurosurg (Hagerstown). 2019 Nov 1;17(5):497-502. (PMID: 30860266)
Neuroimage. 2007 Oct 15;38(1):95-113. (PMID: 17761438)
Neuroimage. 2012 Oct 1;62(4):2222-31. (PMID: 22366334)
World Neurosurg. 2020 Feb;134:e98-e102. (PMID: 31568905)
Neuroimage. 2009 Aug 1;47(1):194-8. (PMID: 19344771)
Stereotact Funct Neurosurg. 2018;96(5):281-288. (PMID: 30269142)
Neuroimage. 2005 Jul 1;26(3):839-51. (PMID: 15955494)
Mov Disord. 2003 Nov;18(11):1332-7. (PMID: 14639676)
Med Image Anal. 2018 Aug;48:177-186. (PMID: 29935442)
Radiology. 2021 Aug;300(2):260-278. (PMID: 34100679)
Neuroimage. 2006 Jul 1;31(3):1116-28. (PMID: 16545965)
Neuroimage. 2015 Feb 15;107:127-135. (PMID: 25498389)
J Neural Eng. 2019 Feb;16(1):016020. (PMID: 30524006)
معلومات مُعتمدة: R01 NS127892 United States NS NINDS NIH HHS; R01 MH113929 United States MH NIMH NIH HHS; P01 AG026276 United States AG NIA NIH HHS; P01 AG003991 United States AG NIA NIH HHS; R01 AG043434 United States AG NIA NIH HHS; UL1 TR000448 United States TR NCATS NIH HHS; R01 EB009352 United States EB NIBIB NIH HHS
فهرسة مساهمة: Keywords: confounder; deep brain structures; deep learning; magnetic resonance imaging; segmentation
تواريخ الأحداث: Date Created: 20221017 Date Completed: 20230118 Latest Revision: 20230222
رمز التحديث: 20231215
مُعرف محوري في PubMed: PMC9842883
DOI: 10.1002/hbm.26097
PMID: 36250712
قاعدة البيانات: MEDLINE
الوصف
تدمد:1097-0193
DOI:10.1002/hbm.26097