000267481 001__ 267481
000267481 005__ 20250523100557.0
000267481 0247_ $$2pmid$$apmid:39574480
000267481 0247_ $$2doi$$a10.1162/imag_a_00034
000267481 0247_ $$2altmetric$$aaltmetric:156261833
000267481 0247_ $$2pmc$$apmc:PMC11576934
000267481 037__ $$aDZNE-2024-00132
000267481 082__ $$a050
000267481 1001_ $$0P:(DE-2719)2812449$$aEstrada, Santiago$$b0$$eFirst author
000267481 245__ $$aFastSurfer-HypVINN: Automated sub-segmentation of the hypothalamus and adjacent structures on high-resolutional brain MRI
000267481 260__ $$aCambridge, MA$$bMIT Press$$c2023
000267481 3367_ $$2DRIVER$$aarticle
000267481 3367_ $$2DataCite$$aOutput Types/Journal article
000267481 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1747922433_19988
000267481 3367_ $$2BibTeX$$aARTICLE
000267481 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000267481 3367_ $$00$$2EndNote$$aJournal Article
000267481 520__ $$aThe hypothalamus plays a crucial role in the regulation of a broad range of physiological, behavioral, and cognitive functions. However, despite its importance, only a few small-scale neuroimaging studies have investigated its substructures, likely due to the lack of fully automated segmentation tools to address scalability and reproducibility issues of manual segmentation. While the only previous attempt to automatically sub-segment the hypothalamus with a neural network showed promise for 1.0 mm isotropic T1-weighted (T1w) magnetic resonance imaging (MRI), there is a need for an automated tool to sub-segment also high-resolutional (HiRes) MR scans, as they are becoming widely available, and include structural detail also from multi-modal MRI. We, therefore, introduce a novel, fast, and fully automated deep-learning method named HypVINN for sub-segmentation of the hypothalamus and adjacent structures on 0.8 mm isotropic T1w and T2w brain MR images that is robust to missing modalities. We extensively validate our model with respect to segmentation accuracy, generalizability, in-session test-retest reliability, and sensitivity to replicate hypothalamic volume effects (e.g., sex differences). The proposed method exhibits high segmentation performance both for standalone T1w images as well as for T1w/T2w image pairs. Even with the additional capability to accept flexible inputs, our model matches or exceeds the performance of state-of-the-art methods with fixed inputs. We, further, demonstrate the generalizability of our method in experiments with 1.0 mm MR scans from both the Rhineland Study and the UK Biobank-an independent dataset never encountered during training with different acquisition parameters and demographics. Finally, HypVINN can perform the segmentation in less than a minute (graphical processing unit [GPU]) and will be available in the open source FastSurfer neuroimaging software suite, offering a validated, efficient, and scalable solution for evaluating imaging-derived phenotypes of the hypothalamus.
000267481 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0
000267481 588__ $$aDataset connected to DataCite
000267481 693__ $$0EXP:(DE-2719)Rhineland Study-20190321$$5EXP:(DE-2719)Rhineland Study-20190321$$eRhineland Study / Bonn$$x0
000267481 7001_ $$0P:(DE-2719)2814290$$aKügler, David$$b1
000267481 7001_ $$0P:(DE-2719)2812803$$aBahrami Rad, Emad$$b2
000267481 7001_ $$0P:(DE-2719)9001766$$aXu, Peng$$b3
000267481 7001_ $$0P:(DE-2719)2814343$$aMousa, Dilshad$$b4
000267481 7001_ $$0P:(DE-2719)2810403$$aBreteler, Monique M. B.$$b5
000267481 7001_ $$0P:(DE-2719)2812578$$aAziz, N. Ahmad$$b6
000267481 7001_ $$0P:(DE-2719)2812134$$aReuter, Martin$$b7$$eLast author
000267481 773__ $$0PERI:(DE-600)3167925-0$$a10.1162/imag_a_00034$$gVol. 1, p. 1 - 32$$p1 - 32$$tImaging neuroscience$$v1$$x2837-6056$$y2023
000267481 8564_ $$uhttps://pub.dzne.de/record/267481/files/DZNE-2024-00132.pdf$$yOpenAccess
000267481 8564_ $$uhttps://pub.dzne.de/record/267481/files/DZNE-2024-00132.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000267481 909CO $$ooai:pub.dzne.de:267481$$pdriver$$pVDB$$popen_access$$pdnbdelivery$$popenaire
000267481 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812449$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b0$$kDZNE
000267481 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2814290$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b1$$kDZNE
000267481 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812803$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b2$$kDZNE
000267481 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9001766$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b3$$kDZNE
000267481 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2814343$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b4$$kDZNE
000267481 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2810403$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b5$$kDZNE
000267481 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812578$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b6$$kDZNE
000267481 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812134$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b7$$kDZNE
000267481 9131_ $$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$$x0
000267481 9141_ $$y2023
000267481 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000267481 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000267481 920__ $$lyes
000267481 9201_ $$0I:(DE-2719)1040310$$kAG Reuter$$lArtificial Intelligence in Medicine$$x0
000267481 9201_ $$0I:(DE-2719)5000071$$kAG Aziz$$lPopulation & Clinical Neuroepidemiology$$x1
000267481 9201_ $$0I:(DE-2719)1012001$$kAG Breteler$$lPopulation Health Sciences$$x2
000267481 980__ $$ajournal
000267481 980__ $$aVDB
000267481 980__ $$aI:(DE-2719)1040310
000267481 980__ $$aI:(DE-2719)5000071
000267481 980__ $$aI:(DE-2719)1012001
000267481 980__ $$aUNRESTRICTED
000267481 9801_ $$aFullTexts