Patient-specific cerebral 3D vessel model reconstruction using deep learning.
Aneurysm
Deep learning
Magnetic resonance angiography
Medical image processing
Segmentation
Journal
Medical & biological engineering & computing
ISSN: 1741-0444
Titre abrégé: Med Biol Eng Comput
Pays: United States
ID NLM: 7704869
Informations de publication
Date de publication:
28 May 2024
28 May 2024
Historique:
received:
19
01
2024
accepted:
18
05
2024
medline:
28
5
2024
pubmed:
28
5
2024
entrez:
27
5
2024
Statut:
aheadofprint
Résumé
Three-dimensional vessel model reconstruction from patient-specific magnetic resonance angiography (MRA) images often requires some manual maneuvers. This study aimed to establish the deep learning (DL)-based method for vessel model reconstruction. Time of flight MRA of 40 patients with internal carotid artery aneurysms was prepared, and three-dimensional vessel models were constructed using the threshold and region-growing method. Using those datasets, supervised deep learning using 2D U-net was performed to reconstruct 3D vessel models. The accuracy of the DL-based vessel segmentations was assessed using 20 MRA images outside the training dataset. The dice coefficient was used as the indicator of the model accuracy, and the blood flow simulation was performed using the DL-based vessel model. The created DL model could successfully reconstruct a three-dimensional model in all 60 cases. The dice coefficient in the test dataset was 0.859. Of note, the DL-generated model proved its efficacy even for large aneurysms (> 10 mm in their diameter). The reconstructed model was feasible in performing blood flow simulation to assist clinical decision-making. Our DL-based method could successfully reconstruct a three-dimensional vessel model with moderate accuracy. Future studies are warranted to exhibit that DL-based technology can promote medical image processing.
Identifiants
pubmed: 38802608
doi: 10.1007/s11517-024-03136-6
pii: 10.1007/s11517-024-03136-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : AIP Network Laboratory
ID : Grant number JPMJCR17A1
Informations de copyright
© 2024. The Author(s).
Références
Kin T, Oyama H, Kamada K, Aoki S, Ohtomo K, Saito N (2009) Prediction of surgical view of neurovascular decompression using interactive computer graphics. Neurosurgery 65:121–128
doi: 10.1227/01.NEU.0000347890.19718.0A
pubmed: 19574833
Saito N, Kin T, Oyama H et al (2013) Surgical simulation of cerebrovascular disease with multimodal fusion 3-dimensional computer graphics. Neurosurgery 60(Suppl 1):24–29
doi: 10.1227/01.neu.0000430312.71326.6d
pubmed: 23839348
Kin T, Shin M, Oyama H et al (2011) Impact of multiorgan fusion imaging and interactive 3-dimensional visualization for intraventricular neuroendoscopic surgery. Neurosurgery 69(1 Suppl Operative):ons40-48
pubmed: 21336214
Yoshino M, Kin T, Hara T (2019) Usefulness of high-resolution three-dimensional multifusion medical imaging for preoperative planning in patients with cerebral arteriovenous malformation. World Neurosurg 124:e755–e763
doi: 10.1016/j.wneu.2018.12.217
pubmed: 30677580
Shojima M, Oshima M, Takagi K et al (2004) Magnitude and role of wall shear stress on cerebral aneurysm: computational fluid dynamic study of 20 middle cerebral artery aneurysms. Stroke 35:2500–2505
doi: 10.1161/01.STR.0000144648.89172.0f
pubmed: 15514200
Shojima M, Oshima M, Takagi K et al (2005) Role of the bloodstream impacting force and the local pressure elevation in the rupture of cerebral aneurysms. Stroke 36:1933–1938
doi: 10.1161/01.STR.0000177877.88925.06
pubmed: 16081858
Haruma J, Sugiu K, Hoshika M et al (2022) A new method of intracranial aneurysm modeling for stereolithography apparatus 3d printer: the “wall-carving technique” using digital imaging and communications in medicine data. World Neurosurg 159:e113–e119
doi: 10.1016/j.wneu.2021.12.018
pubmed: 34896354
Hosny A, Parmar C, Coroller TP et al (2018) Deep learning for lung cancer prognostication: a retrospective multi-cohort radiomics study. PLoS Med 15:e1002711
doi: 10.1371/journal.pmed.1002711
pubmed: 30500819
pmcid: 6269088
Mensah E, Pringle C, Roberts G, Gurusinghe N, Golash A, Alalade AF (2022) Deep learning in the management of intracranial aneurysms and cerebrovascular diseases: a review of the current literature. World Neurosurg 161:39–45
doi: 10.1016/j.wneu.2022.02.006
pubmed: 35134582
Fanwei K, Nathan W, Shawn S (2021) A deep-learning approach for direct whole-heart mesh reconstruction. Med Image Anal 74:102222
doi: 10.1016/j.media.2021.102222
Shin S, Kim MW, Jin KH et al (2023) Deep 3D reconstruction of synchrotron X-ray computed tomography for intact lungs. Sci Rep 13:1738
doi: 10.1038/s41598-023-27627-y
pubmed: 36720962
pmcid: 9889716
Nomura S, Kin T, Kunimatsu A et al (2021) Registration method between phase-contrast magnetic resonance angiography and time-of-flight magnetic resonance angiography—a preliminary study. J Med Imaging Health Inform 11:33–39
doi: 10.1166/jmihi.2021.3505
Zeiler MD (2022) ADADELTA: an adaptive learning rate method. https://doi.org/10.48550/arXiv.1212.5701
Murray CD (1926) The physiological principle of minimum work applied to the angle of branching of arteries. J Gen Physiol 9:835–841
doi: 10.1085/jgp.9.6.835
pubmed: 19872299
pmcid: 2140901
Zhang M, Tupin S, Anzai H et al (2021) Implementation of computer simulation to assess flow diversion treatment outcomes: systematic review and meta-analysis. J Neurointerv Surg 13:164–170
doi: 10.1136/neurintsurg-2020-016724
pubmed: 33097626
Joo B, Ahn SS, Yoon PH et al (2020) A deep learning algorithm may automate intracranial aneurysm detection on MR angiography with high diagnostic performance. Eur Radiol 30:5785–5793
doi: 10.1007/s00330-020-06966-8
pubmed: 32474633
Olive-Gadea M, Crespo C, Granes C et al (2020) Deep learning based software to identify large vessel occlusion on noncontrast computed tomography. Stroke 51:3133–3137
doi: 10.1161/STROKEAHA.120.030326
pubmed: 32842922
Meng S, Tran TML, Hu M et al (2022) End-to-end artificial intelligence platform for the management of large vessel occlusions: a preliminary study. J Stroke Cerebrovasc Dis 31:106753
doi: 10.1016/j.jstrokecerebrovasdis.2022.106753
pubmed: 36115105
Westenberg JJ, van der Geest RJ, Wasser MN et al (2000) Vessel diameter measurements in gadolinium contrast-enhanced three-dimensional MRA of peripheral arteries. Magn Reson Imaging 18:13–22
doi: 10.1016/S0730-725X(99)00099-5
pubmed: 10642098
Yoshino M, Kin T, Nakatomi H, Oyama H, Saito N (2013) Presurgical planning of feeder resection with realistic three-dimensional virtual operation field in patient with cerebellopontine angle meningioma. Acta Neurochir (Wien) 155:1391–1399
doi: 10.1007/s00701-013-1761-6
pubmed: 23722311
Shono N, Igarashi T, Kin T, Saito T, Saito N (2022) Threshold field painting saves the time for segmentation of minute arteries. Int J Comput Assist Radiol Surg 17:2121–2130
doi: 10.1007/s11548-022-02682-4
pubmed: 35689722
Garc ́ıa C, Fang Y, Liu J, Narata AP, Orlando JI, Larrabide I (2022) A deep learning model for brain vessel segmentation in 3DRA with arteriovenous malformations. Symposium on Medical Information Processing and Analysis. https://doi.org/10.48550/arXiv.2210.02416
Livne M, Rieger J, Aydin OU, et al (2019) A U-net deep learning framework for high performance vessel segmentation in patients with cerebrovascular disease. Frontiers in Neuroscience 13. https://doi.org/10.3389/fnins.2019.00097
Vlak MH, Algra A, Brandenburg R, Rinkel GJ (2011) Prevalence of unruptured intracranial aneurysms, with emphasis on sex, age, comorbidity, country, and time period: a systematic review and meta-analysis. Lancet Neurol 10:626–636. https://doi.org/10.1016/S1474-4422(11)70109-0
doi: 10.1016/S1474-4422(11)70109-0
pubmed: 21641282
Morita A, Kirino T, Hashi K et al (2012) The natural course of unruptured cerebral aneurysms in a Japanese cohort. N Engl J Med 366:2474–2482. https://doi.org/10.1056/NEJMoa1113260
doi: 10.1056/NEJMoa1113260
pubmed: 22738097
Greving JP, Wermer MJH, Brown RD et al (2014) Development of the PHASES score for prediction of risk of rupture of intracranial aneurysms: a pooled analysis of six prospective cohort studies. The Lancet Neurology 13:59–66. https://doi.org/10.1016/s1474-4422(13)70263-1
doi: 10.1016/s1474-4422(13)70263-1
pubmed: 24290159
Backes D, Vergouwen MDI, Tiel Groenestege AT et al (2015) PHASES score for prediction of intracranial aneurysm growth. Stroke 46:1221–1226. https://doi.org/10.1161/strokeaha.114.008198
doi: 10.1161/strokeaha.114.008198
pubmed: 25757900