Share：
Share this content in WeChat
X
[Chinese] [PDF] 184 7
• Review •
Advances in deep medullary veins and AI technology in imaging markers of cerebral small vessel disease
HAN Yan  ZHOU Longnian  WANG Yingchao  BA Zhixia  WANG Hong 

DOI:10.12015/issn.1674-8034.2025.08.024.


[Abstract] Cerebral small vessel disease (CSVD) is one of the most common subtypes of cerebrovascular disease, which is highly prevalent in the elderly population and associated with the occurrence and recurrence of stroke, gait disturbances, cognitive impairment, psychological disorders, and urinary difficulties. As CSVD is difficult to diagnose definitively by histology, the diagnosis of CSVD currently mainly relies on the neuroimaging markers shown by magnetic resonance imaging (MRI). An increasing number of studies have shown that deep medullary veins (DMVs) are related to the epidemiological and imaging features of CSVD and may be involved in the development of CSVD as a new imaging marker. However, the diagnostic process of CSVD lacks quantitative evaluation criteria, which easily prone to missed diagnosis and misdiagnosis. In recent years, emerging artificial intelligence (AI) technology has been widely used in the medical field to identify and extract imaging markers of CSVD, providing more neuroimaging information that cannot be identified by the naked eye for the diagnosis and prognosis of CSVD. This paper summarizes the research results on CSVD imaging markers from recent years in China and abroad, and briefly introduces the application of AI in evaluating CSVD imaging features. It summarizes the current research limitations and points out future research directions, aiming to provide more ideas for subsequent research.
[Keywords] cerebral small vessel disease；imaging markers；deep medullary veins；artificial intelligence；magnetic resonance imaging

HAN Yan1, 2   ZHOU Longnian3   WANG Yingchao1, 2   BA Zhixia1, 2   WANG Hong1, 2*  

1 Department of Medical Imaging, Zhangye People's Hospital, Hexi University, Zhangye 734000, China

2 Institute of Medical Imaging, Hexi University, Zhangye 734000, China

3 Department of Neurosurgery, Zhangye People's Hospital, Hexi University, Zhangye 734000, China

Corresponding author: WANG H, E-mail: 916255721@qq.com

Conflicts of interest   None.

Received  2025-03-12
Accepted  2025-08-08
DOI: 10.12015/issn.1674-8034.2025.08.024
DOI:10.12015/issn.1674-8034.2025.08.024.

[1]
LITAK J, MAZUREK M, KULESZA B, et al. Cerebral small vessel disease[J/OL]. Int J Mol Sci, 2020, 21(24): 9729 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/33419271/. DOI: 10.3390/ijms21249729.
[2]
VAN DEN BRINK H, DOUBAL F N, DUERING M. Advanced MRI in cerebral small vessel disease[J]. Int J Stroke, 2023, 18(1): 28-35. DOI: 10.1177/17474930221091879.
[3]
ZHANG X Y, LIU X M, XIA R Y, et al. Chinese herbal medicine for vascular cognitive impairment in cerebral small vessel disease: a protocol for systematic review and meta-analysis of randomized controlled trials[J/OL]. Medicine (Baltimore), 2020, 99(40): e22455 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/33019432/. DOI: 10.1097/MD.0000000000022455. [ DOI: ]
[4]
JIANG Y L, WANG S P, LI F, et al. Predictive value of cerebral blood tubule burden score for recurrent cerebrovascular events in patients with transient ischemic attack[J]. Chin J Magn Reson Imag, 2024, 15(6): 67-71. DOI: 10.12015/issn.1674-8034.2024.06.010.
[5]
ZHENG W Q, WANG X C. Research progress on the effect of neuroimaging markers of cerebral small vessel disease on stroke[J]. Chin J Magn Reson Imag, 2021, 12(4): 96-99. DOI: 10.12015/issn.1674-8034.2021.04.024.
[6]
HUANG P Y, LIU C, ZHEN Z M, et al. Advancements in the application of 7 T-MRI in cerebral small vessel disease[J]. Chin J Magn Reson Imag, 2024, 15(9): 151-156. DOI: 10.12015/issn.1674-8034.2024.09.026.
[7]
WARDLAW J M, SMITH E E, BIESSELS G J, et al. Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration[J]. Lancet Neurol, 2013, 12(8): 822-838. DOI: 10.1016/S1474-4422(13)70124-8.
[8]
DUERING M, BIESSELS G J, BRODTMANN A, et al. Neuroimaging standards for research into small vessel disease-advances since 2013[J]. Lancet Neurol, 2023, 22(7): 602-618. DOI: 10.1016/S1474-4422(23)00131-X.
[9]
CHEN X Q, LUO Y F, SUN W B, et al. Predictive value of increased cerebral deep medullary vein on the severity of small cerebrovascular disease[J]. Chin J Clin Neurosci, 2022, 30(1): 30-38.
[10]
YIN X Y, HAN Y, CAO X, et al. Association of deep medullary veins with the neuroimaging burden of cerebral small vessel disease[J]. Quant Imaging Med Surg, 2023, 13(1): 27-36. DOI: 10.21037/qims-22-264.
[11]
GARCÍA-REVILLA J, RUIZ R, ESPINOSA-OLIVA A M, et al. Dopaminergic neurons lacking Caspase-3 avoid apoptosis but undergo necrosis after MPTP treatment inducing a Galectin-3-dependent selective microglial phagocytic response[J/OL]. Cell Death Dis, 2024, 15(8): 625 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/39223107/. DOI: 10.1038/s41419-024-07014-9.
[12]
SU J H, WOLFF L, VAN ES A C G M, et al. Automatic collateral scoring from 3D CTA images[J]. IEEE Trans Med Imag, 2020, 39(6): 2190-2200. DOI: 10.1109/TMI.2020.2966921.
[13]
SHAHID S, WALI A, IFTIKHAR S, et al. Computational imaging for rapid detection of grade-I cerebral small vessel disease (cSVD)[J/OL]. Heliyon, 2024, 10(18): e37743 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/39309774/. DOI: 10.1016/j.heliyon.2024.e37743.
[14]
WARDLAW J M, SMITH C, DICHGANS M. Small vessel disease: mechanisms and clinical implications[J]. Lancet Neurol, 2019, 18(7): 684-696. DOI: 10.1016/S1474-4422(19)30079-1.
[15]
POIRIER J, DEROUESNÉ C. The concept of cerebral lacunae from 1838 to the present[J]. Rev Neurol (Paris), 1985, 141(1): 3-17.
[16]
HACHINSKI V C, POTTER P, MERSKEY H. Leuko-araiosis[J]. Arch Neurol, 1987, 44(1): 21-23. DOI: 10.1001/archneur.1987.00520130013009.
[17]
LI X L, LIU X H, CAO D N, et al. MRI research progress of white matter lesions and related vascular cognitive impairment[J]. Chin J Magn Reson Imag, 2021, 12(7): 98-101. DOI: 10.12015/issn.1674-8034.2021.07.025.
[18]
RAMIREZ J, BEREZUK C, MCNEELY A A, et al. Imaging the perivascular space as a potential biomarker of neurovascular and neurodegenerative diseases[J]. Cell Mol Neurobiol, 2016, 36(2): 289-299. DOI: 10.1007/s10571-016-0343-6.
[19]
GROESCHEL S, CHONG W K, SURTEES R, et al. Virchow-Robin spaces on magnetic resonance images: normative data, their dilatation, and a review of the literature[J]. Neuroradiology, 2006, 48(10): 745-754. DOI: 10.1007/s00234-006-0112-1.
[20]
HALLER S, VERNOOIJ M W, KUIJER J P A, et al. Cerebral microbleeds: imaging and clinical significance[J]. Radiology, 2018, 287(1): 11-28. DOI: 10.1148/radiol.2018170803.
[21]
BEAMAN C, KOZII K, HILAL S, et al. Cerebral microbleeds, cerebral amyloid angiopathy, and their relationships to quantitative markers of neurodegeneration[J/OL]. Neurology, 2022, 98(16): e1605-e1616 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/35228332/. DOI: 10.1212/WNL.0000000000200142.
[22]
KEITH J, GAO F Q, NOOR R, et al. Collagenosis of the deep medullary veins: an underrecognized pathologic correlate of white matter hyperintensities and periventricular infarction?[J]. J Neuropathol Exp Neurol, 2017, 76(4): 299-312. DOI: 10.1093/jnen/nlx009.
[23]
WANG X Y, LYU J H, DUAN Q, et al. Deep medullary vein damage correlates with small vessel disease in small vessel occlusion acute ischemic stroke[J]. Eur Radiol, 2024, 34(9): 6026-6035. DOI: 10.1007/s00330-024-10628-4.
[24]
ZHOU Y, LI Q Q, ZHANG R T, et al. Role of deep medullary veins in pathogenesis of lacunes: Longitudinal observations from the CIRCLE study[J]. J Cereb Blood Flow Metab, 2020, 40(9): 1797-1805. DOI: 10.1177/0271678X19882918.
[25]
HUANG P Y, ZHANG R T, JIAERKEN Y, et al. Deep white matter hyperintensity is associated with the dilation of perivascular space[J]. J Cereb Blood Flow Metab, 2021, 41(9): 2370-2380. DOI: 10.1177/0271678X211002279.
[26]
ZHANG R T, HUANG P Y, JIAERKEN Y, et al. Venous disruption affects white matter integrity through increased interstitial fluid in cerebral small vessel disease[J]. J Cereb Blood Flow Metab, 2021, 41(1): 157-165. DOI: 10.1177/0271678X20904840.
[27]
YAN S Q, WAN J P, ZHANG X T, et al. Increased visibility of deep medullary veins in leukoaraiosis: a 3-T MRI study[J/OL]. Front Aging Neurosci, 2014, 6: 144 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/25071553/. DOI: 10.3389/fnagi.2014.00144.
[28]
LAN H Y, QIU W W, LEI X J, et al. Deep medullary vein abnormalities impact white matter hyperintensity volume through increases in interstitial free water[J/OL]. BMC Neurol, 2024, 24(1): 405 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/39433983/. DOI: 10.1186/s12883-024-03921-8.
[29]
KALHEIM L F, BJØRNERUD A, FLADBY T, et al. White matter hyperintensity microstructure in amyloid dysmetabolism[J]. J Cereb Blood Flow Metab, 2017, 37(1): 356-365. DOI: 10.1177/0271678X15627465.
[30]
MOLINUEVO J L, RIPOLLES P, SIMÓ M, et al. White matter changes in preclinical Alzheimer's disease: a magnetic resonance imaging-diffusion tensor imaging study on cognitively normal older people with positive amyloid β protein 42 levels[J]. Neurobiol Aging, 2014, 35(12): 2671-2680. DOI: 10.1016/j.neurobiolaging.2014.05.027.
[31]
ILIFF J J, WANG M H, LIAO Y H, et al. A paravascular pathway facilitates CSF flow through the brain parenchyma and the clearance of interstitial solutes, including amyloid β[J/OL]. Sci Transl Med, 2012, 4(147): 147ra111 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/22896675/. DOI: 10.1126/scitranslmed.3003748.
[32]
SHA J Y, CAI L L, ZHAO H L, et al. Function evaluation of glial lymphatic system in cerebral hemorrhage based on diffusion tensor imaging Albers index [J]. Journal of Practical Radiology, 2019, 40(5): 845-847. DOI: 10.3969/j.issn.1002-1671.2024.05.001.
[33]
ZHANG K M, ZHOU Y, ZHANG W H, et al. MRI-visible perivascular spaces in basal Ganglia but not centrum semiovale or hippocampus were related to deep medullary veins changes[J]. J Cereb Blood Flow Metab, 2022, 42(1): 136-144. DOI: 10.1177/0271678X211038138.
[34]
ZHANG X, PEI X, SHI Y, et al. Unveiling connections between venous disruption and cerebral small vessel disease using diffusion tensor image analysis along perivascular space (DTI-ALPS): a 7-T MRI study[J]. Int J Stroke, 2025, 20(4): 497-506. DOI: 10.1177/17474930241293966.
[35]
CHEN X D, WEI L, WANG J H, et al. Decreased visible deep medullary veins is a novel imaging marker for cerebral small vessel disease[J]. Neurol Sci, 2020, 41(6): 1497-1506. DOI: 10.1007/s10072-019-04203-9.
[36]
ZHANG R T, LI Q Q, ZHOU Y, et al. The relationship between deep medullary veins score and the severity and distribution of intracranial microbleeds[J/OL]. Neuroimage Clin, 2019, 23: 101830 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/31039526/. DOI: 10.1016/j.nicl.2019.101830.
[37]
WANG D, XIANG Y Y, PENG Y L, et al. Deep medullary vein and MRI markers were related to cerebral hemorrhage subtypes[J/OL]. Brain Sci, 2023, 13(9): 1315 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/37759916/. DOI: 10.3390/brainsci13091315.
[38]
WANG Y B, CATINDIG J A, HILAL S, et al. Multi-stage segmentation of white matter hyperintensity, cortical and lacunar infarcts[J]. Neuroimage, 2012, 60(4): 2379-2388. DOI: 10.1016/j.neuroimage.2012.02.034.
[39]
UCHIYAMA Y, KUNIEDA T, ASANO T, et al. Computer-aided diagnosis scheme for classification of lacunar infarcts and enlarged Virchow-Robin spaces in brain MR images[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2008, 2008: 3908-3911. DOI: 10.1109/IEMBS.2008.4650064.
[40]
GHAFOORIAN M, KARSSEMEIJER N, HESKES T, et al. Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin[J/OL]. Neuroimage Clin, 2017, 14: 391-399 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/28271039/. DOI: 10.1016/j.nicl.2017.01.033.
[41]
WANG S Y, HUANG P Y, ZHANG R T, et al. Quantity and morphology of perivascular spaces: associations with vascular risk factors and cerebral small vessel disease[J]. J Magn Reson Imaging, 2021, 54(4): 1326-1336. DOI: 10.1002/jmri.27702.
[42]
HE K M, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[J]. IEEE Trans Pattern Anal Mach Intell, 2020, 42(2): 386-397. DOI: 10.1109/TPAMI.2018.2844175.
[43]
BOUTINAUD P, TSUCHIDA A, LAURENT A, et al. 3D segmentation of perivascular spaces on T1-weighted 3 tesla MR images with a convolutional autoencoder and a U-shaped neural network[J/OL]. Front Neuroinform, 2021, 15: 641600 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/34262443/. DOI: 10.3389/fninf.2021.641600.
[44]
DUBOST F, ADAMS H, YILMAZ P, et al. Weakly supervised object detection with 2D and 3D regression neural networks[J/OL]. Med Image Anal, 2020, 65: 101767 [2025-03-11]. https://www.researchgate.net/publication/333640388_Weakly_Supervised_Object_Detection_with_2D_and_3D_Regression_Neural_Networks. DOI: 10.1016/j.media.2020.101767.
[45]
LIU L M, CHEN J Y, XIONG J. Recent advance in role of cerebral microvascular lesions in type 2 diabetes mellitus-associated cognitive impairment[J]. Chin J Neuromed, 2024, 23(1): 83-88. DOI: 10.3760/cma.j.cn115354-20230803-00043.
[46]
LI J Z, ZHANG L J, FENG J, et al. The correlation between the number and location distribution of cerebral microbleeds and imaging of cerebral small vessel disease[J]. Chin J Magn Reson Imag, 2023, 14(10): 46-52. DOI: 10.12015/ISn.1674-8034.2023.10.009.
[47]
RASHID T, ABDULKADIR A, NASRALLAH I M, et al. DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI[J/OL]. Sci Rep, 2021, 11(1): 14124 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/34238951/. DOI: 10.1038/s41598-021-93427-x.
[48]
DUAN Y Y, SHAN W, LIU L Y, et al. Primary categorizing and masking cerebral small vessel disease based on "deep learning system"[J/OL]. Front Neuroinform, 2020, 14: 17 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/32523523/. DOI: 10.3389/fninf.2020.00017.
[49]
ZHANG Y D, ZHANG Y, HOU X X, et al. Seven-layer deep neural network based on sparse autoencoder for voxelwise detection of cerebral microbleed[J]. Multimed Tools Appl, 2018, 77(9): 10521-10538. DOI: 10.1007/s11042-017-4554-8.
[50]
XIA Y W, SHEN Y, WANG Y, et al. White matter hyperintensities associated with progression of cerebral small vessel disease: a 7-year Chinese urban community study[J]. Aging (Albany NY), 2020, 12(9): 8506-8522. DOI: 10.18632/aging.103154.
[51]
ULIVI L, KANBER B, PRADOS F, et al. White matter integrity correlates with cognition and disease severity in Fabry disease[J]. Brain, 2020, 143(11): 3331-3342. DOI: 10.1093/brain/awaa282.
[52]
MOESKOPS P, DE BRESSER J, KUIJF H J, et al. Evaluation of a deep learning approach for the segmentation of brain tissues and white matter hyperintensities of presumed vascular origin in MRI[J/OL]. Neuroimage Clin, 2017, 17: 251-262 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/29159042/. DOI: 10.1016/j.nicl.2017.10.007.
[53]
MOESKOPS P, VIERGEVER M A, MENDRIK A M, et al. Automatic segmentation of MR brain images with a convolutional neural network[J]. IEEE Trans Med Imaging, 2016, 35(5): 1252-1261. DOI: 10.1109/TMI.2016.2548501.
[54]
LI H W, JIANG G F, ZHANG J G, et al. Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images[J]. NeuroImage, 2018, 183: 650-665. DOI: 10.1016/j.neuroimage.2018.07.005.
[55]
LIU L L, CHEN S W, ZHU X F, et al. Deep convolutional neural network for accurate segmentation and quantification of white matter hyperintensities[J]. Neurocomputing, 2020, 384: 231-242. DOI: 10.1016/j.neucom.2019.12.050.
[56]
RACHMADI M F, VALDÉS-HERNÁNDEZ M D C, MAKIN S, et al. Automatic spatial estimation of white matter hyperintensities evolution in brain MRI using disease evolution predictor deep neural networks[J/OL]. Med Image Anal, 2020, 63: 101712 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/32428823/. DOI: 10.1016/j.media.2020.101712.
[57]
GIBSON E, RAMIREZ J, WOODS L A, et al. segcsvdWMH: a convolutional neural network-based tool for quantifying white matter hyperintensities in heterogeneous patient cohorts[J/OL]. Hum Brain Mapp, 2024, 45(18): e70104 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/39723488/. DOI: 10.1002/hbm.70104.
[58]
LIN G H, CHEN W Y, GENG Y K, et al. A multimodal MRI-based machine learning framework for classifying cognitive impairment in cerebral small vessel disease[J/OL]. Sci Rep, 2025, 15(1): 13112 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/40240809/. DOI: 10.1038/s41598-025-97552-9.
[59]
SONG Y, ZHOU X, ZHAO H, et al. Characterizing the role of the microbiota-gut-brain axis in cerebral small vessel disease: an integrative multi-omics study[J/OL]. Neuroimage, 2024, 303: 120918 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/39505226/. DOI: 10.1016/j.neuroimage.2024.120918.

PREV Research progress of MRI in blood-brain barrier injury associated with acute ischemic stroke
NEXT Research progress on imaging-based prediction of recurrent risk after thrombectomy in ischemic stroke
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn