Self-supervised Learning for Accurately Modelling Hierarchical Evolutionary Patterns of Cerebrovasculature

Overview

Journal Nat Commun

Specialty Biology

Date 2024 Oct 25

PMID 39455566

Authors

Bin Guo

Ying Chen

Jinping Lin

Bin Huang

Xiangzhuo Bai

Chuanliang Guo

Bo Gao

Qiyong Gong

Xiangzhi Bai

Affiliations

Soon will be listed here.

Abstract

Cerebrovascular abnormalities are critical indicators of stroke and neurodegenerative diseases like Alzheimer's disease (AD). Understanding the normal evolution of brain vessels is essential for detecting early deviations and enabling timely interventions. Here, for the first time, we proposed a pipeline exploring the joint evolution of cortical volumes (CVs) and arterial volumes (AVs) in a large cohort of 2841 individuals. Using advanced deep learning for vessel segmentation, we built normative models of CVs and AVs across spatially hierarchical brain regions. We found that while AVs generally decline with age, distinct trends appear in regions like the circle of Willis. Comparing healthy individuals with those affected by AD or stroke, we identified significant reductions in both CVs and AVs, wherein patients with AD showing the most severe impact. Our findings reveal gender-specific effects and provide critical insights into how these conditions alter brain structure, potentially guiding future clinical assessments and interventions.

References

Harris J, Jolivet R, Attwell D . Synaptic energy use and supply. Neuron. 2012; 75(5):762-77. DOI: 10.1016/j.neuron.2012.08.019. View

Cole T . The development of growth references and growth charts. Ann Hum Biol. 2012; 39(5):382-94. PMC: 3920659. DOI: 10.3109/03014460.2012.694475. View

Rutherford S, Kia S, Wolfers T, Fraza C, Zabihi M, Dinga R . The normative modeling framework for computational psychiatry. Nat Protoc. 2022; 17(7):1711-1734. PMC: 7613648. DOI: 10.1038/s41596-022-00696-5. View

Liao W, Rohr K, Kang C, Cho Z, Worz S . Automatic 3D Segmentation and Quantification of Lenticulostriate Arteries from High-Resolution 7 Tesla MRA Images. IEEE Trans Image Process. 2015; 25(1):400-13. DOI: 10.1109/TIP.2015.2499085. View

Bollmann S, Mattern H, Bernier M, Robinson S, Park D, Speck O . Imaging of the pial arterial vasculature of the human brain in vivo using high-resolution 7T time-of-flight angiography. Elife. 2022; 11. PMC: 9150892. DOI: 10.7554/eLife.71186. View

Roman G, Erkinjuntti T, Wallin A, Pantoni L, Chui H . Subcortical ischaemic vascular dementia. Lancet Neurol. 2003; 1(7):426-36. DOI: 10.1016/s1474-4422(02)00190-4. View

Leemans E, Cornelissen B, Sing M, Sprengers M, van den Berg R, Roos Y . 7T versus 3T MR Angiography to Assess Unruptured Intracranial Aneurysms. J Neuroimaging. 2020; 30(6):779-785. PMC: 7754498. DOI: 10.1111/jon.12772. View

Hedman A, van Haren N, Schnack H, Kahn R, Hulshoff Pol H . Human brain changes across the life span: a review of 56 longitudinal magnetic resonance imaging studies. Hum Brain Mapp. 2011; 33(8):1987-2002. PMC: 6870052. DOI: 10.1002/hbm.21334. View

Hetts S, Yen A, Cooke D, Nelson J, Jolivalt P, Banaga J . Pial Artery Supply as an Anatomic Risk Factor for Ischemic Stroke in the Treatment of Intracranial Dural Arteriovenous Fistulas. AJNR Am J Neuroradiol. 2017; 38(12):2315-2320. PMC: 7963724. DOI: 10.3174/ajnr.A5396. View

10.

Debatin J, Hany T . MR-based assessment of vascular morphology and function. Eur Radiol. 1998; 8(4):528-39. DOI: 10.1007/s003300050429. View

11.

Tarumi T, Zhang R . Cerebral blood flow in normal aging adults: cardiovascular determinants, clinical implications, and aerobic fitness. J Neurochem. 2017; 144(5):595-608. PMC: 5874160. DOI: 10.1111/jnc.14234. View

12.

Huang S, Pareek A, Jensen M, Lungren M, Yeung S, Chaudhari A . Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ Digit Med. 2023; 6(1):74. PMC: 10131505. DOI: 10.1038/s41746-023-00811-0. View

13.

van der Grond J, de Leeuw F, de Groot J, Algra A, Hillen B, Breteler M . Circle of Willis: morphologic variation on three-dimensional time-of-flight MR angiograms. Radiology. 1998; 207(1):103-11. DOI: 10.1148/radiology.207.1.9530305. View

14.

Varga A, Di Leo G, Banga P, Csobay-Novak C, Kolossvary M, Maurovich-Horvat P . Multidetector CT angiography of the Circle of Willis: association of its variants with carotid artery disease and brain ischemia. Eur Radiol. 2018; 29(1):46-56. PMC: 6291432. DOI: 10.1007/s00330-018-5577-x. View

15.

Schomer D, Marks M, Steinberg G, Johnstone I, Boothroyd D, ROSS M . The anatomy of the posterior communicating artery as a risk factor for ischemic cerebral infarction. N Engl J Med. 1994; 330(22):1565-70. DOI: 10.1056/NEJM199406023302204. View

16.

Yang T, Sun Y, Lu Z, Leak R, Zhang F . The impact of cerebrovascular aging on vascular cognitive impairment and dementia. Ageing Res Rev. 2016; 34:15-29. PMC: 5250548. DOI: 10.1016/j.arr.2016.09.007. View

17.

Wu X, Luboz V, Krissian K, Cotin S, Dawson S . Segmentation and reconstruction of vascular structures for 3D real-time simulation. Med Image Anal. 2010; 15(1):22-34. DOI: 10.1016/j.media.2010.06.006. View

18.

Rutherford S, Fraza C, Dinga R, Kia S, Wolfers T, Zabihi M . Charting brain growth and aging at high spatial precision. Elife. 2022; 11. PMC: 8828052. DOI: 10.7554/eLife.72904. View

19.

Yan P, Kassim A . Segmentation of volumetric MRA images by using capillary active contour. Med Image Anal. 2006; 10(3):317-29. DOI: 10.1016/j.media.2005.12.002. View

20.

Todorov M, Paetzold J, Schoppe O, Tetteh G, Shit S, Efremov V . Machine learning analysis of whole mouse brain vasculature. Nat Methods. 2020; 17(4):442-449. PMC: 7591801. DOI: 10.1038/s41592-020-0792-1. View