Background: The accurate segmentation, labeling and quantification of cerebral blood vessels on MR imaging is important for basic and clinical research, yet results are not generalizable, and often require user intervention. New methods are needed to automate this process.
Purpose: To automatically segment, label and quantify Circle of Willis (CW) arteries on Magnetic Resonance Angiography images using deep convolutional neural networks.
Materials And Methods: MRA images were pooled from three public and private databases. A total of 116 subjects (mean age 56 years ± 21 [standard deviation]; 72 women) were used to make up the training set (N=101) and the testing set (N=15). In each image, fourteen arterial segments making up or surrounding the CW were manually annotated and validated by a clinical expert. Convolutional neural network (CNN) models were trained on a training set to be finally combined in an ensemble to develop eICAB. Model performances were evaluated using (1) quantitative analysis (dice score on test set) and (2) qualitative analysis (external datasets, N=121). The reliability was assessed using multiple MRAs of healthy participants (ICC of vessel diameters and volumes on test-retest).
Results: Qualitative analysis showed that eICAB correctly predicted the large, medium and small arteries in 99±0.4%, 97±1% and 88±7% of all images, respectively. For quantitative assessment, the average dice score coefficients for the large (ICAs, BA), medium (ACAs, MCAs, PCAs-P2), and small (AComm, PComm, PCAs-P1) vessels were 0.76±0.07, 0.76±0.08 and 0.41±0.27, respectively. These results were similar and, in some cases, statistically better (p<0.05) than inter-expert annotation variability and robust to image SNR. Finally, test-retest analysis showed that the model yielded high diameter and volume reliability (ICC=0.99).
Conclusion: We have developed a quick and reliable open-source CNN-based method capable of accurately segmenting and labeling the CW in MRA images. This method is largely independent of image quality. In the future, we foresee this approach as a critical step towards fully automated analysis of MRA databases in basic and clinical research.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neuroimage.2022.119425 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Prognostic analysis of endovascular mechanical thrombectomy in stroke patients with acute internal carotid artery obstruction based on circle of Willis variation.
Front Neurol
January 2025
Department of Neurosurgery, Shaoxing People's Hospital, Shaoxing, China.
Objective: Endovascular mechanical thrombectomy (EVMT) is widely employed in patients with acute intracranial carotid artery occlusion (AIICAO). This study aimed to predict the outcomes of EVMT following AIICAO by utilizing anatomic classification of the circle of Willis and its relative position to the thrombus.
Methods: In this study, we retrospectively analyzed a cohort of 108 patients with AIICAO who underwent endovascular mechanical thrombectomy (EVMT) at Shaoxing People's Hospital.
Impact of A1 segment asymmetry on hemodynamic conditions around the circle of Willis and anterior communicating artery aneurysm formation.
Front Neurol
January 2025
Department of Neurology, Ajou University School of Medicine, Suwon, Republic of Korea.
Background: This study aims to investigate how A1 segment asymmetry-also known as A1 dominancy-influences the development of the anterior communicating artery aneurysm (AcomA) as it affects hemodynamic conditions within the circle of Willis (COW). Using time-of-flight magnetic resonance angiography (TOF-MRA), the research introduces a novel approach to assessing shear stress in A1 segments to uncover the hemodynamic factors contributing to AcomA formation.
Method: An observational study was conducted over 6 years at a tertiary university hospital's outpatient clinic.
Endovascular versus Best Medical Treatment for Acute Carotid Occlusion BelOw Circle of Willis (ACOBOW): The ACOBOW Study.
Radiology
January 2025
From the Dept of Diagnostic and Interventional Neuroradiology, Univ Medical Ctr Hamburg-Eppendorf, Martinistrasse 52, 20246 Hamburg, Germany (L.M., G.B., P.S., J.F., C.P.S.); Dept of Diagnostic and Interventional Neuroradiology, Hosp Bremen-Mitte, Bremen, Germany (M.A., P.P.); Interventional Neuroradiology Section, Dept of Radiology, Donostia Univ Hosp, Donostia-San Sebastián, Spain (Á.L., J.Á.L.); Clinic for Radiology, Section for Interventional Radiology, Univ of Münster and Univ Hosp Münster, Münster, Germany (W.S., H.K., C.P.S.); Dept of Neuroradiology, Westpfalz-Klinikum, Kaiserslautern, Germany (W.N.); Dept of Neuroradiology, Otto-von-Guericke-Universitätsklinikum Magdeburg, Magdeburg, Germany (D.B., M.T.); Inst for Diagnostic and Interventional Radiology and Neuroradiology, Univ Hosp Essen, Essen, Germany (H.S., C.D.); Dept of Neuroradiology, Univ of Cologne, Cologne, Germany (C.K., C.Z.); Dept of Neuroradiology, Univ Hosp Aachen, Aachen, Germany (C.W., M. Möhlenbruch); Dept of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical Univ Munich, Munich, Germany (M.R.H.P., C.M.); Inst of Neuroradiology, Univ Hosps, LMU Munich, Munich, Germany (H.Z.); Dept of Diagnostic and Interventional Neuroradiology, Univ Medical Ctr Goettingen, Goettingen, Germany (M. Ernst, A.J.); Interventional Neuroradiology, Dept of Radiology, Hosp Clínico San Carlos, Madrid, Spain (M.M.G., C.P.G.); Dept of Neuroradiology, Hosp Universitario La Paz, Madrid, Spain (P.N., A.F.P.); Div of Neurology, Dept of Medicine (L.Y., B.T.), and Div of Interventional Radiology, Dept of Diagnostic Imaging (A.G.), National Univ Health System, Singapore; Yong Loo Lin School of Medicine, National Univ of Singapore, Singapore (L.Y., B.T., A.G.); Inst of Neuroradiology, Charité Universitätsmedizin Berlin, Berlin, Germany (E.S., M. Miszczuk); Dept of Neuroradiology, Clinic and Policlinic of Radiology, Univ Hosp Halle/Saale, Halle, Germany (S.S.); Dept of Radiology and Neuroradiology, Stadtspital Zürich, Zürich, Switzerland (P.S.); Dept of Diagnostic and Interventional Neuroradiology, Univ Hosp Basel, Basel, Switzerland (P.S., M.P.); Depts of Interventional Neuroradiology (J.Z.P.) and Neurology (G.P.), Hosp Clínico Universitario Virgen de la Arrixaca, Murcia, Spain; Dept of Neuroradiology, Karolinska Univ Hosp and Dept of Clinical Neuroscience, Karolinska Inst, Stockholm, Sweden (F.A., T.A.); Dept of Medical Imaging, AZ Groeninge, Kortrijk, Belgium (T.A.); Dept of Radiology, Comenius Univ's Jessenius Faculty of Medicine and Univ Hosp, Martin, Slovakia (K.Z.); Dept of Radiology, Aretaieion Univ Hosp, National and Kapodistrian Univ of Athens, Athens, Greece (P.P.); Dept of Neuroradiology, Univ Hosp Marburg, Marburg, Germany (A.K.); Dept of Neuroradiology, Univ Hosp of Bonn, Bonn, Germany (F.D.); and Dept of Neuroradiology, Alfried Krupp Krankenhaus, Essen, Germany (M. Elsharkawy).
Background Symptomatic acute occlusions of the internal carotid artery (ICA) below the circle of Willis can cause a variety of stroke symptoms, even if the major intracranial cerebral arteries remain patent; however, outcome and safety data are limited. Purpose To compare treatment effects and procedural safety of endovascular treatment (EVT) and best medical treatment (BMT) in patients with symptomatic acute occlusions of the ICA below the circle of Willis. Materials and Methods This retrospective, multicenter cohort study from 22 comprehensive stroke centers in Europe and Asia includes patients treated between January 1, 2008, and December 31, 2022.
View Article and Find Full Text PDFSex-specific anatomical variation of circle of Willis arteries.
Neuroimage
January 2025
Department of Neurology and Neurosurgery, University Medical Center Utrecht Brain Center, University Medical Center Utrecht, Utrecht University, the Netherlands. Electronic address:
Background: Anatomical variations in the circle of Willis (CoW) arteries are common and can affect hemodynamic stress, thereby influencing the risk of cerebrovascular pathology. Previous studies have suggested sex differences in CoW anatomy, but findings vary due to limited study population size and different measurement methods. This study aims to investigate sex differences in artery diameters, anatomical variants and bifurcation angles of the CoW using a large population cohort and semi-automatic measurements.
View Article and Find Full Text PDFPhoenixin-14 inhibits the formation of cerebral aneurysms in rats by downregulating the p38/NF-κB signaling pathway.
Neuropeptides
December 2024
Department of Neurology, Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, Sichuan 610072, China. Electronic address:
Cerebral aneurysms (CA) are a serious condition characterized by the bulging of a blood vessel in the brain, which can lead to rupture and life-threatening bleeding. The pathophysiology of CA involves complex processes, particularly inflammation and macrophage infiltration. Phoenixin-14 (PNX-14) is a neuropeptide with diverse biological effects, including roles in reproduction, energy homeostasis, and inflammation.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!