دورية أكاديمية
CAVE: Cerebral artery-vein segmentation in digital subtraction angiography.
| العنوان: | CAVE: Cerebral artery-vein segmentation in digital subtraction angiography. |
|---|---|
| المؤلفون: | Su R; Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands. Electronic address: r.su@erasmusmc.nl., van der Sluijs PM; Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands., Chen Y; Department of Radiology & Nuclear Medicine, UMass Chan Medical School, Worcester, USA., Cornelissen S; Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands., van den Broek R; Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands., van Zwam WH; Department of Radiology & Nuclear Medicine, Maastricht UMC, Cardiovascular Research Institute Maastricht, The Netherlands., van der Lugt A; Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands., Niessen WJ; Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands; Imaging Physics, Applied Sciences, Delft University of Technology, The Netherlands., Ruijters D; Philips Healthcare, Best, The Netherlands., van Walsum T; Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands. |
| المصدر: | Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society [Comput Med Imaging Graph] 2024 Jul; Vol. 115, pp. 102392. Date of Electronic Publication: 2024 May 01. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Elsevier Science Country of Publication: United States NLM ID: 8806104 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-0771 (Electronic) Linking ISSN: 08956111 NLM ISO Abbreviation: Comput Med Imaging Graph Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: Tarrytown Ny : Elsevier Science Original Publication: New York : Pergamon Press, c1988- |
| مواضيع طبية MeSH: | Angiography, Digital Subtraction*/methods , Cerebral Veins*/diagnostic imaging , Cerebral Arteries*/diagnostic imaging, Humans ; Cerebral Angiography/methods |
| مستخلص: | Cerebral X-ray digital subtraction angiography (DSA) is a widely used imaging technique in patients with neurovascular disease, allowing for vessel and flow visualization with high spatio-temporal resolution. Automatic artery-vein segmentation in DSA plays a fundamental role in vascular analysis with quantitative biomarker extraction, facilitating a wide range of clinical applications. The widely adopted U-Net applied on static DSA frames often struggles with disentangling vessels from subtraction artifacts. Further, it falls short in effectively separating arteries and veins as it disregards the temporal perspectives inherent in DSA. To address these limitations, we propose to simultaneously leverage spatial vasculature and temporal cerebral flow characteristics to segment arteries and veins in DSA. The proposed network, coined CAVE, encodes a 2D+time DSA series using spatial modules, aggregates all the features using temporal modules, and decodes it into 2D segmentation maps. On a large multi-center clinical dataset, CAVE achieves a vessel segmentation Dice of 0.84 (±0.04) and an artery-vein segmentation Dice of 0.79 (±0.06). CAVE surpasses traditional Frangi-based k-means clustering (P < 0.001) and U-Net (P < 0.001) by a significant margin, demonstrating the advantages of harvesting spatio-temporal features. This study represents the first investigation into automatic artery-vein segmentation in DSA using deep learning. The code is publicly available at https://github.com/RuishengSu/CAVE_DSA. Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: - Danny Ruijters is an employee of Philips Healthcare. - Wiro J. Niessen is founder, scientific lead, and shareholder of Quantb B. - Aad van der Lugt has received research support from GE HealthCare, Siemens Healthineers, Philips Healthcare, Stryker, Penumbra, Cerenovus, Medtronic, and Thrombolytic Sciences inc (all paid to institution). (Copyright © 2024 The Author(s). Published by Elsevier Ltd.. All rights reserved.) |
| فهرسة مساهمة: | Keywords: Biomarkers; Brain vessels; Deep learning; RNN; Spatio-temporal; Stroke; Temporal transformer; Vessel segmentation |
| تواريخ الأحداث: | Date Created: 20240507 Date Completed: 20240601 Latest Revision: 20240601 |
| رمز التحديث: | 20240602 |
| DOI: | 10.1016/j.compmedimag.2024.102392 |
| PMID: | 38714020 |
| قاعدة البيانات: | MEDLINE |
Full Text via ClinicalKey 
Full Text Finder | تدمد: | 1879-0771 |
|---|---|
| DOI: | 10.1016/j.compmedimag.2024.102392 |