1
|
Liu W, Tian T, Wang L, Xu W, Li L, Li H, Zhao W, Tian S, Pan X, Deng Y, Gao F, Yang H, Wang X, Su R. DIAS: A dataset and benchmark for intracranial artery segmentation in DSA sequences. Med Image Anal 2024; 97:103247. [PMID: 38941857 DOI: 10.1016/j.media.2024.103247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Revised: 05/31/2024] [Accepted: 06/17/2024] [Indexed: 06/30/2024]
Abstract
The automated segmentation of Intracranial Arteries (IA) in Digital Subtraction Angiography (DSA) plays a crucial role in the quantification of vascular morphology, significantly contributing to computer-assisted stroke research and clinical practice. Current research primarily focuses on the segmentation of single-frame DSA using proprietary datasets. However, these methods face challenges due to the inherent limitation of single-frame DSA, which only partially displays vascular contrast, thereby hindering accurate vascular structure representation. In this work, we introduce DIAS, a dataset specifically developed for IA segmentation in DSA sequences. We establish a comprehensive benchmark for evaluating DIAS, covering full, weak, and semi-supervised segmentation methods. Specifically, we propose the vessel sequence segmentation network, in which the sequence feature extraction module effectively captures spatiotemporal representations of intravascular contrast, achieving intracranial artery segmentation in 2D+Time DSA sequences. For weakly-supervised IA segmentation, we propose a novel scribble learning-based image segmentation framework, which, under the guidance of scribble labels, employs cross pseudo-supervision and consistency regularization to improve the performance of the segmentation network. Furthermore, we introduce the random patch-based self-training framework, aimed at alleviating the performance constraints encountered in IA segmentation due to the limited availability of annotated DSA data. Our extensive experiments on the DIAS dataset demonstrate the effectiveness of these methods as potential baselines for future research and clinical applications. The dataset and code are publicly available at https://doi.org/10.5281/zenodo.11401368 and https://github.com/lseventeen/DIAS.
Collapse
Affiliation(s)
- Wentao Liu
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China.
| | - Tong Tian
- State Key Laboratory of Structural Analysis, Optimization and CAE Software for Industrial Equipment, School of Mechanics and Aerospace Engineering, Dalian University of Technology, Dalian, China
| | - Lemeng Wang
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
| | - Weijin Xu
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
| | - Lei Li
- Department of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Haoyuan Li
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
| | - Wenyi Zhao
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
| | - Siyu Tian
- Ultrasonic Department, The Fourth Hospital of Hebei Medical University and Hebei Tumor Hospital, Shijiazhuang, China
| | - Xipeng Pan
- School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China
| | - Yiming Deng
- Department of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Feng Gao
- Department of Interventional Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
| | - Huihua Yang
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China; School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China.
| | - Xin Wang
- Department of Radiology, The Netherlands Cancer Institute, Amsterdam, The Netherlands
| | - Ruisheng Su
- Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands; Medical Image Analysis group, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
| |
Collapse
|
2
|
Li F, Wang Y, Hu T, Wu Y. Application and interpretation of vessel wall magnetic resonance imaging for intracranial atherosclerosis: a narrative review. ANNALS OF TRANSLATIONAL MEDICINE 2022; 10:714. [PMID: 35845481 PMCID: PMC9279807 DOI: 10.21037/atm-22-2364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/13/2022] [Accepted: 06/01/2022] [Indexed: 11/06/2022]
Abstract
Background and Objective Atherosclerosis is a systemic disease that occurs in the arteries, and it is the most important causative factor of ischemic stroke. Vessel wall magnetic resonance imaging (VWMRI) is one of the best non-invasive methods for displaying the vascular features of intracranial atherosclerosis. The main clinical applications of this technique include the exploration of the pathogenesis of intracranial atherosclerotic lesions, follow-up monitoring, and treatment prognosis judgment. As the demand for intracranial VWMRI increases in clinical practice, radiologists should be aware of the selection of imaging parameters and how they affect image quality, clinical indications, evaluation methods, and limitations in interpreting these images. Therefore, this review focused on describing how to perform and interpret VWMRI of intracranial atherosclerotic lesions. Methods We searched the studies on the application of VWMRI in the PubMed database from January 1, 2000 to March 31, 2022, and focused on the analysis of related studies on VWMRI in atherosclerotic lesions, including technical application, expert consensus, imaging characteristics, and the clinical significance of intracranial atherosclerotic lesions. Key Content and Findings We reviewed and summarized recent advances in the clinical application of VWMRI in atherosclerotic diseases. Currently accepted principles and expert consensus recommendations for intracranial VWMRI include high spatial resolution, multiplanar two and three-dimensional imaging, multiple tissue-weighted sequences, and blood and cerebrospinal fluid suppression. Understanding the characteristics of VWMRI of normal intracranial arteries is the basis for interpreting VWMRI of atherosclerotic lesions. Evaluating VWMRI imaging features of intracranial atherosclerotic lesions includes plaque morphological and enhancement characteristics. The evaluation of atherosclerotic plaque stability is the highlight of VWMRI. Conclusions VWMRI has a wide range of clinical applications and can address important clinical questions and provide critical information for treatment decisions. VWMRI plays a key role in the comprehensive evaluation and prevention of intracranial atherosclerosis. However, intracranial VWMRI is still unable to obtain in vivo plaque pathological specimens for imaging—pathological comparison is the most significant limitation of this technique. Further technical improvements are expected to reduce acquisition time and may ultimately contribute to a better understanding of the underlying pathology of lesions on VWMRI.
Collapse
Affiliation(s)
- Fangbing Li
- Department of Radiology, Fourth Affiliated Hospital of China Medical University, Shenyang, China
| | - Yilin Wang
- Department of Radiology, Fourth Affiliated Hospital of China Medical University, Shenyang, China
| | - Tianxiang Hu
- Department of Radiology, Fourth Affiliated Hospital of China Medical University, Shenyang, China
| | - Yejun Wu
- Department of Radiology, Fourth Affiliated Hospital of China Medical University, Shenyang, China
| |
Collapse
|
3
|
Semiautomated Segmentation and Volume Measurements of Cervical Carotid High-Signal Plaques Using 3D Turbo Spin-Echo T1-Weighted Black-Blood Vessel Wall Imaging: A Preliminary Study. Diagnostics (Basel) 2022; 12:diagnostics12041014. [PMID: 35454062 PMCID: PMC9026945 DOI: 10.3390/diagnostics12041014] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2022] [Revised: 04/11/2022] [Accepted: 04/15/2022] [Indexed: 11/24/2022] Open
Abstract
Unstable carotid plaques are visualized as high-signal plaques (HSPs) on 3D turbo spin-echo T1-weighted black-blood vessel wall imaging (3D TSE T1-BB VWI). The purpose of this study was to compare manual segmentation and semiautomated segmentation for the quantification of carotid HSPs using 3D TSE T1-BB VWI. Twenty cervical carotid plaque lesions in 19 patients with a plaque contrast ratio of > 1.3 compared to adjacent muscle were studied. Using the mean voxel value for the adjacent muscle multiplied by 1.3 as a threshold value, the semiautomated software exclusively segmented and measured the HSP volume. Manual and semiautomated HSP volumes were well correlated (r = 0.965). Regarding reproducibility, the inter-rater ICC was 0.959 (bias: 24.63, 95% limit of agreement: −96.07, 146.35) for the manual method and 0.998 (bias: 15.2, 95% limit of agreement: −17.83, 48.23) for the semiautomated method, indicating improved reproducibility by the semiautomated method compared to the manual method. The time required for semiautomated segmentation was significantly shorter than that of manual segmentation times (81.7 ± 7.8 s versus 189.5 ± 49.6 s; p < 0.01). The results obtained in this study demonstrate that the semiautomated segmentation method allows for reliable assessment of the HSP volume in patients with carotid plaque lesions, with reduced time and effort for the analysis.
Collapse
|