Graph confidence intercalibration network for intracranial aneurysm lesion instance segmentation in DSA

doi:10.1016/j.displa.2024.102929

	Graph confidence intercalibration network for intracranial aneurysm lesion instance segmentation in DSA
	Ye, Haili 1,2; Mo, Yancheng 1,2; Tang, Chen 3,4; Liao, Mingqian 1,2; Zhang, Xiaoqing 1,2,5,6; Dai, Limeng 7; Li, Baihua 8; Liu, Jiang 1,2,3,4
	2025-04-01
发表期刊	DISPLAYS
ISSN	0141-9382
卷号	87 页码:12
摘要	Intracranial aneurysm (IA) lesion segmentation is significant for its treatment and prognosis. Although exiting deep network-based instance methods have good IA lesion segmentation results based on digital subtraction angiography (DSA) images, they still face great challenges with instance confidence bias and imprecise boundary segmentation, which may negatively affect IA diagnosis. To tackle these problems, this paper proposes a novel graph confidence intercalibration network (GCINet) to automatically segment IA lesions from DSA images. To be specific, we design a graph confidence intercalibration (GCI) module to mitigate instance confidence bias by dynamically adjusting their confidence distributions. At the same time, we propose an edge space perception (ESP) module to correct ambiguous segmentation boundaries. Extensive experiments on a clinical IA-DSA and a publicly available LiTS dataset demonstrate that our GCINet outperforms state-of-the-art methods. Additionally, visual analysis and ablation studies are provided to verify the effectiveness of each module in GCINet.
关键词	Intracranial aneurysm Instance segmentation Graph confidence intercalibration Edge space perception module DSA image
DOI	10.1016/j.displa.2024.102929
收录类别	SCI
语种	英语
资助项目	Leading Goose Program of Zhejiang[2023C03079] ; General Program of National Natural Science Foundation of China[82272086]
WOS研究方向	Computer Science ; Engineering ; Instruments & Instrumentation ; Optics
WOS类目	Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic ; Instruments & Instrumentation ; Optics
WOS记录号	WOS:001390999400001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40777
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Xiaoqing; Liu, Jiang
作者单位	1.Southern Univ Sci & Technol, Res Inst Trustworthy Autonomous Syst, Shenzhen 518055, Peoples R China 2.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen 518055, Peoples R China 3.Wenzhou Med Univ, Sch Ophthalmol & Optometry, Wenzhou 325027, Peoples R China 4.Wenzhou Med Univ, Eye Hosp, Wenzhou 325027, Peoples R China 5.Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr High Performance Comp, Shenzhen 518055, Peoples R China 6.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab Intelligent Bioinformat, Shenzhen 518055, Peoples R China 7.Shenzhen Peoples Hosp, Neurosurg Dept, Shenzhen 518020, Peoples R China 8.Loughborough Univ, Dept Comp Sci, Loughborough LE11 3TU, England
推荐引用方式 GB/T 7714	Ye, Haili,Mo, Yancheng,Tang, Chen,et al. Graph confidence intercalibration network for intracranial aneurysm lesion instance segmentation in DSA[J]. DISPLAYS,2025,87:12.
APA	Ye, Haili.,Mo, Yancheng.,Tang, Chen.,Liao, Mingqian.,Zhang, Xiaoqing.,...&Liu, Jiang.(2025).Graph confidence intercalibration network for intracranial aneurysm lesion instance segmentation in DSA.DISPLAYS,87,12.
MLA	Ye, Haili,et al."Graph confidence intercalibration network for intracranial aneurysm lesion instance segmentation in DSA".DISPLAYS 87(2025):12.