Diagnosis and Subtyping of Autoimmune Encephalitis Using an Attention-Based Multi-Instance Learning Model: A Multi-Center <SUP>18</SUP>F-FDG PET Study

doi:10.1111/cns.70513

	Diagnosis and Subtyping of Autoimmune Encephalitis Using an Attention-Based Multi-Instance Learning Model: A Multi-Center ¹⁸F-FDG PET Study
	Sun, Yueqian 1; Sun, Ruizhe 2; Lv, Jiahua 3; Kong, Qingxia 4; Dai, Cixiang 5; Wang, Bin 6; Han, Xiong 6; Chen, Min 7; Liu, Ruihan 8; Jiang, Yan 7; Yuan, Leilei 9; Ai, Lin 9; Yang, Xiaodong 2; Chen, Yiqiang 2; Wang, Qun 1,7,10
	2025-08-04
发表期刊	CNS NEUROSCIENCE & THERAPEUTICS
ISSN	1755-5930
卷号	31 期号:8 页码:11
摘要	Background: The aim was to develop an attention-based model using F-18-fluorodeoxyglucose (F-18-FDG) PET imaging to differentiate autoimmune encephalitis (AE) patients from controls and to discriminate among different AE subtypes. Methods: This multi-center retrospective study enrolled 390 participants: 222 definite AE patients (comprising four subtypes: LGI1-AE, NMDAR-AE, GABAB-AE, GAD65-AE), 122 age- and sex-matched healthy controls, and 33 age- and sex-matched antibody-negative AE patients along with 13 age- and sex-matched viral encephalitis patients, both serving as disease controls. An attention-based multi-instance learning (MIL) model was trained using data from one hospital and underwent external validation with data from other institutions. Additionally, a multi-modal MIL (m-MIL) model integrating imaging features, age, and sex parameters was evaluated alongside logistic regression (LR) and random forest (RF) models for comparative analysis. Results: The attention-based m-MIL model outperformed classical algorithms (LR, RF) and single-modal MIL in AE vs. all controls binary classification, achieving the highest accuracy (84.00% internal, 67.38% external) and sensitivity (90.91% internal, 71.19% external). For multiclass AE subtype classification, the MIL-based model achieved 95.05% (internal) and 77.97% (external) accuracy. Heatmap analysis revealed that NMDAR-AE involved broader brain regions, including the medial temporal lobe (MTL) and basal ganglia (BG), whereas LGI1-AE and GABAB-AE showed focal attention on the MTL and BG. In contrast, GAD65-AE demonstrated concentrated attention exclusively in the MTL. Conclusion: The m-MIL model effectively discriminates AE patients from controls and enables subtyping of different AE subtypes, offering a valuable diagnostic tool for the clinical assessment and classification of AE.
关键词	F-18-FDG PET attention-based autoimmune encephalitis multi-instance learning
DOI	10.1111/cns.70513
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation
WOS研究方向	Neurosciences & Neurology ; Pharmacology & Pharmacy
WOS类目	Neurosciences ; Pharmacology & Pharmacy
WOS记录号	WOS:001543951800001
出版者	WILEY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41997
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Yiqiang; Wang, Qun
作者单位	1.Capital Med Univ, Beijing Tiantan Hosp, Dept Neurol, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 3.Jining Med Univ, Clin Med Coll, Jining, Peoples R China 4.Jining Med Univ, Affiliated Hosp, Dept Neurol, Jining, Peoples R China 5.Hebei Yanda Hosp, Dept Neurol, Sanhe, Peoples R China 6.Peoples Hosp Henan, Dept Neurol, Zhengzhou, Peoples R China 7.Zhengzhou Univ, Affiliated Hosp 1, Dept Neurol, Zhengzhou, Peoples R China 8.Cent South Univ, Dept Neurol, Xiangya Hosp, Changsha, Peoples R China 9.Capital Med Univ, Beijing Tiantan Hosp, Dept Nucl Med, Beijing, Peoples R China 10.Natl Ctr Clin Med Neurol Dis, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Sun, Yueqian,Sun, Ruizhe,Lv, Jiahua,et al. Diagnosis and Subtyping of Autoimmune Encephalitis Using an Attention-Based Multi-Instance Learning Model: A Multi-Center ¹⁸F-FDG PET Study[J]. CNS NEUROSCIENCE & THERAPEUTICS,2025,31(8):11.
APA	Sun, Yueqian.,Sun, Ruizhe.,Lv, Jiahua.,Kong, Qingxia.,Dai, Cixiang.,...&Wang, Qun.(2025).Diagnosis and Subtyping of Autoimmune Encephalitis Using an Attention-Based Multi-Instance Learning Model: A Multi-Center ¹⁸F-FDG PET Study.CNS NEUROSCIENCE & THERAPEUTICS,31(8),11.
MLA	Sun, Yueqian,et al."Diagnosis and Subtyping of Autoimmune Encephalitis Using an Attention-Based Multi-Instance Learning Model: A Multi-Center ¹⁸F-FDG PET Study".CNS NEUROSCIENCE & THERAPEUTICS 31.8(2025):11.