Share：
Share this content in WeChat
X
[Chinese][PDF]381
• Clinical Article •
Differential diagnosis of autoimmune encephalitis and herpes simplex virus encephalitis using radiomics models based on multimodal MRI
LIU Huan  DAI Jian  LIU Xianping  LI Yuxin  WU Hao  GENG Daoying 

Cite this article as: LIU H, DAI J, LIU X P, et al. Differential diagnosis of autoimmune encephalitis and herpes simplex virus encephalitis using radiomics models based on multimodal MRI .[J]. Chin J Magn Reson Imaging, 2025, 16(5): 127-135. DOI:10.12015/issn.1674-8034.2025.05.020.


[Abstract] Objective To investigate the diagnostic value of radiomics models based on multimodal MRI in differentiating autoimmune encephalitis (AE) from herpes simplex virus encephalitis (HSE).Materials and Methods A retrospective collection was conducted for patients with acute or subacute autoimmune encephalitis (AE) and herpes simplex encephaliti (HSE) confirmed by cerebrospinal fluid or serological tests at Huashan Hospital Affiliated to Fudan University between January 2013 and July 2024. Patients were randomly divided into training and independent test sets at a ratio of 8∶2. T2-fluid attenuated inversion recovery (T2-FLAIR), T1-weighted imaging (T1WI), and diffusion weighted imaging (DWI) data were collected. All T2-FLAIR hyperintense lesions were manually delineated. Pyradiomics was employed to extract radiomic features, followed by feature selection using the least absolute shrinkage and selection operator (LASSO) algorithm and correlation analysis. The random forest (RF), support vector machine (SVM) and K-nearest neighbor (KNN) models were established; the model parameters were optimized via five-fold cross-validation, and the models were validated on the independent test set. Diagnostic performance was evaluated by AUC, sensitivity, specificity, and accuracy of ROC curves.Results The study totally included 117 AE cases and 110 HSE cases. There were 182 patients including 810 lesions in the training set and 45 patients including 215 lesions in the test set, there were respectively 22, 10, 15, and 12 features being selected for the multimodal, T2-FLAIR, DWI, and T1WI models. The AUCs of RF models based on multimodal, T2-FLAIR, DWI, and T1WI were 0.884, 0.841, 0.775, and 0.799 respectively in the training set. The corresponding AUCs were 0.805, 0.809, 0.696, and 0.737 in the test set, with accuracies of 74.9%, 73.5%, 67.0%, and 67.4% respectively. The AUCs of SVM models based on multimodal, T2-FLAIR, DWI, and T1WI were 0.831, 0.820, 0.780 and 0.816 respectively in the training set. The corresponding AUCs were 0.792, 0.807, 0.696 and 0.728 in the test set, with accuracies of 74.9%, 76.7%, 68.8% and 68.8% respectively. The AUCs of KNN models based on multimodal, T2-FLAIR, DWI, and T1WI were 0.850, 0.806, 0.760 and 0.766 respectively in the training set. The corresponding AUCs were 0.805, 0.809, 0.712 and 0.734 in the test set, with accuracies of 74.0%, 73.0%, 67.9% and 71.2% respectively. The multimodal and T2-FLAIR-based RF, SVM and KNN models exhibited significantly higher AUCs than the DWI-based model (P < 0.05). There were no significant differences in the AUC values of the RF, SVM, and KNN models based on different MRI modalities in the test set.Conclusions The radiomics RF, SVM and KNN models based on multimodal MRI and T2-FLAIR sequence achieved a high diagnostic performance in distinguishing AE from HSE, assistting clinicians making diagnoses in a non-invasive method and helpful for the early formulation of clinical decisions.
[Keywords] autoimmune encephalitis；herpes simplex virus encephalitis；multimodal magnetic resonance imaging；radiomics

LIU Huan1   DAI Jian2   LIU Xianping3   LI Yuxin3   WU Hao4*   GENG Daoying3*  

1 Shanghai Institute of Infectious Disease and Biosecurity, Fudan University, Shanghai 200030, China

2 Institute of Engineering and Applied Technology, Fudan University, Shanghai 200082, China

3 Department of Radiology, Huashan Hospital Affiliated to Fudan University, Shanghai 200040, China

4 Department of Dermatology, Huashan Hospital Affiliated to Fudan University, Shanghai 200040, China

Corresponding author: GENG D Y, E-mail: daoyinggeng@fudan.edu.cn WU H, E-mail: seaseewh@163.com

Conflicts of interest   None.

Received  2025-03-12
Accepted  2025-05-10
DOI: 10.12015/issn.1674-8034.2025.05.020
Cite this article as: LIU H, DAI J, LIU X P, et al. Differential diagnosis of autoimmune encephalitis and herpes simplex virus encephalitis using radiomics models based on multimodal MRI .[J]. Chin J Magn Reson Imaging, 2025, 16(5): 127-135. DOI:10.12015/issn.1674-8034.2025.05.020.

[1]
REN H T, FAN S Y, ZHAO Y H, et al. The changing spectrum of antibody-mediated encephalitis in China[J/OL]. J Neuroimmunol, 2021, 361: 577753 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/34739913/. DOI: 10.1016/j.jneuroim.2021.577753.
[2]
PIRET J, BOIVIN G. Immunomodulatory strategies in herpes simplex virus encephalitis[J/OL]. Clin Microbiol Rev, 2020, 33(2): e00105-19 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/32051176/. DOI: 10.1128/CMR.00105-19.
[3]
ZHANG L H, ZHANG L J, LI F J, et al. When herpes simplex virus encephalitis meets antiviral innate immunity[J/OL]. Front Immunol, 2023, 14: 1118236 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/36742325/. DOI: 10.3389/fimmu.2023.1118236.
[4]
ALI F, WIJDICKS E F. Treatment of movement disorder emergencies in autoimmune encephalitis in the neurosciences ICU[J]. Neurocrit Care, 2020, 32(1): 286-294. DOI: 10.1007/s12028-019-00875-5.
[5]
LIU P P, HE Q Y, LI Y, et al. Clinical characteristics of patients with anti-N-methyl-D-aspartate receptor encephalitis in ICU and the influencing factors of their prognosis[J]. Pract J Card Cereb Pneumal Vasc Dis, 2023, 31(11): 35-39. DOI: 10.12114/j.issn.1008-5971.2023.00.267.
[6]
DUBEY D, TOLEDANO M, MCKEON A. Clinical presentation of autoimmune and viral encephalitides[J]. Curr Opin Crit Care, 2018, 24(2): 80-90. DOI: 10.1097/MCC.0000000000000483.
[7]
SONNEVILLE R, JAQUET P, VELLIEUX G, et al. Intensive care management of patients with viral encephalitis[J]. Rev Neurol (Paris), 2022, 178(1/2): 48-56. DOI: 10.1016/j.neurol.2021.12.002.
[8]
VARLEY J A, STRIPPEL C, HANDEL A, et al. Autoimmune encephalitis: recent clinical and biological advances[J]. J Neurol, 2023, 270(8): 4118-4131. DOI: 10.1007/s00415-023-11685-3.
[9]
KUMAR R. Understanding and managing acute encephalitis[J/OL]. F1000Res, 2020, 9: F1000FacultyRev-F1000FacultyR60 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/32047620/. DOI: 10.12688/f1000research.20634.1.
[10]
MICHAEL B D, BRICIO-MORENO L, SORENSEN E W, et al. Astrocyte- and neuron-derived CXCL1 drives neutrophil transmigration and blood-brain barrier permeability in viral encephalitis[J/OL]. Cell Rep, 2020, 32(11): 108150 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/32937134/. DOI: 10.1016/j.celrep.2020.108150.
[11]
VENKATESAN A. Immune-mediated encephalitis for the infectious disease specialist[J]. Curr Opin Infect Dis, 2019, 32(3): 251-258. DOI: 10.1097/QCO.0000000000000546.
[12]
MARINAS J E, MATVEYCHUK D, MCCOMBE J A, et al. Paraneoplastic and autoimmune encephalitis: Alterations of mood and emotion[J/OL]. Handb Clin Neurol, 2021, 183: 221-234 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/34389119/. DOI: 10.1016/B978-0-12-822290-4.00010-4.
[13]
FERREIRA J H F, DISSEROL C C D, DE FREITAS DIAS B, et al. Recent advances in autoimmune encephalitis[J]. Arq Neuropsiquiatr, 2024, 82(12): 1-13. DOI: 10.1055/s-0044-1793933.
[14]
ABBATEMARCO J R, YAN C, KUNCHOK A, et al. Antibody-mediated autoimmune encephalitis: a practical approach[J]. Cleve Clin J Med, 2021, 88(8): 459-471. DOI: 10.3949/ccjm.88a.20122.
[15]
KIM K T. Lumbar puncture: considerations, procedure, and complications[J]. Encephalitis, 2022, 2(4): 93-97. DOI: 10.47936/encephalitis.2022.00045.
[16]
HARTUNG T J, BARTELS F, KUCHLING J, et al. MRI findings in autoimmune encephalitis[J]. Rev Neurol (Paris), 2024, 180(9): 895-907. DOI: 10.1016/j.neurol.2024.08.006.
[17]
TOMASZEWSKI M R, GILLIES R J. The biological meaning of radiomic features[J]. Radiology, 2021, 298(3): 505-516. DOI: 10.1148/radiol.2021202553.
[18]
PASCHALI M, CHEN Z H, BLANKEMEIER L, et al. Foundation models in radiology: what, how, why, and why not[J/OL]. Radiology, 2025, 314(2): e240597 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/39903075/. DOI: 10.1148/radiol.240597.
[19]
BOUTET A, HAILE S S, YANG A Z, et al. Assessing the emergence and evolution of artificial intelligence and machine learning research in neuroradiology[J]. AJNR Am J Neuroradiol, 2024, 45(9): 1269-1275. DOI: 10.3174/ajnr.A8252.
[20]
KHALILI N, KAZEROONI A F, FAMILIAR A, et al. Radiomics for characterization of the glioma immune microenvironment[J/OL]. NPJ Precis Oncol, 2023, 7(1): 59 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/37337080/. DOI: 10.1038/s41698-023-00413-9.
[21]
KALASAUSKAS D, KOSTERHON M, KERIC N, et al. Beyond glioma: the utility of radiomic analysis for non-glial intracranial tumors[J/OL]. Cancers (Basel), 2022, 14(3): 836 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/35159103/. DOI: 10.3390/cancers14030836.
[22]
JANG K, RUSSO C, DI IEVA A. Radiomics in gliomas: clinical implications of computational modeling and fractal-based analysis[J]. Neuroradiology, 2020, 62(7): 771-790. DOI: 10.1007/s00234-020-02403-1.
[23]
KAPADIA R K, TYLER K L, PASTULA D M. Encephalitis in adults caused by herpes simplex virus[J/OL]. CMAJ, 2020, 192(32): E919 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/32778604/. DOI: 10.1503/cmaj.191636.
[24]
LUO Y, MÖHN N, SKRIPULETZ T, et al. Differentiation of viral and autoimmune central nervous system inflammation by kynurenine pathway[J]. Ann Clin Transl Neurol, 2021, 8(12): 2228-2234. DOI: 10.1002/acn3.51383.
[25]
GRANILLO A, LE MARÉCHAL M, DIAZ-ARIAS L, et al. Development and validation of a risk score to differentiate viral and autoimmune encephalitis in adults[J/OL]. Clin Infect Dis, 2023, 76(3): e1294-e1301 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/36053949/. DOI: 10.1093/cid/ciac711.
[26]
TAN Y M, LIU M, HE L C. Clinical and MRI differential analysis of autoimmune encephalitis and viral encephalitis[J]. J Taibah Univ Med Sci, 2022, 18(2): 271-278. DOI: 10.1016/j.jtumed.2022.09.016.
[27]
XIANG Y Y, ZENG C, LIU B Y, et al. Deep learning-enabled identification of autoimmune encephalitis on 3D multi-sequence MRI[J]. J Magn Reson Imaging, 2022, 55(4): 1082-1092. DOI: 10.1002/jmri.27909.
[28]
MA X X, ZHANG L W, HUANG D H, et al. Quantitative radiomic biomarkers for discrimination between neuromyelitis optica spectrum disorder and multiple sclerosis[J]. J Magn Reson Imaging, 2019, 49(4): 1113-1121. DOI: 10.1002/jmri.26287.
[29]
REINERT L S, RASHIDI A S, TRAN D N, et al. Brain immune cells undergo cGAS/STING-dependent apoptosis during herpes simplex virus type 1 infection to limit type I IFN production[J/OL]. J Clin Invest, 2021, 131(1): e136824 [2025-03-11]. https://pubmed.ncbi.nlm.nih.gov/32990676/. DOI: 10.1172/JCI136824.

PREV Correlation study of local habitat entropy based on multimodal MRI for predicting IDH molecular status in adult-type diffuse glioma
NEXT Value of diffusion kurtosis imaging combined with conventional MRI in the differential diagnosis of benign and malignant thyroid nodules
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn