Share：
Share this content in WeChat
X
[Chinese][PDF]4823
• Clinical Article •
Classification and early diagnosis of children viral encephalitis on MRI images based on convolutional neural network
HUANG Jian  YU Zhuo  XU Lu  ZHOU Haichun  YU Gang 

Cite this article as: HUANG J, YU Z, XU L, et al. Classification and early diagnosis of children viral encephalitis on MRI images based on convolutional neural network[J]. Chin J Magn Reson Imaging, 2023, 14(1): 54-60. DOI:10.12015/issn.1674-8034.2023.01.010.


[Abstract] Objective To establish a magnetic resonance imaging (MRI) classification and early diagnosis model of children viral encephalitis based on convolutional neural network (CNN), and to explore its value in early diagnosis, precise treatment and improvement of prognosis of children viral encephalitis.Materials and Methods A total of 1077 cases of brain MRI data were collected from the Children's Hospital of Zhejiang University School of Medicine from 2020 to 2022, including 577 cases with viral encephalitis (VE) and 500 cases without VE. The Squeeze-and-Excitation Residual Networks (SE-ResNet) model in CNN was used to construct the MRI classification and early diagnosis model of children viral encephalitis, and was compared with Convolutional Block Attention Module Residual Networks (CBAM-ResNet), Mobile Networks (MobileNet), Residual Networks (ResNet), and Shuffle Networks (ShuffleNet) models.Results All models converged on the training set. The accuracy of SE-ResNet, CBAM-ResNet, MobileNet and ShuffleNet models all reached more than 90% after 100 rounds of training in the training set, while only CBAM-ResNet model and SE-ResNet model selected in this study also achieved more than 90% accuracy in the validation set. In the test set, CBAM-ResNet had the highest accuracy rate of 73.91%, ResNet had the highest recall rate of 75.45%, yet only SE-ResNet model used in this work had a high level in both accuracy and recall, and achieved the best F1 and area under the curve (AUC): the accuracy rate was 70.83%, the recall rate was 72.73%, the AUC was 0.77, and the F1 score was 0.7183.Conclusions The results in this work showed that it is feasible to realize the early diagnosis of viral encephalitis in children by using artificial intelligence technology combined with MR images, and provided theoretical and practical foundation for further achieving the early diagnosis and precise treatment of children viral encephalitis and improving the prognosis of children with encephalitis in a comprehensive way.
[Keywords] childhood diseases；viral encephalitis；magnetic resonance imaging；Squeeze-and-Excitation Residual Networks；deep learning；classification models；early diagnosis

HUANG Jian1, 2   YU Zhuo3   XU Lu4   ZHOU Haichun5   YU Gang1, 2*  

1 Department of Data and Information, the Children's Hospital Zhejiang University School of Medicine, Hangzhou 310052, China

2 Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou 310052, China

3 Department of Scientific Research, Huiying Medical Technology (Beijing) Co., Ltd., Beijing 100192, China

4 Department of Neurology, the Children's Hospital of Zhejiang University School of Medicine, Hangzhou 310052, China

5 Department of Radiology, the Children's Hospital Zhejiang University School of Medicine, Hangzhou 310052, China

Corresponding author: Yu G, E-mail: yugbme@zju.edu.cn

Conflicts of interest   None.

ACKNOWLEDGMENTS National Key R&D Program of China (No. 2019YFE0126200); National Natural Science Foundation of China (No. 62076218).
Received  2022-08-09
Accepted  2022-12-12
DOI: 10.12015/issn.1674-8034.2023.01.010
Cite this article as: HUANG J, YU Z, XU L, et al. Classification and early diagnosis of children viral encephalitis on MRI images based on convolutional neural network[J]. Chin J Magn Reson Imaging, 2023, 14(1): 54-60. DOI:10.12015/issn.1674-8034.2023.01.010.

[1]
LI M L, WANG H. Outcome and related factors for prognosis following severe viral encephalitis in children[J]. Chin J Appl Clin Pediatr, 2011, 26(23): 1817-1820. DOI: 10.3969/j.issn.1003-515X.2011.23.020.
[2]
KNEEN R, MICHAEL B D, MENSON E, et al. Management of suspected viral encephalitis in children-Association of British Neurologists and British Paediatric Allergy, Immunology and Infection Group National Guidelines[J]. J Infect, 2012, 64(5): 449-477. DOI: 10.1016/j.jinf.2011.11.013.
[3]
IRO M A, SADARANGANI M, NICKLESS A, et al. A population-based observational study of childhood encephalitis in children admitted to pediatric intensive care units in England and Wales[J]. Pediatr Infect Dis J, 2019, 38(7): 673-677. DOI: 10.1097/INF.0000000000002280.
[4]
MESSACAR K, FISCHER M, DOMINGUEZ S R, et al. Encephalitis in US children[J]. Infect Dis Clin North Am, 2018, 32(1): 145-162. DOI: 10.1016/j.idc.2017.10.007.
[5]
DUBEY D, PITTOCK S J, KELLY C R, et al. Autoimmune encephalitis epidemiology and a comparison to infectious encephalitis[J]. Ann Neurol, 2018, 83(1): 166-177. DOI: 10.1002/ana.25131.
[6]
JI Q, ZHOU X Z. Logistic regression analysis of prognostic factors of viral encephalitis in children[J]. Neural Inj Funct Reconstr, 2015, 10(4): 344-346. DOI: 10.3870/sjsscj.2015.04.024.
[7]
ZENG K, ZHENG H, CAI C B, et al. Simultaneous single- and multi-contrast super-resolution for brain MRI images based on a convolutional neural network[J]. Comput Biol Med, 2018, 99: 133-141. DOI: 10.1016/j.compbiomed.2018.06.010.
[8]
MITTAL M, GOYAL L M, KAUR S, et al. Deep learning based enhanced tumor segmentation approach for MR brain images[J]. Appl Soft Comput, 2019, 78: 346-354. DOI: 10.1016/j.asoc.2019.02.036.
[9]
BUNEVICIUS A, SCHREGEL K, SINKUS R, et al. REVIEW: MR elastography of brain tumors[J/OL]. Neuroimage Clin, 2020, 25: 102109 [2022-08-08]. https://www.sciencedirect.com/science/article/pii/S2213158219304565. DOI: 10.1016/j.nicl.2019.102109.
[10]
HAMMERNIK K, KLATZER T, KOBLER E, et al. Learning a variational network for reconstruction of accelerated MRI data[J]. Magn Reson Med, 2018, 79(6): 3055-3071. DOI: 10.1002/mrm.26977.
[11]
CHEN F Y, TAVIANI V, MALKIEL I, et al. Variable-density single-shot fast spin-echo MRI with deep learning reconstruction by using variational networks[J]. Radiology, 2018, 289(2): 366-373. DOI: 10.1148/radiol.2018180445.
[12]
WANG S S, SU Z H, YING L, et al. Accelerating magnetic resonance imaging via deep learning[J]. Proc IEEE Int Symp Biomed Imaging, 2016, 2016: 514-517. DOI: 10.1109/ISBI.2016.7493320.
[13]
KIM K H, DO W J, PARK S H. Improving resolution of MR images with an adversarial network incorporating images with different contrast[J]. Med Phys, 2018, 45(7): 3120-3131. DOI: 10.1002/mp.12945.
[14]
QIN C, SCHLEMPER J, CABALLERO J, et al. Convolutional recurrent neural networks for dynamic MR image reconstruction[J]. IEEE Trans Med Imaging, 2019, 38(1): 280-290. DOI: 10.1109/TMI.2018.2863670.
[15]
POLONI K M, DE OLIVEIRA I A D, TAM R, et al. Brain MR image classification for Alzheimer's disease diagnosis using structural hippocampal asymmetrical attributes from directional 3-D log-Gabor filter responses[J]. Neurocomputing, 2021, 419: 126-135. DOI: 10.1016/j.neucom.2020.07.102.
[16]
LATIF G, ISKANDAR D N F A, ALGHAZO J, et al. Brain MR Image Classification for Glioma Tumor detection using Deep Convolutional Neural Network Features[J]. Curr Med Imaging, 2021, 17(1): 56-63. DOI: 10.2174/1573405616666200311122429.
[17]
GU X Q, SHEN Z X, XUE J, et al. Brain tumor MR image classification using convolutional dictionary learning with local constraint[J/OL]. Front Neurosci, 2021, 15: 679847 [2022-08-08]. https://www.frontiersin.org/articles/10.3389/fnins.2021.679847/full. DOI: 10.3389/fnins.2021.679847.
[18]
CHEN L Y. Value of electroencephalogram in early diagnosis of viral encephalitis in children[J]. Guide China Med, 2022, 20(29): 68-71. DOI: 10.15912/j.cnki.gocm.2022.29.040.
[19]
LIU C Y, LAI H, LIU L H, et al. MRI features of viral encephalitis in children[J]. J Pract Radiol, 2018, 34(12): 1922-1924. DOI: 10.3969/j.issn.1002-1671.2018.12.027.
[20]
BAI X D, QIU H Z, WANG S L, et al. Analysis on value of multivoxel and monovoxel of 1H-MRS in the diagnosis of low-grade glioma acute and subacute cerebral infarction and viral encephalitis[J]. Hebei Med, 2020, 26(10): 1702-1706. DOI: 10.3969/j.issn.1006-6233.2020.10.028.
[21]
ZHANG K Q, CHEN L L, HAN X O, et al. MELAS mitochondrial encephalomyopathy misdiagnosed as viral encephalitis, epilepsy and cerebral infarction: a case report[J]. J Apoplexy Nerv Dis, 2019, 36(5): 457-459. DOI: 10.19845/j.cnki.zfysjjbzz.2019.05.015.
[22]
ZHAO J L, CHEN F D, LU L, et al. Japanese encephalitis (JE) mimicking acute ischemic stroke: a case report[J/OL]. Medicine, 2020, 99(45): e23071 [2022-08-08]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7647585/. DOI: 10.1097/MD.0000000000023071.
[23]
ZHOU J, QIN X Y. Clinical features and influencing factors of prognosis in patients with viral encephalitis[J]. Chin Gen Pract, 2012, 15(34): 3975-3977. DOI: 10.3969/j.issn.1007-9572.2012.34.014.
[24]
ZHAO S, ZHANG S, SONG N, et al. Interpretation of consensus guidelines for investigation and management of encephalitis in adults and children in Australia and New Zealand[J]. Clin Focus, 2016, 31(12): 1370-1376. DOI: 10.3969/j.issn.1004-583X.2016.12.022.
[25]
ISENSEE F, SCHELL M, PFLUEGER I, et al. Automated brain extraction of multisequence MRI using artificial neural networks[J]. Hum Brain Mapp, 2019, 40(17): 4952-4964. DOI: 10.1002/hbm.24750.
[26]
WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[EB/OL]. [2022-08-08]. https://arxiv.org/abs/1807.06521.
[27]
WANG W, HU Y Y, ZOU T, et al. A new image classification approach via improved MobileNet models with local receptive field expansion in shallow layers[J/OL]. Comput Intell Neurosci, 2020, 2020: 8817849 [2022-08-08]. https://www.hindawi.com/journals/cin/2020/8817849/. DOI: 10.1155/2020/8817849.
[28]
ZHANG X H, JIANG L Q, YANG D X, et al. Urine sediment recognition method based on multi-view deep residual learning in microscopic image[J/OL]. J Med Syst, 2019, 43(11): 325 [2022-08-08]. https://link.springer.com/article/10.1007/s10916-019-1457-4. DOI: 10.1007/s10916-019-1457-4.
[29]
MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[C]//Computer Vision - ECCV 2018: 15th European Conference New York: ACM, 2018: 122-138. DOI: 10.1007/978-3-030-01264-9_8.
[30]
XIE Y H, TAN Y, CHONGSUVIVATWONG V, et al. A population-based acute meningitis and encephalitis syndromes surveillance in Guangxi, China, may 2007-June 2012[J/OL]. PLoS One, 2015, 10(12): e0144366 [2022-08-08]. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0144366. DOI: 10.1371/journal.pone.0144366.
[31]
HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141. DOI: 10.1109/CVPR.2018.00745.
[32]
GONG L, JIANG S, YANG Z Y, et al. Automated pulmonary nodule detection in CT images using 3D deep squeeze-and-excitation networks[J]. Int J Comput Assist Radiol Surg, 2019, 14(11): 1969-1979. DOI: 10.1007/s11548-019-01979-1.
[33]
JIANG Y, CHEN L, ZHANG H, et al. Breast cancer histopathological image classification using convolutional neural networks with small SE-ResNet module[J/OL]. PLoS One, 2019, 14(3): e0214587 [2022-08-08]. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0214587. DOI: 10.1371/journal.pone.0214587.
[34]
ZHU Z W, WANG H, ZHAO T T, et al. Classification of cardiac abnormalities from ECG signals using SE-ResNet[C]//2020 Computing in Cardiology. Rimini: IEEE, 2021: 1-4.
[35]
HE J, JIANG D. Fully automatic model based on SE-ResNet for bone age assessment[J]. IEEE Access, 2021, 9: 62460-62466. DOI: 10.1109/ACCESS.2021.3074713.
[36]
IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37. New York: ACM, 2015: 448-456. DOI: 10.5555/3045118.3045167.
[37]
SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 2818-2826. DOI: 10.1109/CVPR.2016.308.
[38]
SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. San Francisco: New York: ACM, 2017: 4278-4284. DOI: 10.5555/3298023.3298188

PREV Amplitude of low-frequency fluctuation and regional homogeneity of rs-fMRI in patients with unilateral sudden sensorineural hearing loss
NEXT Value of 3D arterial spin labeling in early diagnosis and prognostic grouping of full-term neonatal hypoxic-ischemic encephalopathy
  


LINK


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