Behavioral scoring based on clinical observations remains the gold standard for screening, diagnosing,and evaluating infantile epileptic spasm syndrome (IESS). The accurate identification of seizures is crucial for clinical diagnosis and assessment. In this study, we propose an innovative seizure detection method based on video feature recognition of patient spasms. To capture the temporal characteristics of the spasm behavior presented in the videos effectively, we incorporate asymmetric convolution and convolution–batch normalization–ReLU (CBR) modules. Specifically within the 3D-ResNet residual blocks, we split the larger convolutional kernels into two asymmetric 3D convolutional kernels. These kernels are connected in series to enhance the ability of the convolutional layers to extract key local features, both horizontally and vertically. In addition, we introduce a 3D convolutional block attention module to enhance the spatial correlations between video frame channels efficiently. To improve the generalization ability, we design a composite loss function that combines cross-entropy loss with triplet loss to balance the classification and similarity requirements. We train and evaluate our method using the PLA IESS-VIDEO dataset, achieving an average seizure recognition accuracy of 90.59%, precision of 90.94%, and recall of 87.64%. To validate its generalization capability further, we conducted external validation using six different patient monitoring videos compared with assessments by six human experts from various medical centers. The final test results demonstrate that our method achieved a recall of 0.647 6, surpassing the average level achieved by human experts (0.559 5), while attaining a high F1-score of 0.721 9. These findings have substantial significance for the long-term assessment of patients with IESS.
DING Lihui1，2(丁黎辉)
,
FU Lijun1，3* (付立军)
,
YANG Guang4(杨光)
,
WAN Lin4，5 (万林)
,
CHANG Zhijun7(常志军)
. Video-Based Detection of Epileptic Spasms in IESS: Modeling,
Detection, and Evaluation[J]. Journal of Shanghai Jiaotong University(Science), 2025
, 30(1)
: 1
-9
.
DOI: 10.1007/s12204-024-2789-x
[1] DING D, ZHOU D, SANDER J W, et al. Epilepsy in China: Major progress in the past two decades [J]. The Lancet Neurology, 2021, 20(4): 316-326.
[2] PELLOCK J M, HRACHOVY R, SHINNAR S, et al. Infantile spasms: A U.S. consensus report [J]. Epilepsia, 2010, 51(10): 2175-2189.
[3] WANG Z, FU L J, YANG G, et al. Mixture of expert system for IESS detection based on EEG signal [J/OL]. Journal of Shanghai Jiao Tong University (Science),2024. https://doi.org/10.1007/s12204-024-2771-7
[4] KARACSONY T, JENI L A, DE LA TORRE F, et al.Deep learning methods for single camera based clinical in-bed movement action recognition [J]. Image and Vision Computing, 2024, 143: 104928.
[5] ZHANG C B, SABOR N, LUO J W, et al. Automatic removal of multiple artifacts for single-channel electroencephalography [J]. Journal of Shanghai Jiao Tong University (Science), 2022, 27(4): 437-451.
[6] WU J Y, ZHOU T S, GUO Y F, et al. Video-based evaluation system for tic action in Tourette syndrome: Modeling, detection, and evaluation [J]. Health Information Science and Systems, 2023, 11(1): 39.
[7] HALEEM A, JAVAID M, SINGH R P, et al. Telemedicine for healthcare: Capabilities, features, barriers, and applications [J]. Sensors International,2021, 2: 100117.
[8] LOWE T L, CAPRIOTTI M R, MCBURNETT K. Long-term follow-up of patients with Tourette’s syndrome [J]. Movement Disorders Clinical Practice, 2019, 6(1): 40-45.
[9] AHMEDT-ARISTIZABAL D, ALI ARMIN M, HAYDER Z, et al. Deep learning approaches for seizure video analysis: A review [J]. Epilepsy & Behavior, 2024, 154: 109735.
[10] YANG Y H, SARKIS R A, ATRACHE R E, et al. Video-based detection of generalized tonic-clonic seizures using deep learning [J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(8): 2997-3008.
[11] EGUCHI K, YAGUCHI H, NAKAKUBO S, et al. Video-based detection of epileptic spasms in West syndrome using a deep neural network: A pilot case study [J]. Journal of the Neurological Sciences, 2023, 449:120671.
[12] MYSZCZYNSKA M A, OJAMIES P N, LACOSTE A M B, et al. Applications of machine learning to diagnosis and treatment of neurodegenerative diseases [J]. Nature Reviews Neurology, 2020, 16(8): 440-456.
[13] JAVEED A, DALLORA A L, BERGLUND J S, et al. Machine learning for dementia prediction: A system atic review and future research directions [J]. Journal of Medical Systems, 2023, 47(1): 17.
[14] MESQUITA I A, PINHEIRO A R V, VELHOTE CORREIA M F P, et al. Methodological considerations for kinematic analysis of upper limbs in healthy and poststroke adults. part I: A systematic review of sampling and motor tasks [J]. Topics in Stroke Rehabilitation, 2019, 26(2): 142-152.
[15] DASH D P, KOLEKAR M, CHAKRABORTY C, et al. Review of machine and deep learning techniques in epileptic seizure detection using physiological signals and sentiment analysis [J]. ACM Transactions on Asian and Low Resource Language Information Processing, 2024, 23(1): 16.
[16] TURAEV S, AL-DABET S, BABU A, et al. Review and analysis of patients’ body language from an artificial intelligence perspective [J]. IEEE Access, 2023,11: 62140-62173.
[17] SUN Z H, KE Q H, RAHMANI H, et al. Human action recognition from various data modalities: A review [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(3): 3200-3225.
[18] QUAN W, CAI Y Q, WANG C, et al. VR sickness estimation model based on 3D-ResNet two-stream network [J]. Journal of Zhejiang University (Engineering Science), 2023, 57(7): 1345-1353 (in Chinese).
[19] NIU W H, ZHAI R B. A video human behavior recognition method based on improved 3D ResNet [J]. Computer Engineering & Science, 2023, 45(10): 1814-1821(in Chinese).
[20] VUONG G H, TRAN M T. Resnet video 3D for gait retrieval: A deep learning approach to human identification [C]//12th International Symposium on Information and Communication Technology. Ho Chi Minh: ACM, 2023: 886-892.
[21] PEREZ-GARCIA F, SCOTT C, SPARKS R, et al. Transfer learning of deep spatiotemporal networks to model arbitrarily long videos of seizures [M]//Medical image computing and computer assisted intervention– MICCAI 2021. Cham: Springer, 2021: 334-344.
