A new preprocessing parameter estimation based on geodesic active contour model for automatic vestibular neuritis diagnosis
作者：
Highlights：
• An automated method based on geodesic active contour and PCA-MNN classifier is proposed in order to improve the diagnosis of vestibular neuritis (VN).
• The proposed method is tested on dataset of VideoNystagmoGraphy (VNG) containing different types of VN.
• The segmentation accuracy proves the superiority of the proposed method when compared with the classical active contour method.
• Results from rotational eye movement show that the feature extraction step gives interested results even in irregular waveform cases.
• The classification experiments prove the accuracy of the proposed PCA-MNN method which is over than 95%.
• (VNG) containing different types of vestibular disorder.
• The segmentation accuracy proves the superiority of the proposed method in terms of pupil region and contour detection when compared with the classical active contour method.
• Results from rotational eye movement show that the feature extraction step gives interested results even in irregular waveform cases.
摘要
•An automated method based on geodesic active contour and PCA-MNN classifier is proposed in order to improve the diagnosis of vestibular neuritis (VN).•The proposed method is tested on dataset of VideoNystagmoGraphy (VNG) containing different types of VN.•The segmentation accuracy proves the superiority of the proposed method when compared with the classical active contour method.•Results from rotational eye movement show that the feature extraction step gives interested results even in irregular waveform cases.•The classification experiments prove the accuracy of the proposed PCA-MNN method which is over than 95%.•(VNG) containing different types of vestibular disorder.•The segmentation accuracy proves the superiority of the proposed method in terms of pupil region and contour detection when compared with the classical active contour method.•Results from rotational eye movement show that the feature extraction step gives interested results even in irregular waveform cases.
论文关键词：Principal component analysis (PCA),Multilayer neural network (MNN),Nystagmus analysis,Vestibular neuritis,Pupil segmentation,Geodesic active contours,VNG technique
论文评审过程：Received 28 December 2016, Revised 9 June 2017, Accepted 12 July 2017, Available online 23 July 2017, Version of Record 7 September 2017.
论文官网地址：https://doi.org/10.1016/j.artmed.2017.07.005
