A new preprocessing parameter estimation based on geodesic active contour model for automatic vestibular neuritis diagnosis

• Published in: Artificial intelligence in medicine Vol. 80; pp. 48 - 62
• Main Authors: Ben Slama, Amine, Mouelhi, Aymen, Sahli, Hanene, Manoubi, Sondes, Mbarek, Chiraz, Trabelsi, Hedi, Fnaiech, Farhat, Sayadi, Mounir
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01-07-2017
• Subjects: Algorithms; Geodesic active contours; Humans; Image Processing, Computer-Assisted; Multilayer neural network (MNN); Nystagmus analysis; Principal Component Analysis; Principal component analysis (PCA); Pupil segmentation; Vestibular neuritis; Vestibular Neuronitis - diagnostic imaging; VNG technique; Pupil segmentation; Multilayer neural network (MNN); Vestibular neuritis; Geodesic active contours; Nystagmus analysis; VNG technique; Principal component analysis (PCA)
• ISSN: 0933-3657; 1873-2860
• DOI: 10.1016/j.artmed.2017.07.005

[Display omitted]
•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.
The diagnostic of the vestibular neuritis (VN) presents many difficulties to traditional assessment methods This paper deals with a fully automatic VN diagnostic system based on nystagmus parameter estimation using a pupil detection algorithm. A geodesic active contour model is implemented to find an accurate segmentation region of the pupil. Hence, the novelty of the proposed algorithm is to speed up the standard segmentation by using a specific mask located on the region of interest. This allows a drastically computing time reduction and a great performance and accuracy of the obtained results. After using this fast segmentation algorithm, the obtained estimated parameters are represented in temporal and frequency settings. A useful principal component analysis (PCA) selection procedure is then applied to obtain a reduced number of estimated parameters which are used to train a multi neural network (MNN). Experimental results on 90 eye movement videos show the effectiveness and the accuracy of the proposed estimation algorithm versus previous work.