Detection of ataxia with hybrid convolutional neural network using static plantar pressure distribution model in patients with multiple sclerosis

• Published in: Computer methods and programs in biomedicine 2022-02, Vol.214, p.106525-106525, Article 106525
• Main Authors: Kaya, Mustafa, Karakuş, Serkan, Tuncer, Seda Arslan
• Format: Article
• Language: English
• Subjects: Ataxia; Ataxia - diagnosis; CNN; Deep learning; Humans; Multiple sclerosis; Multiple Sclerosis - diagnostic imaging; Neural Networks, Computer; Static plantar pressure distribution; Support Vector Machine
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2021.106525

•Multiple Sclerosis (PwMS) detection with an artificial intelligence-based approach in the early stage is crucial to follow the course of the disease.•The detection of ataxia in PwMS with the VGG19-SVM hybrid model is an alternative and objective method that supports physicians in deciding the disease in the early stage.•Ataxia, which does not yet cause symptoms and cannot be recognized clinically, can be diagnosed with the 95.12% accuracy value by using the proposed model in the early period. In this study, it is aimed to detect ataxia for Persons with Multiple Sclerosis (PwMS) through a deep learning-based approach using an image dataset containing static plantar pressure distribution. Here, an alternative and objective method will be proposed to assist physicians who diagnose PwMS in the early stages. A total of 406 static bipedal pressure distribution image data for 43 ataxic PwMS and 62 healthy individuals were used in the study. After preprocessing, these images were given as input to pre-trained deep learning models such as VGG16, VGG19, ResNet, DenseNet, MobileNet, and NasNetMobile. The data of each model is utilized to generate its feature vectors. Finally, feature vectors obtained from static pressure distribution images were classified by SVM (Support Vector Machine), K-NN (K-Nearest Neighbors), and ANN (Artificial Neural Network). In addition, a cross-validation method was used to examine the validity of the classifier. The performance of the proposed models was evaluated with accuracy, sensitivity, specificity, and F1-measure criteria. The VGG19-SVM hybrid model showed the best performance with 95.12% acc, 94.91% sen, 95.31% spe, and 94.44% F1. In this study, a specific and sensitive automatic test evaluation system was proposed for Ataxic syndromes using digital images to observe the motor skills of the subjects. Comparative results show that the proposed method can be applied in practice for ataxia that is clinically difficult to detect or not yet symptomatic. It can be defined using only static plantar pressure distribution in the early stage and it can be recommended as an assistant system to physicians in clinical practice.