Imaging tremor quantification for neurological disease diagnosis

Abstract

In this paper, we introduce a simple method based on image analysis and deep learning that can be used in the objective assessment and measurement of tremors. A tremor is a neurological disorder that causes involuntary and rhythmic movements in a human body part or parts. There are many types of tremors, depending on their amplitude and frequency type. Appropriate treatment is only possible when there is an accurate diagnosis. Thus, a need exists for a technique to analyze tremors. In this paper, we propose a hybrid approach using imaging technology and machine learning techniques for quantification and extraction of the parameters associated with tremors. These extracted parameters are used to classify the tremor for subsequent identification of the disease. In particular, we focus on essential tremor and cerebellar disorders by monitoring the finger–nose–finger test. First of all, test results obtained from both patients and healthy individuals are analyzed using image processing techniques. Next, data were grouped in order to determine classes of typical responses. A machine learning method using a support vector machine is used to perform an unsupervised clustering. Experimental results showed the highest internal evaluation for distribution into three clusters, which could be used to differentiate the responses of healthy subjects, patients with essential tremor and patients with cerebellar disorders.