Analysis of Different Methodsfor Identification and Classification of Cevical Spondylosis (CS): A Survey

In this paper we have compared different methods of Cervical Spondylosis detection. There are various measuring tools to evaluate the neck pain, regional pain, neurologic deficits of the sphincters, torso caused by cervical spondylosis. However, the results are challenged because cervical spondylosis can be subdivided into different sub-types due to different pathological diagnosis. After comparison we have found that for the analysis of Cervical Spondylosis (CS) detection requires an extensive knowledge of the anatomy, skill and experience of specialist. We also found one interesting thing that Doctors are doing manual inspection by using MRI and CT scans. There is no automatic method available so we propose the system which can automatically detect and analyses the Cervical Spondylosis using CNN-LSTM algorithm. The Long Short-Term Memory (LSTM) and the Convolutional Neural Networks (CNNs) is an algorithm to make automation in various real life applications by using machine learning methodology. This architecture includes utilizing Convolutional Neural Network (CNN) layers for highlight extraction on input information joined with LSTMs to help grouping expectation which gives higher accuracy in classification and detection of disease from MRI images. A CNN LSTM can be characterized by including CNN layers in front end and LSTM layers in back end. We had also analyzed various dataset and its results obtained in many existing research work and made comparative study in automation techniques, also proposed our system for making automation efficiently and found that we can improve the detection accuracy significantly.