Deep Feature Extraction of MRI Image– A Reliable Tool for Shoulder Pain Analysis

Main Article Content

B. Triveni, P. Bhargavi, S. Jyothi

Abstract

Pain in shoulder is the most common complaint from patients. The shoulder joint is a complex structure that needs the complete coordination of Bone and soft tissues typical for its regular function at its extremity. Damage of shoulder or its continuous usage causes dysfunction of shoulder and needs proper medication. In general, shoulder problems are solved by a physician without surgery which require a keen diagnosis of the underlying cause and its perfect management. To revaluate accurate outcome regarding patient diagnosis and information related services investigation will require huge amount of information for that big data is used.


Review studies reveal that classification of various types of shoulder disorders is needed for diagnosis and is complicated task to differentiate shoulder diseases. Clinicians face a challenge to categorise patients with chronic cases, high pain issues or both. Since that, the diagnostic classification is primary source to perform treatment, poor diagnosis results in unsatisfactory medication. Hence, the reproducibility, improvement for effective treatment is highly essential.


The objectively precise pain detection system stemming from the scientific and medical significance of emotion detection, as well as the merits promised by the prospect are built to facilitate such possibilities by using images analysis. The segmentation algorithms like Watershed and Region based algorithms are used to analyse the shoulder pain. Also proposed a hybrid segmentation algorithm for the analysis of shoulder pain. Image segmentation will extract the information from the object but feature extraction technique can redefine the image in to a set of features of image. So feature extraction techniques like GLCM, GLRM, LBP and deep feature extraction techniques are also applied on MRI images to analyse the exact cause for the shoulder pain.

Article Details

Section
Articles