Machine Learning Approaches in Developing Expert System for Medical Image Analysis with respect to THR: From Detection to Diagnosis
Sandhya Tatekalva · International Journal of Computer Engineering in Research Trends · 2022
Machine learning approaches are increasingly successful in image-based diagnosis, disease prognosis, and risk assessment.There is a need to find any deviation that can be acquired in position of artificial femur after the log time of surgery, well in advance thereby overcome the adverse socio economic and psychological burden to both the patient as well as the surgeon.The aim of the study is to develop a noninvasive, ultrasound-based, method of diagnosing acetabular cup loosening at an early stage before any major bone erosion has taken place.The proposed study will build on a previously successful technique for the diagnosis of loosing of the femoral stem component of a THR.This paper highlights the steps like box filter section, mainly first order and second order, followed by key points selection, key points extraction, key point matching and finally finding the deviation through motion vector analysis.The data for this research has been collected from different hospitals in Andhra Pradesh and Tamil Nadu.