About the project
„Automated Assessment of Joint Synovitis Activity from Medical Ultrasound and Power Doppler Examinations Using Image Processing and Machine Learning Methods” acronym: MEDUSA
The main research goal of the MEDUSA project is computer aid diagnostic system that will allow for automated assessment of synovitis activity. The project output will be clinically validated by comparing its results with the assessment carried out by medical personnel.
The achieve the project goals, new image processing techniques will be created. Multiple types of local features will be detected, and they will provide a reference frame which will help to normalize measurements performed on ultrasound images with respect to changes in the probe position and the joint articulation. These measurements will be integrated into a function approximating the humanassessment.
Machine learning methods will be used for training the feature detectors and the assessment function on ultrasound images of synovitis cases, annotated and scored by medical experts. An additional research result will be novel visualization methods for power Doppler images, intended to aid the examiners.
The key expected result of MEDUSA project will be a prototype of a software system, that will be useful for medical personnel and will help in diagnosis of rheumatic diseases.
The project proposed project can be classified as multidisciplinary since is overlaps with Rheumatology, Image Processing and Machine Learning, and it belongs to the field of modern diagnostics, a part of the health area of the Polish – Norwegian Research Cooperation Programme."In addition to relieving patient suffering, research is needed to help reduce the enormous economic and social burdens posed by chronic diseases such as osteoporosis, arthritis, diabetes, Parkinson's and Alzheimer's diseases, cancer, heart disease, and stroke."
The Project Pol-Nor/204256/16/2013 is carried out within the Polish-Norwegian Research Programme, Norwegian Financial Mechanism 2009-2014