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."
Ike Skelton

 The Project Pol-Nor/204256/16/2013 is carried out within the Polish-Norwegian Research Programme, Norwegian Financial Mechanism 2009-2014