Musculoskeletal Tissue Regeneration

ESR project

3.10

Title of Project

Deep Learning Imaging to Value and Supervise Osteoarthritis Progression

We offer

Three 4-year PhD student positions in the interdisciplinary area of regenerative medicine. The project will focus on imaging of the skeleton, ectopic bone and cartilage by using magnetic resonance imaging and computed tomography.

We ask

You hold a Master’s degree in medicine, medical biology or in a related area. You have affinity with imaging research and clinical translation and thrive in a multidisciplinary research environment. Experience with microbiological experiment and/or orthopaedic and bone related research are of benefit.

Department

The Department of Orthopedic Surgery and Radiology at UMC Utrecht is leading in the field of musculoskeletal imaging, with over 200 active PhD students at both departments.

Description

Osteoarthritis is a major cause of disability worldwide. With an ageing population that becomes more obese the life-time risk of getting osteoarthritis is estimated at 25-40%. Pharmaceutical companies are actively searching for Disease Modifying OsteoArthritis Drugs (so-called DMOADS), though appropriate outcome measures that can identify patient benefits from a specific therapy are not available yet. New non-invasive imaging strategies that specifically address the modifying aspect of osteoarthritis are crucial to create a breakthrough for pharmaceutical companies to find new drugs and to guide clinical implementation in finding the right patient for the right therapy and subsequently monitor treatment.  We think that the interaction of bone and cartilage in the joint plays an important role in selected patients (bone-phenotype) and that in another subgroup the vasculature is important in the development and progression of osteoarthritis (vascular phenotype).

We will apply dedicated MRI sequences and spectral CT to image various aspects of knee osteoarthritis in order to grade the disease and find early markers to predict disease progression. Machine/Deep learning techniques will be used to provide detailed quantitative images that can be deduced from the complex-valued imaging data. Subsequently, machine learning algorithms will be used to translate these images in clinically applicable information regarding patients’ phenotype and disease progression. Although sophisticated image analyses have been used previously to improve imaging of osteoarthritis, applications of machine learning algorithms to make both detailed images and clinical predictions for osteoarthritis is novel. With deep learning algorithms applied to imaging data we expect that complex interactions between subtle cartilage, bone, vascular and/or synovial tissue alterations can be identified as possible predictors for disease progression.

The current concept reaches far beyond current image interpretation and it is anticipated that the method can be used to guide new therapeutic interventions, which will likely be different for different subsets (phenotypes) of patients. The project will lead to new MRI and CT based methods for imaging of osteoarthritis and vascular disease as potential predictors for disease progression, thereby creating a potential breakthrough in osteoarthritis research and care.

Requirements

  • You have a Master in biomedical engineering, physics, computer science or in a related area
  • You have affinity with bone and orthopaedic research and/or imaging
  • You can travel and stay to collaborating research facilities overseas (Hong Kong)
  • Experience with medical image analysis and machine learning are of benefit

Contact person & more information

Dr. Peter Seevinck, UMC Utrecht
P.Seevinck@umcutrecht.nl

RESCUE

This project is part of RESCUE, a multidisciplinary, intersectoral and interdisciplinary PhD training programme in Regenerative Medicine and Stem Cells organised by Regenerative Medicine Utrecht. RESCUE is part funded by the European Commission under Horizon 2020's Marie Skłodowska-Curie Actions COFUND scheme. Specific requirements with regards to English language and mobility apply for candidates who would like to take part in this programme, for more information check: link .