Background

Osteoarthritis of the knee is a degenerative disease resulting in reduced knee function and pain. Knee menisci help in transmitting loads and shocks in the knee as well as to decrease friction during motion.

Meniscal lesions and meniscal tears significantly contribute to the development and progression of osteoarthritis.

 

Thesis Objective

In a previous master's thesis in our workgroup, it was shown that convolutional neural networks (CNNs) can be trained to detect meniscal tears in 2D slices of 3D MRI data.

The idea of this thesis is, that the accuracy of these CNNs can be improved by a sophisticated image pre-processing.

Image pre-processing (A) increases the amount of training data, and (B) the considered 2D slices can be choosen in a way such that the information in each slice is maximised.

 

Pre-requisites

1. Experience in C++ and Python programming
                - Experience with Deep learning would be a huge bonus

We Offer

Insight into medical image data processing in combination with deep learning techniques in a stimulating research environment.

We offer co-supervision for the thesis and close collaboration within the research group over the entire duration of the project.

Contact: 
Research Group: 
Deep Vision for Ecology and Environment
MA 02/17
Design and Implementation of a Crowdsourced Study on Computer-aided Diagnosis
MA 01/17