MSc Thesis: Realtime Image Enhancement Algorithms for Medical Images

Project Description 

In radiotherapy, an X-ray taken before treatment may be compared with a reference image simulated from the patient’s CT scan to check patient positioning. Users can display the images on top of each other to assess and adjust their alignment, a process known as image registration. Poor contrast, noise, imaging artifacts, and limited resolution can make bones and other anatomical features difficult to distinguish. Differences in appearance between images can further complicate comparison. Users often adjust brightness and contrast manually through settings known as window/level, but some structures remain difficult to see. Image enhancement could improve anatomical visibility and support both visual registration and general image viewing. However, settings tuned for one device or image type may not work equally well for others. Enhancement also involves trade-offs: sharpening can amplify noise, while smoothing can obscure useful details. 

The thesis will survey the state of the art in conventional image enhancement, select promising methods, and implement and evaluate them in our existing C++ medical image viewer using GLSL shaders. Relevant areas may include: 

•  Automatic window/level and other intensity mappings. 

•  Histogram-based contrast enhancement and matching an image’s intensity distribution to that of a reference. 

•  Noise reduction, sharpening, and local contrast enhancement. 

Your profile

We are looking for a master’s student with experience in C++ programming and an interest in visualization and image processing. Knowledge of image processing or computer vision, and familiarity with GPU programming and shaders in OpenGL or Vulkan, are advantages. Prior knowledge of medical imaging is not necessary. 

Application

Please apply to the position through the link below. Selection and interviews will be ongoing. We do not accept applications by e-mail. 

Application Link.