School of Science and Technology

Medical Image Classification and Segmentation

Motivation and scope

Computer-aided diagnosis (CAD) is a useful tool for assisting doctors in interpreting medical images such as X-rays, MRI, ultrasound, and computed tomography (CT) scans. Applications can range from image preprocessing, segmentation of organs, and detecting certain anomalous patterns. Recent scientific progress in deep learning has resulted in a number of powerful machine learning algorithms for computer vision that can be used for medical image interpretation.

Specific tasks 

The task is to use recent advanced deep learning algorithms on CT scans for classifying the emphysema score of patients.

Necessary skills

Good programming skills in at least one of the following: Python, Tensorflow, Keras, PyTorch, and/or Matlab. Basic knowledge in machine learning.

Benefits

You will learn how to work on a machine learning project using computer vision algorithms for the task of interpreting medical images.

Contact

Martin Längkvist