Description: Job description
This position is part of a collaboration with physicians from the Karolinska University Hospital. The main task will be to develop deep learning methods to analyse medical images, focusing on breast cancer. The successful applicant will apply his/her knowledge in deep learning to several types of medical images, including histological sections, mammograms, and possibly others. Generally, the goal will be towards predicting patient outcome, but we aim to develop models for specific predictors of patient outcome, such as tumour heterogeneity biomarkers and risk models. In additional to these medical applications, the successful candidate will also participate in theoretical research in deep learning and computer vision. Other duties include helping to mentor MSc and PhD students, and potential teaching duties.
The position is initially funded for one year, with a possibility for extension contingent upon funding and eligibility.
Candidates must have a PhD in computer science, computational science, or a related field received within the last three years. Proven knowledge and ability in one or more deep learning frameworks (Tensorflow, Keras, Torch, Caffe, etc) is absolutely required. Also required is knowledge of standard computer vision techniques and experience in implementing, analysing, and optimizing scientific applications for image analysis. Proficiency in one or two scientific computing languages (Python, Matlab, R) is required. Experience with parallel programming environments and cloud computing is a plus. Previous experience working with medical or biological images is also desirable.