Postdoc in Deep Learning Based Educational System for Dermatology at Technical University of Denmark

A new opening postdoctoral researcher position in applied mathematics is available at Technical University of Denmark, Denmark. The funding allows successful candidate to work for six years. Applicants should apply before June 15, 2020.

The section for Image Analysis and Computer Graphics (latest Computer Graphics scholarship positions) at DTU's Department for Applied Mathematics and Computer Science ("DTU Compute") would like to invite applications for a 2.5-year PostDoc position starting in the middle of 2020. The position is part of an ambitious project aimed at developing new deep learning based educational tools for diagnosing skin lesions.

DTU Compute is an internationally unique academic environment spanning the science disciplines mathematics, statistics and computer science. At the same time, we are an engineering department covering informatics and communication technologies (ICT) in their broadest sense. Finally, we play a major role in addressing the societal challenges of the digital society where ICT is a part of every industry, service, and human endeavour. DTU Compute strives to achieve research excellence in its basic science disciplines, to achieve technological leadership in research and innovation, and to address societal challenges in collaboration with partners at DTU and other academic institutions, nationally and internationally, and, equally important, with industry and organizations. We communicate and collaborate with leading centres and strategic partners in order to increase participation in major consortia. DTU Compute plays a central role in education at all levels of the engineering programmes at DTU – both in terms of our scientific disciplines and our didactic innovation. Project Description The worldwide incidence of skin cancer has been rising for 50 years, in particular, the incidence of melanoma (mole cancer) has increased approx. 4-6% annually. The time to train dermatologists - i.e. before they are significantly better than novices - is six years. To err on the safe side, too many skin lesions are therefore removed, with a huge cost for society and discomfort for the patients. To make the doctors better, we will develop an app-based educational tool. When a skin lesion is removed today, it is sent to histopathology to confirm the diagnosis. When the doctor gets an answer back after 1-2 weeks he/she cannot remember what that specific skin lesion looked like, and therefore doesn't get better at diagnosing. The app will store images of all skin lesions together with their verified diagnosis. This will allow us to start training a deep learning based model on the data. The data initially available is a research data base in Denmark (Denmark scholarships) with >20.000 verified images. As the app is deployed, more images will become available making it a large globally unique dataset. The goal is not to build an automatic tool for classifying the images, but rather a tool for determining how difficult the images are to diagnose. In this way, we can make customized training programs for the doctors, present them with images that fit their current expertise, and in that way increase their diagnostic proficiency rapidly. If we can build a model that is good at classifying the images, it can be used to give the doctors hints about what to look for in an image e.g. through saliency heatmaps, and over time more direct decision-support. Potentially, the model can be used to create new diagnostic guidelines as well. The Postdoc will be responsible for the deep learning model research, and how it can support the education of the doctors. A company MelaTech is developing the app, and the involved hospitals will implement it clinically. It is therefore crucial that the candidate thrives in a cross-disciplinary environment, as it will be necessary to interface and communicate with many different disciplines. Candidates must have a PhD-degree in applied mathematics, physics, computer science, electrical engineering, or a similar degree with an equivalent academic level. A genuine interest in deep learning, image analysis, and education is a must. It is an advantage to have a good command of Python and knowledge of PyTorch/Tensorflow. Ability to work in a multidisciplinary environment is essential, as is a good command of the English language. The assessment of the applicants will be made by Associate Professor Anders Nymark Christensen and Professor Anders Bjorholm Dahl. DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility. Furthermore, the project offers a number of unique possibilities, including:

More scholarships: postdoc position in applied mathematics, postdoc position in computer graphics, postdoc position in computer science, postdoc position in mathematics, postdoc position in pathology, applied mathematics postdoc position, computer graphics postdoc position, computer science postdoc position, mathematics postdoc position, pathology postdoc position, postdoc position in denmark, postdoc position at technical university of denmark

Get latest scholarships via your email! It's free!
Remember to check your email and active the subscription.
You can unsubscribe any time.
Copyright © 2019 All Right Reserved.