Postdoc in Deep Learning based Educational System for Dermatology

mandag 27 apr 20

Send ansøgning

Frist 15. juni 2020
Du kan søge om jobbet ved DTU Compute ved at udfylde den efterfølgende ansøgningsformular.

Ansøg online

The section for Image Analysis and Computer Graphics 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 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.

Requirements 
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. 

Assessment 
The assessment of the applicants will be made by Associate Professor Anders Nymark Christensen and Professor Anders Bjorholm Dahl. 

We offer 
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: 
 

  • Access to a globally unique dataset
  • Access to a large knowledge base on campus, and direct contact with industry
Salary and appointment terms
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The period of employment is 2.5 years. The position is full-time starting 1 September 2020 or as soon as possible thereafter.

You can read more about career paths at DTU here

Further Information 
Further information concerning the project can be obtained from Associate Professor Anders Nymark Christensen, anym@dtu.dk

Application procedure
Please submit your online application no later than 15 June 2020 (23:59 local time). Applications must be submitted as
one PDF file containing all materials to be given consideration. To apply, please open the link "Apply online", fill out the online application form, and attach all your materials in English in one PDF file. The file must include: 
  • Application (cover letter)
  • CV
  • Diploma (MSc/PhD)
  • List of publications
Applications and enclosures received after the deadline will not be considered.

Candidates may apply prior to obtaining their PhD degree, but cannot begin before having received it. 

All interested candidates irrespective of age, gender, race, disability, religion or ethnic background are encouraged to apply. 

DTU Compute has a total staff of 400 including 100 faculty members and 130 Ph.D. students. We offer introductory courses in mathematics, statistics, and computer science to all engineering programmes at DTU and specialised courses to the mathematics, computer science, and other programmes. We offer continuing education courses and scientific advice within our research disciplines, and provide a portfolio of innovation activities for students and employees.

Technology for people
DTU develops technology for people. With our international elite research and study programmes, we are helping to create a better world and to solve the global challenges formulated in the UN’s 17 Sustainable Development Goals. Hans Christian Ørsted founded DTU in 1829 with a clear vision to develop and create value using science and engineering to benefit society. That vision lives on today. DTU has 11,500 students and 6,000 employees. We work in an international atmosphere and have an inclusive, evolving, and informal working environment. Our main campus is in Kgs. Lyngby north of Copenhagen and we have campuses in Roskilde and Ballerup and in Sisimiut in Greenland.