Skip to content  

Working at TU/e

PhD position on robust and efficient Artificial Intelligence (AI) in endoscopy

PhD position on robust and efficient Artificial Intelligence (AI) in endoscopy

Position
PhD-student
Department(s)
Electrical Engineering
FTE
1,0
Date off
02/05/2021
Reference number
V36.4932

Job description

Background

While the enormous potential of AI in medical imaging have been demonstrated over the last decade, the vast majority of the presented algorithms have only been evaluated in an artificial, strictly controlled setting. Often, a limited amount of high-quality images are used, acquired in expert centers, which is generally not representative of the much more heterogeneous data that can be expected in clinical practice. This gap between the domain in which these algorithms are developed and the application domain casts uncertainty on the actual clinical performance of such AI algorithms. Especially in the field of endoscopy, this domain gap poses a problem, as the quality of the imagery heavily depends on the skill and experience of the endoscopist. In addition to data heterogeneity, which places demands on system robustness, two additional challenges currently hinder clinical integration of endoscopic AI. First, the clinical application typically requires real-time, embedded operation. Current state-of-the-art endoscopic AI models are generally large and fail to meet a real-time execution speed. Second, while the interface between the algorithm and the endoscopist will be elemental in successful application of supportive endoscopic AI systems, current systems are evaluated in a man-vs-machine experimental setup, in which there is no communication between the medical specialist and the AI system.

Project description

In this project, we aim to make the next steps towards clinical application of AI-based supportive systems in endoscopy, by addressing key aspects for this translation, such as model robustness, efficiency and interpretability. The PhD candidate starting on this project will explore novel methods to improve the robustness, efficiency and interpretability of the employed AI models, which are currently convolutional neural networks. Specific tasks towards this goal include:

  • Domain-specific (un-/semi-supervised) pre-training, for which a total of 5 million endoscopic images are collected;
  • Combining methods from signal processing (e.g. discrete wavelet transform) with CNNs to enhance efficiency and interpretability;
  • Exploring methods for exploiting temporal information in endoscopic video;
  • Model calibration and uncertainty modeling.

Consortium

This project is carried out in an intensive collaboration between Eindhoven University of Technology and the Amsterdam University Medical Centers (A-UMC). The consortium has an unrivaled track record on AI for endoscopy, including publications in top-tier journals in the field, awarded grants and industry collaborations. As a highlight, last year, the consortium published the results of a developed AI system for detecting early Barrett’s cancer that demonstrated very high detection rates, outperforming a large group of international endoscopists and a matching performance in a live clinical pilot study.

Job requirements

The envisioned candidate for the open position holds an MSc degree in a relevant field for this project (e.g. Electrical engineering, Computer science, Applied Mathematics, Artificial Intelligence, …) with a strong background in machine learning, computer vision and image processing and a drive to improve healthcare. The candidate should have:

  • Deep understanding of convolutional neural networks and basic knowledge on signal processing;
  • Basic understanding of conventional machine learning approaches and their efficient implementation;
  • Strong communication skills, including an excellent proficiency in English (spoken and written);
  • Solid coding skills (e.g Matlab, Python and/or C++);
  • Experience with commonly used deep learning frameworks (TensorFlow/Keras or PyTorch);
  • An affinity with the field of medicine and in particular oncology.

For this particular project, some additional points are desired and could break the tie for two equally suited candidates. These properties are:

  • Knowledge of signal transformations, information theory and image processing;
  • Proficiency in Dutch (or eagerness to quickly learn, written and spoken, for optimal communication within all involved hospitals);
  • Experience with Bayesian neural networks and/or Normalizing flows.

Conditions of employment

  • A meaningful job in a dynamic and ambitious university with the possibility to present your work at international conferences.
  • A full-time employment for four years, with an intermediate evaluation after one year.
  • To support you during your PhD and to prepare you for the rest of your career, you will have free access to a personal development program for PhD students (PROOF program).
  • A gross monthly salary of € 2.395,00 in the first year and € 3.061,00 in the last year (on a fulltime basis). The salary is in accordance with the Collective Labor Agreement of the Dutch Universities.
  • Benefits in accordance with the Collective Labor Agreement for Dutch Universities.
  • Additionally, an annual holiday allowance of 8% of the yearly salary, plus a year-end allowance of 8.3% of the annual salary.
  • A broad package of fringe benefits, including an excellent technical infrastructure, moving expenses, and savings schemes.
  • Family-friendly initiatives are in place, such as an international spouse program, and excellent on-campus children day care and sports facilities.

Information and application

Do you recognize yourself in this profile and would you like to know more? Please contact
dr. Fons van der Sommen, fvdsommen[at]tue.nl or Prof.dr. Peter de With, p.h.n.de.with[at]tue.nl
for more general information.

For information about terms of employment, please contact HR, hrservices.flux[at]tue.nl

Please visit www.tue.nl/jobs to find out more about working at TU/e!

Application

We invite you to submit a complete application by using the 'apply now'-button on this page.
The application should include a:

  • Cover letter in which you describe your motivation and qualifications for the position.
  • Curriculum vitae, including a list of your publications and the contact information of
    two references.
  • Brief description (or summary) of your MSc thesis.
  • Copies of diplomas and transcripts (with course grades).

We look forward to your application and will screen it as soon as we have received it.
Screening will continue until the position has been filled.
The VCA research group has regularly more opportunities (surveillance, industrial AI applications) than only this vacancy. If you largely satisfy the profile, but not specifically interested in healthcare, you are also allowed to apply.

We do not respond to applications that are sent to us in a different way.

Please keep in mind you can upload only 5 documents up to 2 MB each. If necessary please combine files.