PhD Candidate in Explainable AI (xAI) for Capsule Endoscopy

This is NTNU NTNU is a broad-based university with a technical-scientific profile and a focus in professional education. The university is located in three cities with headquarters in Trondheim. At NTNU, 9,000 employees and 43,000 students work to create knowledge for a better world. You will find more information about working at NTNU and the application process here.

Video: https://www.youtube.com/watch?v=_KHQjc4ndas&t=41sAbout the position NTNU is a broad-based university with a technical-scientific profile and a focus in professional education. The university is located in three cities with headquarters in Trondheim. This position will be in Gjøvik, Norway. At NTNU, 9,000 employees and 43,000 students work to create knowledge for a better world. You will find more information about working at NTNU and the application process here. Video: https://youtu.be/Xt-yHCN5QS0 Are you interested in pursuing a doctoral degree in an international research environment? This position offers the opportunity to join the Marie Skłodowska-Curie Actions (MSCA) Doctoral Network CAPTURE, collaborate with academic, healthcare, and industry partners across Europe, and develop expertise within a multidisciplinary research project on wireless endoscopy. As part of the CAPTURE network, the PhD Candidate will participate in workshops, conferences, transferable skills training, and research secondments with partner organisations. The position provides opportunities for both academic and professional development within an international setting. The successful candidate will be offered a fixed-term, full-time position as a PhD Candidate for a period of 36 months and will be enrolled in a PhD programme leading to the award of a doctoral degree. The expected start date is 1 August 2027. Your immediate leader will be the unit leader of Colourlab.

About the project The CAPTURE project is an EU-funded Marie Skłodowska-Curie Actions (MSCA) Doctoral Network dedicated to advancing wireless capsule endoscopy (WCE) through developments in computer vision and artificial intelligence. The project aims to improve image-based diagnosis, monitoring, and treatment by developing methods that reduce clinicians’ workload, enhance imaging quality, and support more accurate and timely diagnoses. CAPTURE combines research with a strong focus on doctoral training, preparing a new generation of researchers to work at the interface of technology and medicine. The consortium brings together expertise from academia, industry, and hospitals, ensuring that the research is both scientifically rigorous and clinically relevant. The project focuses on inflammatory bowel disease (IBD), reflecting its growing prevalence in Europe. As many of the methods developed have broader applicability, the project will also consider other gastrointestinal diseases. These goals will be achieved through the recruitment and training of 15 doctoral candidates in an international and intersectoral environment, providing interdisciplinary expertise across the technical, clinical, and applied aspects of WCE.

Duties of the position Automated approaches for pathology detection using WCE are generally based on recent AI models. These models often result in black-box decisions. For a clinician to use these systems, the basis for diagnostic decision should be clearly explained. The PhD candidate will help develop explainable AI (XAI) methods for automated diagnostic decision systems to enhance the explainability and actionability of their predictions for doctors. The candidate will also evaluate the generated explanations with medical doctors to assess their relevance, usefulness, and importance in clinical settings. Key responsibilities

• •Complete the doctoral education until obtaining a doctorate
• •Carry out research of good quality within the framework described above
• •Academic publications and popular science dissemination
• •Participate in the Colourlab research group
• •Participate in the network’s joint research and training activities, both online and in person across the CAPTURE partner institutions and contribute to CAPTURE project deliverables in accordance with the Description of Action and the project's governance procedures.
• •Participate in international activities such as conferences and/or research stays at foreign educational institutions. Particularly, secondments of a few months’ duration are foreseen to Robert Gordon University, UK and Technical University of Darmstadt, Germany.
• •Close collaboration with hospitals for assessing methods developed in PhD project

Be prepared for changes to your work duties after employment.

Required selection criteria

• •You must have experience with computer vision and machine learning.
• •You must have excellent programming skills in Python with exposure to popular deep learning libraries like PyTorch or Tensorflow.
• •At the date of recruitment, you must NOT have been awarded a doctoral degree. Researchers who have successfully defended their doctoral thesis but have not yet formally been awarded the degree are also not eligible.
• •You must meet the requirements for admission to the faculty's Doctoral Programme in computer science, see Section 6-1 of the PhD regulations for more information.
• •You must have a relevant master's degree in computer science, electrical engineering or equivalent. Your degree must include a major independent project (minimum 30 ECTS) equivalent to a master’s thesis.
• •Master students can apply, but the master's degree must be obtained and documented before starting the position.
• •You must have a strong and relevant academic background from your previous studies and have an average grade from your master’s degree study, or equivalent education, which is equal to B or better compared to NTNU's grading scale. If you do not have letter grades from previous studies, you must have an equally good academic foundation. If you have a weaker academic background, you may be considered if you can document that you are exceptionally suited for a PhD education, for example through relevant work experience and/or peer-reviewed academic works.
• •Excellent oral and written communication skills in English.
• •You must comply with the MSCA mobility rule: you must not have resided or carried out your main activity (work, studies, etc.) in the country of the recruiting organisation for more than 12 months in the 36 months immediately before recruitment (short stays such as holidays are not taken into account).

The appointment is to be made in accordance with NTNUs guidelines for recruitment positions for general criteria for the position.

Preferred selection criteria Preference may be given to candidates with:

• •Experience with computer vision, medical image processing, self-supervised learning or learning in low-data regimes.
• •Experience with statistical signal processing and pattern recognition will be counted positive.
• •Experience with pretrained representation models, transfer learning and xAI.
• •Knowledge of robustness analysis in computer vision applications.
• •Knowledge of explainable AI, uncertainty estimation, calibration, out-of-distribution detection, adversarial robustness, or causal analysis.
• •Experience with causal inference, counterfactual explanations, or uncertainty quantification in deep learning
• •Evidence of scientific writing, publications, a strong master's thesis, research software, or relevant open-source contributions.
• •Excellent analytical and communication skills.
• •Ability to work in an international and interdisciplinary environment.

Personal characteristics To complete a doctoral degree (PhD), it is important that you are able to:

• •Show strong motivation for research and a willingness to engage deeply with challenging scientific questions.
• •Work in a structured way, set goals and make plans to achieve them.
• •Present and discuss your research with other professionals.
• •Get involved and contribute constructively with feedback.