Over the past few years, thanks to improvements in video imaging, endoscope technology and robotics, much progress has been made to minimize the invasiveness of surgical procedures. For some procedures, this means that the surgeon is no longer able to see or touch the structures on which they operate. Esophagectomy is such a procedure, used to treat patients with esophageal cancer. However, this complex minimally invasive operation is associated with high learning curves for surgeons (up to 70 patient cases). Morbidity and mortality remain substantial, even when the operation is performed by expert surgeons.

Anatomy recognition algorithms based on machine learning hold the promise to facilitate and improve surgical training and guidance during such minimally invasive, robot-assisted operations. However, these algorithms are still in their infancy in soft-tissue oncological surgery, as we showed in a systematic review. Assisting surgeons by recognizing vital anatomical structures in the laparoscopic video feed can help avoid unnecessary damage to these structures and thereby improve clinical outcomes and patient safety.

In this project, you will develop intelligent algorithms for anatomy and surgical phase recognition to support surgeons intraoperatively. The research focus will be on improving the quality, accuracy and speed of these algorithms towards our final goal of clinical implementation. To achieve this, we can benefit from several recent breakthroughs in machine learning research, such as active learning, self-supervised learning, developing novel efficient network architectures, and creating additional simulated video frames to improve network performance and robustness. In addition, you will investigate whether the intraoperative video feed can be augmented with a 3D patient-specific model of the anatomy derived from pre-operative CT or MRI scans.

This PhD position is part of the 'INTRA-SURGE' project, a collaboration between the Medical Image Analysis group of Eindhoven University of Technology (TU/e) and the Department of Surgical Oncology of University Medical Center (UMC) Utrecht. Within this collaboration we have access to a large database of more than 500 standardized surgical videos of robot-assisted esophagectomies. You will work in a multidisciplinary team and will collaborate closely with the expert surgeons of the UMC Utrecht and a clinical PhD student who will start working on this project around the same time.

• A master's degree (or an equivalent university degree) in Physics, Computer Science, Mathematics, Electrical Engineering, Biomedical Engineering/Technology or a related discipline.
• Excellent programming skills in Python.
• Preferably experience both in deep learning and image analysis.
• Ability to work in an interdisciplinary team.
• Fluent in spoken and written English (C1 level).
• A research-oriented and proactive attitude.

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:

• Full-time employment for four years, with an intermediate evaluation after one year. In this project you will spend approximately 10% of your employment on teaching tasks.
• Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale P (min. € 2.541,- max. € 3.247,- gross per month based on a fulltime employment).
• A year-end bonus of 8.3% and annual vacation pay of 8%.
• High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process.
• An excellent technical infrastructure, on-campus children's day care and sports facilities.
• An allowance for commuting, working from home and internet costs.
• A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates.