We at the research team at the Department of Obstetrics and Gynaecology of the University Hospitals KU Leuven, collaborates with the School of Biomedical Engineering and Imaging Sciences at King’s College London. Together, develop and apply innovative machine-learning techniques to enhance ultrasound (US) and Magnetic Resonance Imaging (MRI) examinations. US is the primary imaging modality for assessing pelvic organs in women and monitoring fetal development during pregnancy. In Europe, MRI is typically used to complement US findings when clinically indicated.We primarily focus on using US to evaluate women with pelvic floor dysfunction, and fetuses with congenital malformations that may benefit from perinatal interventions. Our goal is to develop and validate algorithms that automate aspects of the clinical workflow, thereby saving clinicians' time for patient care and reducing dependence on operator expertise. This computational research aims to lower the threshold for using ultrasound, making it accessible to less experienced users and improving the current clinical workflow.The Department of Obstetrics and Gynaecology at University Hospitals Leuven routinely uses ultrasound and has protocols in place to support this research. Patients consent to the use of their images, providing a vast annotated dataset for our studies. In addition to engineers, several clinicians are fully or partially engaged in this research.KU Leuven is one of Europe’s leading universities, with English as the working language for research. It ranks 45th according to the Times Higher Education World University Rankings 2024.ProjectWe are seeking a talented and motivated individual to join our team in developing novel deep learning-based tools aimed at automating and enhancing the current clinical workflow.About Our ResearchIn the field of pelvic floor dysfunction we have already a baseline automatic pipeline that segments the area of the levator hiatus (which serves as a bio-marker) from a transperineal ultrasound volume. Another pipeline extracts the imaging sequence used to analyse the anal sphincter. There is also work with interactive segmentation and diagnostic plane selection that gives the clinician control of segmentation boundaries and diagnostic planes respectively.What We OfferInnovative Environment: Work on cutting-edge research in a fine interdisciplinary research team, and in collaboration with top institutions, including the School of Biomedical Engineering and Imaging Sciences at King’s College London and the University of Michigan (Pelvic Floor Research Group).Comprehensive Data: Access to a large, annotated dataset of images and volumes from both healthy controls and symptomatic patients, with ongoing data collection.Impactful Work: Develop algorithms that have clinical impact, improving workflow efficiency and reducing dependency on operator expertise.Immediate Research GoalsIn Pelvic Floor MedicineUtilise deep learning techniques to quantitatively analyse the structure of the anal sphincter complex and its changes during labour and after vaginal delivery, aiming to uncover new clinical insights. In addition, development of an automated algorithm to track the urethra and bladder neck on dynamic US sequences. Evaluate this tracking algorithm on a symptomatic population to identify patterns between urethra mobility and patient-reported symptoms.In Obstetrics and Fetal Medicine: Develop an intuitive, user-friendly, automated tool to assess markers of normal progression of labour and safe delivery on both static and dynamic 3D/4D US images. Ensure the pipeline provides near real-time analysis for clinical use. Finally, the development of AI-based methodologies to provide interpretable, automated, volumetric and qualitative fetal lung and brain analysis on US images.Why Join Us?You will have the opportunity to collaborate with machine learning researchers from academia, and you will see your research applied in clinic. The research aims to have clinical impact and is in collaboration with clinicians and clinician researchers at the UZ Leuven hospital, who specialise in Pelvic Floor Medicine, and Obstetrics and Fetal Medicine.ResponsibilitiesInnovative Development: Develop and implement state-of-the-art machine learning techniques to address real-world problems with significant clinical impact.Academic Contributions: Publish research findings in top-tier machine learning journals and present at prestigious medical conferences.Collaborative Research: Collaborate with researchers from external academic partners to enhance and expand the scope of the project.OpportunitiesLearn and Contribute: Engage with cutting-edge applications of AI in the medical imaging analysis field, making significant contributions to innovative research.Skill Development: Enhance your programming skills with industry-standard tools such as PyTorch.Dynamic Environment: Work in a creative and inspiring academic setting with direct clinical impact.ProfileEducational Background: Master’s degree in computer science or a related STEM field (e.g., physics, chemistry, mathematics, chemical engineering, electrical engineering).Analytical and Communication Skills: Strong analytical thinking, scientific writing, and presentation skills in English, coupled with robust mathematical abilities.Programming Experience: Proficiency in a programming language such as Python, C, C++, or C#.Desirable Traits: A keen interest in machine learning, deep learning, medical imaging analysis, and the applications of AI in healthcare.OfferWe offer an exciting PhD project in automatic imaging analysis for pelvic floor ultrasound images using cutting-edge deep learning techniques. This research aims to culminate in a PhD after three to four years. Within the first year the candidates are helped applying for a personal fellowship of the Flemish Research Council (FWO).This is a full-time, fixed-term contract for one year, and based on progress after that year, extendable to four years . Join KU Leuven for a prestigious, fully-funded PhD program with a competitive salary (scale 43) salary details, complemented by a comprehensive benefits package. Enjoy free transport from your Belgian residence to the office, a free university bike, and annual eco-cheques worth 240 €. Eligible candidates also receive a holiday bonus, an end-of-year bonus, and an exceptional holiday leave scheme. For more details, visit KU Leuven PhD Information. Seize this opportunity to advance your academic career with unparalleled support in one of Europe’s leading research institutions.You will be based in Leuven, a historic, dynamic, and vibrant mid-sized city with plenty of activities for its more than 60,000 students. Leuven is located in the heart of Belgium, just twenty minutes from Brussels, the capital of the European Union, and less than two hours from Paris, London, and Amsterdam.Contact:Main supervisor: Dr Helena Williams, [email protected]