PCCT-based fracture detection

Karlstad University; Louvain; Sur place; EUR 30 000 - 50 000; Plein temps

Résumé du poste

A prestigious university in Leuven is offering an exciting PhD position focused on developing AI algorithms for fracture detection. The role includes collaboration with clinical partners and interdisciplinary research. Candidates should have a Master in a relevant field, solid understanding of deep learning, and excellent Python skills. This opportunity provides research experience in a dynamic environment with travel possibilities.

Prestations

Research experience within a prestigious university

International research environment

Flexible working hours

Traveling opportunities

Qualifications

• Obtained a first class Master in a relevant field.
• Experience with large biomedical data and AI tools.
• Aptitude to collaborate with local and international project partners.

Responsabilités

• Conduct research on trustworthy AI algorithms for fracture detection.
• Collaborate with other PhD candidates and clinical partners.
• Support clinical decision-making for patients with pelvic ring fractures.

Connaissances

Good understanding of statistics and machine/deep learning algorithms

Excellent programming skills in Python

Proficient English, both oral and written

Enthusiasm about research and medical applications of AI

Aptitude to work independently and critically

Good team spirit

Formation

Master in a relevant field (computer science, biomedical engineering, or mathematical engineering)

Description du poste

KU Leuven is an autonomous university. It was founded in 1425. It was born of and has grown within the Catholic tradition.

The project will be supervised by KU Leuven professor Maarten De Vos (Department of Electrical Engineering (ESAT) and is in collaboration with clinical partners at UZ Leuven (e.g. Michiel Herteleer). The successful candidate will closely collaborate with other PhD candidates working on the same project and on related projects. The research is embedded in a stimulating interdisciplinary environment with state-of-the-art analysis expertise and with ample opportunities for interaction with clinicians and AI experts.

Who are we? The STADIUS-BIOMED research group at the Department of Electrical Engineering (ESAT) of KU Leuven is one of the world-leading groups developing and validating AI approaches in Healthcare, with applications covering various clinical disciplines.
The group is a friendly, close-knit collaborative team focused on delivering novel innovations into healthcare practice.
We closely collaborate with medical colleagues in UZ Leuven and with various industry partners, and have prior expertise in deploying methodology in clinical applications.

We are offering an exciting PhD position at the KU Leuven, within the Biomed lab to develop new trustworthy AI algorithms for fracture detection based on novel photon counting CT technology. Particularly relevant is experience with large biomedical data and AI tools. The goal of the project is Automated Detection and Classification of Osteoporotic Pelvic Fractures using Deep Learning and Photon-Counting CT Images.

While Computed Tomography (CT) is the current gold standard for diagnosis and a major improvement over conventional X-rays, it has significant downsides. Even for trained specialists, the detection of subtle, minimally displaced osteoporotic fractures on CT scans remains challenging. This diagnostic uncertainty frequently leads to a "wait-and-see" clinical strategy, as clinicians struggle to evaluate the fracture's mechanical stability, as the complex interplay of muscle forces and ligament damage can render even non-displaced fractures unstable depending on the patient's activity. To address these limitations, this project will leverage Photon-Counting CT (PCCT), a cutting-edge modality offering superior resolution and material differentiation to improve diagnostic precision. The aim of the project is to support clinical decision-making for patients with pelvic ring fractures.

Profile

The requirements for the position are :

• Obtained a first class Master in a relevant field, e.g. computer science, biomedical engineering or mathematical engineering
• Good understanding of statistics and machine/deep learning algorithms
• Interest in Biomedical data science
• Excellent programming skills in Python
• Proficient English, both oral and written
• Enthusiasm about research and medical applications of AI
• Aptitude to work independently, think critically, lead project deliverables and meet deadlines
• Good team spirit, be pro-active and participate in the lab’s scientific life
• Aptitude to collaborate with local and international project partners (including technical and clinical collaborators)

Offer

We offer :

• A PhD position
• Research experience within a prestigious university (most innovative university in Europe)
• Cutting-edge research in AI for healthcare in one of the most dynamic research groups in Europe
• An international research environment by joining a multi-cultural team representing all continents
• Opportunities to collaborate with international and inter-disciplinary collaborators as part of the European projects
• Traveling opportunities to scientific events, project meetings and international stays
• Freedom to independently conduct research and contribute with own ideas
• Flexible working hours, with possibility to telework

Application requirements :

• Academic records (grades) for Bachelor and Master degrees

Interested?

For more information please contact Prof. dr. Maarten De Vos, tel.: [phone], mail: [emailprotected] .

KU Leuven strives for an inclusive, respectful and socially safe environment. We embrace diversity among individuals and groups as an asset. Open dialogue and differences in perspective are essential for an ambitious research and educational environment. In our commitment to equal opportunity, we recognize the consequences of historical inequalities. We do not accept any form of discrimination based on, but not limited to, gender identity and expression, sexual orientation, age, ethnic or national background, skin colour, religious and philosophical diversity, neurodivergence, employment disability, health, or socioeconomic status.