Postdoctoral Researcher in Multimodal AI for Breast Radiology and Digital Pathol

The Laboratory for Translational Cell and Tissue Research is embedded within the Department of Imaging and Pathology at KU Leuven and is closely affiliated with University Hospitals Leuven. It brings together research-active pathologists, radiologists, biomedical scientists and computational researchers working at the interface of cancer biology, medical imaging and artificial intelligence.

The research teams use clinically annotated human tissue samples and medical images, supported by shared infrastructure for biobanking, histopathology, digital pathology, radiology and quantitative image analysis. This interdisciplinary setting provides an excellent environment for developing multimodal AI methods and translating them into clinically relevant applications.

The postdoctoral researcher will join the M4GIC-ILC project under the supervision of Prof. Giuseppe Floris and will collaborate closely with computational and clinical researchers at KU Leuven and across the international consortium.

Responsibilities

The postdoctoral researcher will lead the development, fine-tuning and benchmarking of foundation models for breast radiology, including mammography, magnetic resonance imaging and ultrasound.

You will develop robust lesion-, image- and patient-level representations that capture characteristics relevant to invasive lobular carcinoma while accounting for variation between hospitals, scanner vendors and acquisition protocols.

You will integrate radiology representations with embeddings derived from digital pathology images and contribute to multimodal models for diagnosis, staging, prognosis, relapse prediction and treatment-response modelling.

You will design and perform rigorous internal and external validation, including cross-site benchmarking, uncertainty estimation, model calibration and subgroup analyses.

You will develop reproducible and well-documented software, maintain data-analysis pipelines and contribute to model documentation and responsible research practices.

You will collaborate closely with radiologists, pathologists, computational scientists and clinical researchers across the international M4GIC-ILC consortium.

You will communicate results through scientific publications, presentations and consortium activities. Depending on experience, you may also supervise doctoral and master's students and contribute to the scientific coordination of related research activities.

Profile

We are looking for a motivated and independent researcher with a strong computational background and demonstrated experience in radiology image analysis.

You hold a PhD in computer science, artificial intelligence, biomedical engineering, medical imaging, bioinformatics, statistics or a closely related computational field.

You have strong programming skills, preferably in Python, and substantial experience with machine learning or deep learning for medical images. You have a scientific publication record appropriate to your career stage.

Proven research experience in radiology image analysis is required. Experience with DICOM and one or more breast-imaging modalities, such as mammography, ultrasound or MRI, is strongly preferred.

Experience with digital pathology, multimodal learning, three-dimensional computer vision, self-supervised learning, foundation models, model calibration or high-performance computing is an advantage.

You are able to take intellectual and technical ownership of an ambitious research project while collaborating effectively in an interdisciplinary and international team. You work in a structured and reproducible manner and communicate scientific results clearly in English, both orally and in writing.

You are interested in clinically meaningful artificial intelligence and motivated to work closely with radiologists, pathologists and other clinical and computational researchers.

Offer

We offer a full-time postdoctoral position for three years, with an initial probationary period of one year. The preferred starting date is 1 October 2026, but this can be adjusted where necessary to accommodate visa procedures or other practical constraints.

You will lead an ambitious research project in breast-imaging AI, foundation-model adaptation and multimodal integration of radiology and digital pathology. You will have access to unique multi-site breast cancer datasets and the computational infrastructure required to analyse large collections of medical images.

You will be supervised by Prof. Giuseppe Floris, co-supervised by Prof. Asier Antoranz and work closely with experts in breast radiology, digital pathology, biomedical AI and translational cancer research. You will become part of an international and interdisciplinary research environment and collaborate with clinical and technical partners across the M4GIC-ILC consortium.

The po