Radiology AI Lab @ The Netherlands Cancer Institute
At the forefront of integrating AI in oncologic imaging, our mission is to navigate through the complexities of cancer diagnosis and treatment planning by developing AI algorithms to unlock new potentials in radiology.
Latest news
Radiology AI Lab at EMBC 2024!
We have three papers accepted at EMBC 2024! These works focus on the impact of federated learning, differential privacy and on methods to increase generalizability and interpretability in AI.
Read moreH100 server joins our AI cluster
We have added Herakles, a server with 8xH100 SXM5 GPUs, to our Kosmos cluster. This will allow us to scale our AI models significantly.
Read moreWe are at ESMO Sarcoma and Rare Cancers Congress 2024!
We have two abstracts accepted at ESMO Sarcoma and Rare Cancers Congress 2024! These works focus on automatically assessing response-to-treatment, respectively, in neuroendocrine tumours and in soft tissue sarcoma.
Read moreResearch
The research projects of the Radiology AI Lab
Patient and Treatment Monitoring
Patient monitoring in cancer care is crucial to track the efficacy of anti-cancer treatments and overall patient condition, utilizing methods as follow-ups and response assessments. Our goal is to leverage AI methods to propose optimized treatment strategies, objective progression definition and diagnostic precision.
Read moreRadiogenomics
Radiogenomics
Radiogenomics brings together multiple disciplines. Our goal is to study the impact of somatic mutations on the morphology of the tumour, to identify radiomic signatures predictive of clinically relevant molecular profiles, and to explore MR techniques to predict tumour microenvironment.
Read moreResponse or Recur
Response or Recur
Pre-treatment imaging has the power to give insights into response to therapy before it is given. Our goal is to leverage advanced machine learning combining imaging modalities to craft more personalized treatment plans. Currently these algorithms focus on prostate, rectal and oesophageal cancer, by using self-supervised and semi-supervised learning, image-to-image translation and multimodal AI.
Read moreTrustworthy AI
Trustworthy AI
It is extremely common that Deep Learning algorithm performs well in one medical dataset but is unable to generalize to a different dataset. Our goal is the development of robust algorithms, techniques to share data and understanding of AI decisions, by focusing on generalizability, privacy and explainable AI.
Read moreVisual Foundational Models
Visual Foundational Models
Image encoders are often trained for project-specific tasks, failing to capture an optimal representation of the medical scan. Our goal is to develop powerful encoders capable of generating high-quality embeddings, and to subsequently use them for clinical-use cases, such as automatic radiology report generation or promptable segmentation via textual queries.
Read morePeople
The people working at the Radiology AI Lab