Background
Image-guided interventional radiology plays an important role in the minimally invasive treatment of liver cancer, particularly in patients who are unsuitable for surgical resection. Computed tomography (CT) provides detailed anatomical visualisation of liver tumours and surrounding structures, enabling accurate needle placement and precise targeting during interventions such as percutaneous thermal ablation. CT guidance facilitates treatment planning, procedural monitoring, and assessment of tumour coverage, while minimising damage to surrounding healthy tissue. Consequently, CT-guided interventions have become an important component of the multidisciplinary management of liver cancer.
Aim
The aim of this project is to develop an image-guided interventional radiology workstation that integrates multiple deep learning algorithms for the automatic detection and segmentation of clinically relevant anatomical structures and pathological regions, including the liver, tumours, and areas of necrosis. The ultimate goal is to deliver a fully functional workstation that enables radiologists to evaluate the feasibility and clinical potential of deep learning-based image analysis in interventional treatment planning.
Funding
The project was funded by the Hanarth Fonds


