Method And System For Lesion Segmentation of 4-Dimensional Medical Data
Department of Electronics and Informatics (ETRO)
Lesion segmentation plays an important role in diagnosis, radiotherapy and surgery planning. Its goal is to identify the lesion’s shape, precise location and connectivity to the vessel system. Nowadays, the current clinical practice is to use volumetric dynamic contrast enhanced computer tomography images, acquired before and after contrast agent injection. However, currently computer aided diagnosis systems work on a single volumetric image, i.e. the volume exhibiting the best contrast enhancement. Therefore, the motivation of our work is to explore the gray-level enhancement in the different abdominal tissues and organs present in all volumes or phases, acquired for instance when the contrast agent reaches for instance in the case of the liver, the hepatic artery, the portal vein and/or the hepatic vein.
Keywords
- Segmentation
- Tumor perfusion
- Contrast enhanced CT
- Multi-phase volumetric data
- Deformable registration.