User-Guided Semi-Automatic Segmentation of Medical 3D Images

Abstract

In cooperation with the Utrecht Medical Center (UMC), I built a 3D browserbased MRI/CT e-learning system. I propose an improved way of defining correct target volumes in 3D MRI and CT scans: instead of user-defined, handcrafted target volumes in which the target contour of a specific anatomical structure has to be traced by hand for each 2D image slice, this method introduces automatic interpolation between user-provided contours. This is achieved with a new variant of the active contour method. As a result, only a subset of the slices have to be segmented manually. This improves on similar contour-based user-guided segmentation methods.