GrowCut under StudierFenster

Alessandra Masur

Supervisor(s): Jan Egger

TU Graz

Abstract: Segmentation is a crucial procedure in medical image analysis. The usage of automatic algorithms in this field is an attractive alternative to manual segmentation. One promising semi-automatic segmentation tool is the GrowCut algorithm, which allows n-dimensional image segmentation, providing interactive and dynamic features. Currently, using the GrowCut algorithm for medical image segmentation with a user interface is only possible via medical image analysis software, making it device- and platform-dependent. The GrowCut algorithm without a user interface is available via various implementations but requires a lot of technical knowledge of the user. The aim of this contribution is to provide a user interface for the GrowCut algorithm on the basis of a web application. This is achieved by implementing an adapted version of the GrowCut algorithm, the Fast GrowCut algorithm, into a client/server based, web-hosted 3-dimensional medical image viewer, called StudierFenster. As a result, the Fast GrowCut algorithm can be used directly inside the online environment without installing software and without technical knowledge of the user. It is now possible to use the segmentation tool on any 2-dimensional transverse slice of a 3-dimensional image. The workflow was made user-friendly, allowing input to be drawn with a brush onto the image and loading the output automatically, making it immediately visible.
Keywords: Image Processing
Full text:
Year: 2023