SmartPaint: a tool for interactive segmentation of medical volume images. Issue 1 (2nd January 2017)

• Record Type: Journal Article
• Authors: Malmberg, Filip; Nordenskjöld, Richard; Strand, Robin; Kullberg, Joel
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 5:Issue 1(2017)
• Page Start: 36
• Page End: 44
• Publication Date: 2017-01-02
• Subjects: image segmentation -- medical imaging -- interactive segmentation; Imaging systems in biology -- Periodicals; Imaging systems in medicine -- Periodicals; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; 616.0757
• DOI: 10.1080/21681163.2014.960535
• Languages: English
• ISSNs: 2168-1163

Abstract

Abstract : We present SmartPaint, a general-purpose method and software for interactive segmentation of medical volume images. SmartPaint uses a novel paint-brush interaction paradigm, where the user segments objects in the image by 'sweeping' over them with the mouse cursor. The key feature of SmartPaint is that the painting tools adapt to the image content, selectively sticking to objects of interest while avoiding other structures. This behaviour is achieved by modulating the effect of the tools by both the Euclidean distance and the range distance (difference in image intensity values) from the mouse cursor. We evaluate SmartPaint on three publicly available medical image datasets, covering different image modalities and segmentation targets. The results show that, with a limited user effort, SmartPaint can produce segmentations whose accuracy is comparable to both the state-of-the-art automatic segmentation methods and manual delineations produced by expert users. The SmartPaint software is freely available, and can be downloaded from the authors' web page (http://www.cb.uu.se/~filip/SmartPaint/ ).