Opening up the “black box” of medical image segmentation with statistical shape models
- 791 Downloads
The importance of medical image segmentation increases in fields like treatment planning or computer aided diagnosis. For high quality automatic segmentations, algorithms based on statistical shape models (SSMs) are often used. They segment the image in an iterative way. However, segmentation experts and other users can only asses the final segmentation results, as the segmentation is performed in a “black box manner”. Users cannot get deeper knowledge on how the (possibly bad) output was produced. Moreover, they do not see whether the final output is the result of a stabilized process.
We present a novel Visual Analytics method, which offers this desired deeper insight into the image segmentation. Our approach combines interactive visualization and automatic data analysis. It allows the expert to assess the quality development (convergence) of the model both on global (full organ) and local (organ areas, landmarks) level. Thereby, local patterns in time and space, e.g., non-converging parts of the organ during the segmentation, can be identified. The localization and specifications of such problems helps the experts creating segmentation algorithms to identify algorithm drawbacks and thus it may point out possible ways how to improve the algorithms systematically.
We apply our approach on real-world data showing its usefulness for the analysis of the segmentation process with statistical shape models.
KeywordsMedical imaging Medical modeling Visual analytics Image segmentation Statistical shape models Spatio-temporal data
The work has been partially supported by the DFG SPP 1335 project “Visual Analytics Methods for Modeling in Medical Imaging”. The authors would like to thank J. Beutel for his support with the project.
- 4.Angelelli, P., Viola, I., Nylund, K., Gilja, O.H., Hauser, H.: Guided visualization of ultrasound image sequences. In: Eurographics Workshop on Visual Computing for Biology and Medicine (VCBM), pp. 125–132 (2010) Google Scholar
- 9.Demšar, U., Fotheringham, A.S., Charlton, M.: Exploring the spatio-temporal dynamics of geographical processes with geographically weighted regression and geovisual analytics. Inf. Vis. 7(3), 181–197 (2008) Google Scholar
- 18.Mayer, et al.: Java SOMToolbox. Online. http://www.ifs.tuwien.ac.at/dm/somtoolbox/index.html, accessed 8/2/2013
- 19.Preim, B., Bartz, D.: Visualization in Medicine: Theory, Algorithms, and Applications. Morgan Kaufmann, San Mateo (2007) Google Scholar
- 22.Silva, S., Madeira, J., Santos, B.: Polymeco—a polygonal mesh comparison tool. In: Proceedings Ninth International Conference on Information Visualisation, 2005, pp. 842–847. IEEE, New York (2005) Google Scholar
- 26.Zhou, L., Pang, A.: Metrics and visualization tools for surface mesh comparison. Ph.D. thesis, University of California, Santa Cruz (2001) Google Scholar