MDL Based Structure Selection of Union of Ellipse Models for Scaled and Smoothed Histological Images
In this chapter, we investigate refinements to the structure selection method used in our recently developed minimum description length (MDL) method for interpreting clumps of nuclei in histological images. We start from the SNEF method, which fits elliptical shapes to the clump image based on the extracted contours and on the image gradient information. Introducing some variability in the parameters of the algorithm, we obtain a number of competing interpretations and we select the least redundant interpretation based on the MDL principle, where the description codelengths are evaluated by a simple implementable coding scheme. We investigate in this paper two ways for allowing additional variability in the basic SNEF method: first by utilizing a pre-processing stage of smoothing the original image using various degrees of smoothing and second by using re-scaling of the original image at various downsizing scales. Both transformations have the potential to hide artifacts and features of the original image that prevented the proper interpretation of the nuclei shapes, and we show experimentally that the set of candidate segmentations obtained will contain variants with better MDL values than the MDL of the initial SNEF segmentations. We compare the results of the automatic interpretation algorithm against the ground truth defined by annotations of human subjects.
KeywordsGround Truth Original Image Similarity Index Minimum Description Length Histological Image
Unable to display preview. Download preview PDF.
- 3.Ghido, F., Tabus, I.: Performance of sparse modeling algorithms for predictive coding. In: Proc. of the 18th International Conference on Control Systems and Computer Science (CSCS-18), Bucharest, Romania, May 24-27 (2011)Google Scholar
- 5.Hukkanen, J., Hategan, A., Sabo, E., Tabus, I.: Segmentation of cell nuclei from histological images by ellipse fitting. In: Proc. of the European Signal Processing Conference, Aalborg, Denmark, pp. 1219–1223 (2010)Google Scholar
- 6.Hukkanen, J., Sabo, E., Tabus, I.: Representing clumps of cell nuclei as unions of elliptic shapes by using the MDL principle. In: Proc. of the European Signal Processing Conference, Barcelona, Spain, pp. 1010–1014 (2011)Google Scholar
- 7.Kanungo, T., Dom, B., Niblack, W., Steele, D.: A fast algorithm for MDL-based multi-band image segmentation. In: Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 609–616 (1994)Google Scholar
- 11.Onose, A., Dumitrescu, B.: Sparsity estimation for greedy RLS filters via information theoretic criteria. In: Proc. of the 18th International Conference on Control Systems and Computer Science (CSCS-18), Bucharest, Romania, May 24-27 (2011)Google Scholar
- 12.Ward, J., Cok, D.: Resampling algorithms for image resizing and rotation. In: Proc. SPIE Digital Image Processing Applications, vol. 1075, pp. 260–269 (1989)Google Scholar
- 13.Weinberger, M.J., Seroussi, G., Sapiro, G.: LOCO-I: A low complexity, context-based, lossless image compression algorithm. In: Proc. of the IEEE Data Compression Conference, Snowbird, Utah (1996)Google Scholar