The goal of this master thesis is to implement a method for the the automatic segmentation of mast cells and the segmentation and classification of their cell organelles from 2D electron microscopic recordings. The different tissues we want to segment, are cytoplasm, nucleus, mitochondria, and vesicles. . The segmentation should rely on the texture inside the cells as well as their topology, i.e. the position and shape of an organelle should be considered for the segmentation.

---

Bibliography

[1] M. Keuper, T. Schmidt, M. Rodriguez-Franco, W. Schamel, T. Brox, H. Burkhardt, O. Ronneberger: Hierarchical Markov Random Fields for Mast Cell Segmentation in Electron Microscopic Recordings, Proc. of the ISBI, pages 973-978, 2011.

[2] D. Comanciu, P. Meer: Mean Shift: A Robust Approach Toward Feature Space Analysis, IEEE PAMI, Vol. 24, No. 5, p.603-619, 2002.

[3] P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik: Contour Detection and Hierarchical Image Segmentation, TPAMI 2010.

Kontakt:

Margret Keuper
Raum: 01-022
Telephon: 0761/203-8267
E-Mail: keuper@informatik.uni-freiburg.de


April 2011