Virtual Mouse Placenta: Tissue Layer Segmentation

Microscopic imaging is an important phenotyping tool to characterize the phenotype (e.g., morphology and behavior) change caused by genotype manipulation such as mutation and gene knockout. Recently we use high resolution microscopic imaging to study the morphological change on mouse placenta induced by retinoblast (Rb) gene knockout. In order to assess the morphological change we first segment each microscopic image into regions corresponding to different tissue types. Due to the complex structure of these tissues and large variation among the more than 2000 images, we design a Bayesian supervised segmentation method which utilizing image features of all levels. The method has been applied to the entire data set and generated satisfactory results that is essential for further analysis on 3-D morphological change of the tissue types

[1]  Jitendra Malik,et al.  Color- and texture-based image segmentation using EM and its application to content-based image retrieval , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[2]  R.M. Haralick,et al.  Statistical and structural approaches to texture , 1979, Proceedings of the IEEE.

[3]  Lani F. Wu,et al.  Multidimensional Drug Profiling By Automated Microscopy , 2004, Science.

[4]  J. Boldys,et al.  Bayesian supervised segmentation of objects in natural images using low-level information , 2003, 3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the.

[5]  Robert F. Murphy,et al.  Robust Numerical Features for Description and Classification of Subcellular Location Patterns in Fluorescence Microscope Images , 2003, J. VLSI Signal Process..

[6]  Z. Werb,et al.  The labyrinthine placenta , 2000, Nature Genetics.