Slice Based 3d Cell Segmentation Of Optical Projection Tomography Images

Optical Projection Tomography (OPT) is a new imaging technique used to image cellsrnin 3D cultured in a hydrogel. Reconstructed OPT images of cells suffer from severalrnartifacts. These artifacts reduce the overall image quality. This will create a challengernfor isolating and studying each cell in 3D cell culture. It is highly required to enhance thern3D OPT images of cells for successful analysis of cell interaction and growth in 3D cellrnculture. In that regard, this thesis intends to build a robust algorithm for use in effectivernsegmentation of cells cultured inside hydrogel. There exist various 3D cell segmentationrnalgorithms in the literature including those schemes that rely on thresholding, edgerndetection, region growing and clustering approaches. Among these algorithms, movingrnaverage adaptive thresholding (MAAT) and region growing algorithm present commendablernperformance in segmentation of cells identified on OPT images. In this thesis thernperformance of an automatic seeded region growing algorithm (ASRGA) and MAAT havernbeen compared rigorously in terms of their use in 2D slice based segmentation of the cellsrnon the 3D OPT image sets considered. Results have shown that the MAAT method showrnsuperior performance and provide promising 3D visualization of cells. The output of thernresearch will have a tremendous contribution to reduce artifacts in 3D cell images andrnenhance 3D visualization.

Get Full Work

Report copyright infringement or plagiarism