Automatic count of hepatocytes in microscopic images

Abstract

This paper describes a part of current research work on counting dead and live hepatocytes (liver cells) in cultures from microscopic images. The requirement of the work is to develop an automatic cell counting process that is simple, fast, and achieves high level of count accuracy. Cells in the acquired images are difficult to identify due to low contrast, uneven illumination, gray intensity variations within a cell, irregular cell shapes. For automatic counting, our cell images undergo threestage image processing: conditioning, segmentation, and mathematical morphology operations. Local adaptive thresholding technique is employed in the segmentation stage. At the end of the morphological process, cells are identified and counted based on size. Compared to a manual cell count, the automatic count has achieved an on average accuracy of 95% for single cell counting and 85% for total cell counting.

Detection of mitoses in embryonic epithelia using motion field analysis

“…For example, if cells remain isolated from each other, as they often do in culture, individual cells can be identified by image segmentation and the topological changes associated with the separation of the daughter cells (Bertucco et al 1998;Chen et al 1999;Refai et al 2003;Shimada et al 2005) used to identify mitoses. Alternatively, if adequate contrast exists between the cell boundary and the interiors of cells, then cell boundary algorithms can be used (Vincent and Masters 1992;Talukder and Casasent 1998;Puddister 2003;Phukpattaranont and Boonyaphiphat 2006;Iles et al 2007).…”

Improving reliability of live/dead cell counting through automated image mosaicing

“…In this way, combined with the fact that the KOVA counting chambers are really shallow (i.e., 0.1 mm), the problem of out-of-focus cells [71] is practically negligible. Nevertheless, the very low contrast of the cells [72], especially when they are visualized in brightfield [36], often makes them not easily detectable (Fig. 3).…”

Fuzzy Rule based Classification of Microscopic Images of Squamous Cell Carcinoma of Esophagus

“…Anoraganingrum [5] used a combination of median filter and mathematical morphology operation. Hazem Refai et al [6] used similar approach as of Anoraganingrum [5] for cell segmentation. In this paper, we present a novel method based on active contours for segmentation and fuzzy rule based classification of microscopic images of esophagus tissues obtained from the abnormal regions of human esophagus detected through endoscopy.…”