Jayanthi.P, Mallika.D
This paper presents a new progressive segmentation for cancer cells of third harmonic microscopic image. This method is based on detection of early diagnosis of cancer cells. The experimental result shows that the proposed algorithm gives Competitive results compared to the previous works deals with watershed transform. Basically biopsy means removal of invasive tissue from a living subject is a time consuming and complicated processes, so non invasive in vivo virtual biopsy, which possesses the ability to obtain exhaustive tissue images without removing tissues, is highly desired. Some sets of in vivo virtual biopsy images provided by healthy volunteers were processed by the proposed cell segmentation approach. This algorithm not only reveals high accuracy for cell segmentation but also has dramatic potential for non-invasive analysis of cell nuclear-to-cytoplasm ratio (NC ratio). The cell nuclear-to-cytoplasm ratios (NC ratios) of epidermis are generally larger in cancer than in normal cells This method indeed saves much time and provides convincing results with interpretation and discussion by medical doctors. Therefore, the method has significant potential for biomedical imaging analysis using MATLAB.
Cell segmentation, Computer tomography, Graph-cut algorithm, Nuclear to Cytoplasm (NC) ratio, Red BloodCells, Third harmonic microscopy, White blood cells