Medical Cell Image Segmentation And Recognition Technology

With the rapid deployment of computer technology, computer image processing and analysis play more and more important role in clinical diagnosis and treatment. The segmentation and recognition methods of medical microscopic cell image become the one-up research task in present image domain. It is absolutely helpful for clinical diagnosis and medical studies of computer-aided cancerous diagnosis system, especially in the case of lack of specialists. In this paper, regarding to the image of immunohistochemical gastric adenocarcinoma, some image segmentation methods of this cell image and the knowledge base of gastric adenocarcinoma cell characteristics are focused on.The key-points of research are listed below:1. Based on colorimetric analysis of image that from the immunohistochemical gastric adenocarcinoma, the result shows that in each pixel of positive cell, the R component is bigger than B component; while the result is just the reverse for the pixel of negative cell. Then following this colorimetric rule, raw division is feasible to get the image of positive cell and negative cell. Then the noise in the image of positive cell is partly removed with smoothing filtering.2. To detect the edge of cells, the Roberts operator, the Sobel operator, the Prewitt operator, the LOG operator and the Canny operator are applied in the image which come from the forward step. When the overlapping cells and adhesive cells are divided with water shed algorithm of range transformation, the over division is always inevitable, then the developed water shed algorithm is applied in the doubtful overlapping areas, to get the relatively proper contour edge of cancer cells.3. Nine measurement parameters such as centroid , area, area rate of karyon and cytoplasm, optic density, cells and karyon shape factor are extracted for further research.4. According to the extraction of figures, the BP neural net method is applied for identification for cells of gastric adenocarcinoma, and gets better discrimination.In our investigations, the efficiency and accuracy of the doctors can be improved efficiently in clinical diagnosis and medical studies, and it is also very significant for adenocarcinoma cell characteristics.