Method and system for digital image based tissue independent simultaneous nucleus cytoplasm and membrane quantitation
A method and system for automatic digital image based tissue independent simultaneous nucleus, cytoplasm and membrane quantitation. Plural types of pixels comprising cell components including at least cell cytoplasm and cell membranes from a biological tissue sample to which a chemical compound has been applied and has been processed to remove background pixels and pixels including counterstained components are simultaneously identified. The identified cell components pixels are automatically classified to determine a medical conclusion such as a human breast cancer, a human prostrate cancer or an animal cancer.
1. An automated method for simultaneously identifying a plurality of pixels in a digital image of a biological tissue stained with a chemical compound, comprising:
considering a first color plane of a plurality of pixels in a foreground of the digital image for simultaneous identification of cell cytoplasm and cell membrane pixels, wherein the digital image has been processed to remove background portions of the digital image and to remove counterstained components of the digital image;
determining a threshold level between cell cytoplasm and cell membrane pixels in the foreground of the digital image; and
determining simultaneously with a selected pixel and its eight neighbors from the foreground if the selected pixel is cell cytoplasm pixel, a cell membrane pixel or a transitional pixel in the digital image using the determined threshold level.
2. The method of claim 1 further comprising a computer readable medium have stored therein instructions for causing a processor to execute the steps of the method.
3. The method claim 1 wherein step of determining simultaneously with a selected pixel and its eight neighbors includes:
determining a square root of a product of the selected pixel with its eight neighboring pixels;
comparing the product to the determined threshold level;
incrementing a first counter for a cell membrane, a second counter for cell cytoplasm or a third counter for transitional pixel based on the comparison;
determining whether the first counter, second counter or third counter exceeds a pre-determined maximum value, and if so, classifying the selected pixel based on a counter that exceeds the predetermined maximum value.
4. The method of claim 1 wherein the step of determining a threshold level includes:
determining a directional property of the selected pixel based on a 3×3 pixel neighborhood on a closed contour, wherein cell membrane pixels form a closed contour enclosing cell cytoplasm and cell nucleus of a cell.
5. The method of claim 4 wherein the step of determining a direction property includes determining a dominance factor D comprising:
D=DConstant*(number of directional pixels/number of uniform pixels), wherein DConstant is a pre-determined constant and wherein the dominance factor D is used to determine whether the selected pixel cell has dominant factors of a cell cytoplasm pixel, a cell membrane pixel or a transitional pixel.