Computerized detection of laryngopharyngeal reflux
A method and apparatus for determining a likelihood of LPR by analyzing a laryngeal cell preparation. The laryngeal sample is fixed on a microscope slide and analyzed by a microscope combined with an image acquisition system and a computer having an image recognition system. The image recognition system detects mobile cells that are implicated in the body's inflammatory response and counts how many of such cells are on the slide. The computer generates an absolute number of such cells and percentage values for such cells out the total number of mobile cells classified. The computer then utilizes the absolute numbers, the ratios of mobile cells with respect to each other—or a combination of both to generate a score. The score represents a probabilistic determination of inflammation.
1. A method of determining a presence of laryngopharyngeal reflux, comprising the steps of:
examining a slide comprising a laryngeal cellular sample with a microscope combined with an image acquisition system;
acquiring images of cells in said laryngeal cellular sample;
analyzing said images of said cells with an image recognition system to detect at least two types of mobile cells;
counting individual cells of each of said at least two types of mobile cells;
generating at least two sums from said counts, each of said sums representing a number of individual cells;
comparing each of said sums to an average number of expected cells for each of said cell types; and
generating a score based on said comparison, said score indicating a likelihood of inflammation.
2. The method of claim 1 , wherein said at least two types of mobile cells comprise PMNs and lymphocytes.
3. The method of claim 1 , further comprising the step of adding the sums from said counts to generate a sum of combined mobile cells and determining a percentage value for each cell type, said percentage value representing a percentage of a mobile cell type out of a sum of combined mobile cells.
4. The method of claim 3 , wherein percentage values for at least two cell types and sums of individual cell numbers of said at least two cell types are combined to generate said score.
5. A method of determining a presence of laryngopharyngeal reflux, comprising the steps of:
examining a slide comprising a laryngeal cellular sample with a microscope combined with an image acquisition system;
acquiring images of cells in said laryngeal cellular sample;
analyzing said images of said cells with an image recognition system to detect at least first mobile cell type and a second mobile cell type;
counting individual cells of each of said first mobile cell type and said second mobile cell type;
calculating a total number of mobile cells on said slide;
generating a first percentage value, said first percentage value corresponding to a percentage of said first mobile cell type out of said total number of mobile cells;
generating a second percentage value, said second percentage value corresponding to a percentage of said second mobile cell type out of said total number of mobile cells;
comparing said first percentage value to a first expected value and comparing said second percentage value to said to a second expected percentage value; and
generating a score based on said comparisons, said score indicating a likelihood of inflammation.
6. The method of claim 5 , whereby said mobile cells first mobile cell type comprises lymphocytes and said second cell type comprises PMNs.
7. A method of determining a presence of laryngopharyngeal reflux, comprising the steps of:
examining a slide comprising a laryngeal cellular sample with a microscope combined with an image acquisition system;
acquiring images of cells in said laryngeal cellular sample;
analyzing said images of said cells with an image recognition system to detect at least a first mobile cell type and a second mobile cell type;
analyzing said images of said cells with an image recognition system to detect at least two epithelial cell types;
counting individual cells of said first mobile cell type and said second mobile cell type;
counting individual cells of said first epithelial cell type and said second epithelial cell type cell type;
calculating a total number of mobile cells on said slide;
calculating a total number of epithelial cells on said slide;
generating a first percentage value, said first percentage value corresponding to a percentage of said first mobile cell type out of said total number of mobile cells;
generating a second percentage value, said second percentage value corresponding to a percentage of said first epithelial cell type out of said total number of epithelial cells;
comparing said first percentage value to a first expected value and comparing said second percentage value to said to a second expected percentage value; and
generating a score based on said comparisons, said score indicating a likelihood of inflammation.
8. The method of claim 7 , whereby said first mobile cell type is lymphocytes and said first epithelial cell type is superficial epithelial cells.
9. The method of claim 8 , whereby said first mobile cell type is lymphocytes and said first epithelial cell type is basal cells.