Quantifying cell scattering: the blob algorithm revisited.
BACKGROUND: A method to objectively quantify cell scattering would permit quantitative evaluation of therapies and compounds intended to affect this physiologic process, which has relevance to normal (e.g., development) and pathologic (e.g., metastasis) events. METHODS: A grid-based modified blob analysis was performed on a set of images of Madin-Darby Canine Kidney (MDCK) cells to quantify the following parameters: the number of cellular clusters in each image, the size of the clusters in terms of pixel counts, and the number of cells in each cluster. These parameters were used as measures of cell scattering and were compared with subjective assessments of scattering made by three experienced examiners. RESULTS: The quantitative parameters correlated strongly to subjective assessments. The algorithm displayed a different concept of "clustering" than the examiners and consistently identified more clusters than did the examiners. There was close agreement in the number of cells counted. All three quantitative parameters correlated strongly to the subjective scattering scores, as follows: cluster count (r(s) = -0.765 to -0.789, P < 0.0001), cluster size in pixels (r(s) = 0.838 to 0.845, P < 0.0001), and cluster size in cells (r(s) = 0.758 to 0.804, P < 0.0001). The parameters were continuous, providing greater resolving power than ordinal subjective scores. CONCLUSIONS: The findings confirmed that our algorithm reproduces the traditional classification of scattering with improved resolution, quantification, and objectivity.