Feature representation and signal classification in fluorescence in-situ hybridization image analysis

Fast and accurate analysis of fluorescence in-situ hybridization (FISH) images for signal counting will depend mainly upon two components: a classifier to discriminate between artifacts and valid signals of several fluorophores (colors), and well discriminating features to represent the signals. Our previous work has focused on the first component. To investigate the second component, we evaluate candidate feature sets by illustrating the probability density functions (pdfs) and scatter plots for the features. The analysis provides first insight into dependencies between features, indicates the relative importance of members of a feature set, and helps in identifying sources of potential classification errors. Class separability yielded by different feature subsets is evaluated using the accuracy of several neural network (NN)-based classification strategies, some of them hierarchical, as well as using a feature selection technique making use of a scatter criterion. The complete analysis recommends several intensity and hue features for representing FISH signals. Represented by these features, around 90% of valid signals and artifacts of two fluorophores are correctly classifled using the NN. Although applied to cytogenetics, the paper presents a comprehensive, unifying methodology of qualitative and quantitative evaluation of pattern feature representation essential for accurate image classification. This methodology is applicable to many other real-world pattern recognition problems.