Classification of multicolor fluorescence in-situ hybridization (M-FISH) image using structure based sparse representation model

Abstract

We developed a structure based sparse representation model for classifying chromosomes in M-FISH images. The sparse representation based classification model used in our previous work only considered one pixel without incorporating any structural information. The new proposed model extends the previous one to multiple pixels case, where each target pixel together with its neighboring pixels will be used simultaneously for classification. We also extend Orthogonal Matching Pursuit (OMP) algorithm to the multiple pixels case, named simultaneous OMP algorithm (SOMP), to solve the structure based sparse representation model. The classification results show that our new model outperforms the previous sparse representation model with the p-value less than le-6. We also discussed the effects of several parameters (neighborhood size, sparsity level, and training sample size) on the accuracy of the classification. Our proposed method can be affected by the sparsity level and the neighborhood size but is insensitive to the training sample size. Therefore, the comparison indicates that the structure based sparse representation model can significantly improve the accuracy of the chromosome classification, leading to improved diagnosis of genetic diseases and cancers.