Cell phenotype classification using multi threshold uniform local ternary patterns in fluorescence microscope images

Identifying locations of protein expression in live cells plays an important role in several medical applications ranging from early disease diagnosis to monitoring effectiveness of drugs. Protein localization is directly related to their cell types. Today florescence imaging is widely used to understand biology at the cellular level. Hence, cell phenotype classification in fluorescence microscope images, is related with protein localization. Today it is performed by human, which is very time consuming with low accuracy. According to the visual structure, it can be seen that samples of a unique cell type have quite similar texture, but the texture of different cell types, are very different. In this respect, texture information can be used more widely than shape or color information, to classify types. Local ternary pattern is a noise-resistant texture descriptor that provides discriminative features. In this paper a local texture analysis descriptor is proposed titled multi threshold uniform-based local ternary patterns with notation MT-ULTP. MT-ULTP extracts local significant texture information in different locality levels. In this respect, local ternary patterns are extracted in different thresholds and finally the occurrence probability of the uniform patterns is extracted as features. MT-ULTP is a skillful combination of LTP and MLBP with novelty in feature extracting and local pattern selecting. Performance of the proposed descriptor is evaluated on 2d-hela dataset in terms of accuracy. 2d-hela is the benchmark dataset of cell phenotype images. Experimental results show that MT-ULTP provides higher classification rates than very well-known texture descriptors such as lbp-like descriptors. In other experiments, it has been shown that ignoring uniform textural patterns in the image analysis can increase the accuracy of cell phenotype classification and some other computer vision-based applications. The results also showed that extraction uniform patterns based on a combination of thresholds provide better results than the simple form in local ternary patterns. The proposed image texture descriptor is a general case which can be used in many computer vision applications to describe the image contents.