Accurate Automatic Spot Addressing for Microarray Images

In this paper a novel procedure based on texture spatial characterization techniques is proposed aimed at automatically addressing spots in microarray images. The algorithm relies on the regular and pseudo-periodic patterns of spots, which can be considered as texture primitives. A fully automatic procedure is proposed to segment the autocorrelation functions of subgrid images and accurately determine the locations of the peaks. These candidate peaks, i.e., vectors, are next used to compute the displacement vectors that fully characterize the spatial arrangement of spots, describing the spot spacing and angle of rotation of the pattern. A refinement procedure is then applied to improve the accuracy of the norms and angles of the displacement vectors. An ideal template is generated using the computed spanning vectors, which is deformed and adjusted via Markov Random Fields (MRF) modelling. Experiments based on artificial and real images are promising, showing improvements regarding robustness against image rotations, and accuracy, over results provided by state-of-the-art methods.