Efficient GPU-based Gridding and Segmentation of Microarray Images via K-Means and Fuzzy C-Means

The analysis of microarray image helps in identifying new genes that enables us to understand their functions and gene expression levels simultaneously at different conditions. This is also useful in diagnosing the various diseases and helps in develop the treatment for the required disease. In general it has 3 stages, the first one is gridding, and the second segmentation and the third one is intensity extraction. In this paper we are going to discuss various machine learning techniques in segmenting the microarray images. This proposed algorithm eliminates the noise and enhances the image quality by finding the nearest spots in segmentation and enhancing the spot using KNN algorithm. The performance can be improved further by the efficient utilization of a graphics processing unit (GPU). It is also shown that the method can be employed to produce a model on health based on a PET-MRI dataset which can be utilized to automatically detect pathology in the imaging.