Evaluation of protein crystallization states based on texture information derived from greyscale images

In recent years, several projects have advanced research and development related to the automation of the protein crystallization process. However, evaluation of crystallization states has not yet been completely automated. In the usual crystallization process, researchers evaluate the protein crystallization growth states based on visual impressions and assign them a score over and over again. The method presented here automates this evaluation process. This method attempts to categorize the individual crystallization droplet images into five classes. The algorithm is comprised of pre-processing, feature extraction from images using texture analysis and a categorization process using linear discriminant analysis. The performance of this method has been evaluated by comparing the results obtained by using this method with the results from a human expert and the concordance rate was 90.6%.