Automated, computerized, feature-based phenotype analysis of slit lamp images of the mouse lens.

摘要: Longitudinal studies of a variety transgenic mouse models for lens development can create substantial challenges in database management and analysis. We report novel, automated, feature-based informatics approach to screening phenotypes large slit lamp images. Digital images normal abnormal lenses eyes wild type (wt), SC1 null SPARC mice were recorded quantitative evaluation their structural phenotype. The processed improve the contrast features that corresponded rings opacity fluctuations scattering intensity lenses. Measurable attributes assigned given as an output vector 46 dimensions. Characteristic patterns correlated with phenotype each mutant wt statistical fit was defined. genotype identified correctly nearly 85% on basis automated computer analysis algorithm has potential evaluate distinguish genotypes objectively using neural network observed is promising technology objective genotype/phenotype relationships based light Further improvements method be expected simplify increase accuracy efficiency feature linked genetic variation.