Detection of osteogenesis imperfecta by automated texture analysis

Abstract

An automated system for detecting Osteogenesis Imperfecta (OI), an inheritable disorder of human connective tissue, is described. The approach is one of texture analysis, founded on standard statistical recognition of co-occurrence-based texture descriptors. Our contribution is to show that texture descriptors derived from gray-level co-occurrence matrices can be used in conjunction with descriptors derived from generalized co-occurrence matrices of local image features to increase performance. In fact, for the OI problem, our system demonstrates a level of performance which is significantly better than that of medical specialists.