Establishment of Diagnostic Decision Support System (DDSS) in Clinical Diagnosis of Genetic Diseases: The FaceGP DDSS Methodology and Its Applications

Abstract

A face develops under the influence of many genes. Thus, facial appearance can be a significant clue in the initial identification of genetic anomalies associated with especially cognitive impairments. It may be possible to diagnose a good number of syndromes correctly by using computer-assisted face analysis. For dysmorphic syndromes -with - known genetic causes, cyto- and/or molecular genetic analysis is the appropriate route of investigation in order to confirm a diagnosis. In this study, in terms of helping non experienced practitioners in diagnosing process as well as supporting experts in their decisions, we established a methodology to ease the process and we refer to our method as FaceGP DDSS. In the methodology, digital facial image processing methods are used to reveal facial features with disorders indicating genotype-phenotype interrelation. A great number of genetic disorders indicating a characteristic pattern of facial anomalies can be typically identified by analyzing specific features with the aid of facial image processing methods such as PCA in order to determine reference values (eigenfaces) and train the system. Distance algorithms such as Euclidean, Mahalanobis are used to construct the correlation of the input image with the trained images in matching. Some image enhancement methods such as histogram equalization and median filter are implemented on detected degraded images to capture better features. This study proposes a novel computer-assisted and cost-effective method by merging several methods in the characterization of the facial dysmorphology, in particular a method relying primary on face image capture and manipulation to diagnose genetic diseases.