RESUMEN
The heterogeneity of autism spectrum disorders (ASDs) confounds attempts to identify causes and pathogenesis. Identifiable endophenotypes and reliable biomarkers within ASDs would help to focus molecular research and uncover genetic causes and developmental mechanisms. We used dense surface-modelling techniques to compare the facial morphology of 72 boys with ASD and 128 first-degree relatives to that of 254 unrelated controls. Pattern-matching algorithms were able to discriminate between the faces of ASD boys and those of matched controls (AUC=0.82) and also discriminate between the faces of unaffected mothers of ASD children and matched female controls (AUC=0.76). We detected significant facial asymmetry in boys with ASD (P<0.01), notably depth-wise in the supra- and periorbital regions anterior to the frontal pole of the right hemisphere of the brain. Unaffected mothers of children with ASD display similar significant facial asymmetry, more exaggerated than that in matched controls (P<0.03) and, in particular, show vertical asymmetry of the periorbital region. Unaffected fathers of children with ASD did not show facial asymmetry to a significant degree compared to controls. Two thirds of unaffected male siblings tested were classified unseen as more facially similar to unrelated boys with ASD than to unrelated controls. These unaffected male siblings and two small groups of girls with ASD and female siblings, all show overall directional asymmetry, but without achieving statistical significance in two-tailed t-tests of individual asymmetry of ASD family and matched control groups. We conclude that previously identified right dominant asymmetry of the frontal poles of boys with ASD could explain their facial asymmetry through the direct effect of brain growth. The atypical facial asymmetry of unaffected mothers of children with ASD requires further brain studies before the same explanation can be proposed. An alternative explanation, not mutually exclusive, is a simultaneous and parallel action on face and brain growth by genetic factors. Both possibilities suggest the need for coordinated face and brain studies on ASD probands and their first-degree relatives, especially on unaffected mothers, given that their unusual facial asymmetry suggests an ASD susceptibility arising from maternal genes.
Asunto(s)
Trastorno Autístico/genética , Encéfalo/anatomía & histología , Cara/anatomía & histología , Asimetría Facial/genética , Expresión Facial , Adolescente , Adulto , Niño , Preescolar , Femenino , Historia del Siglo XVII , Humanos , Masculino , Madres , HermanosRESUMEN
In a previous paper [Artif. Intell. Med. 5 (1993) 431] we described RaPiD, a knowledge-based system for designing dental prostheses. The present paper discusses how RaPiD has been extended using techniques from computer vision and logic grammars. The first employs point distribution and active shape models (ASMs) to determine dentition from images of casts of patient's jaws. This enables a design to be customized to, and visualised against, an image of a patient's dentition. The second is based on the notion of a path grammar, a form of logic grammar, to generate a path linking an ordered sequence of subcomponents. The shape of an important and complex prosthesis component can be automatically seeded in this fashion. Combining these models now substantially automates the design process, beginning with a photograph of a dental cast and ending with an annotated and validated design diagram ready to guide manufacture.
Asunto(s)
Inteligencia Artificial , Diseño de Prótesis/métodos , Antropometría , Automatización , Humanos , Fotograbar , Programas InformáticosRESUMEN
OBJECTIVES: To evaluate the potential for machine learning techniques to identify objective criteria for classifying vertical facial deformity. METHODS: 19 parameters were determined from 131 lateral skull radiographs. Classifications were induced from raw data with simple visualisation, C5.0 and Kohonen feature maps; and using a Point Distribution Model (PDM) of shape templates comprising points taken from digitised radiographs. RESULTS: The induced decision trees enable a direct comparison of clinicians' idiosyncrasies in classification. Unsupervised algorithms induce models that are potentially more objective, but their blackbox nature makes them unsuitable for clinical application. The PDM methodology gives dramatic visualisations of two modes separating horizontal and vertical facial growth. Kohonen feature maps favour one clinician and PDM the other. Clinical response suggests that while Clinician 1 places greater weight on 5 of 6 parameters, Clinician 2 relies on more parameters that capture facial shape. CONCLUSIONS: While machine learning and statistical analyses classify subjects for vertical facial height, they have limited application in their present form. The supervised learning algorithm C5.0 is effective for generating rules for individual clinicians but its inherent bias invalidates its use for objective classification of facial form for research purposes. On the other hand, promising results from unsupervised strategies (especially the PDM) suggest a potential use for objective classification and further identification and analysis of ambiguous cases. At present, such methodologies may be unsuitable for clinical application because of the invisibility of their underlying processes. Further study is required with additional patient data and a wider group of clinicians.
Asunto(s)
Inteligencia Artificial , Anomalías Maxilofaciales/clasificación , Algoritmos , Interpretación Estadística de Datos , Sistemas de Apoyo a Decisiones Clínicas , Árboles de Decisión , Humanos , Aprendizaje , Anomalías Maxilofaciales/diagnóstico , Anomalías Maxilofaciales/terapia , Intensificación de Imagen Radiográfica , Reino UnidoRESUMEN
This paper describes an evaluation of the application of active shape models to cephalometric landmarking. Permissible deformations of a template were established from a training set of hand-annotated images and the resulting model was used to fit to unseen images. An evaluation of this technique in comparison to the accuracy achieved by previous methods is presented. Sixty-three randomly selected cephalograms were tested using a drop-one-out method. On average, 13 per cent of 16 landmarks were within 1 mm, 35 per cent within 2 mm, and 74 per cent within 5 mm. It was concluded that the current implementation does not give sufficient accuracy for completely automated landmarking, but could be used as a time-saving tool to provide a first-estimate location of the landmarks. The method is also of interest because it provides a framework for a range of future improvements.