RESUMEN
Computerized image analysis (IA) can provide quantitative and repeatable object measurements by means of methods such as segmentation, indexation, classification, etc. Embedded in reliable automated systems, IA could help pathologists in their daily work and thus contribute to more accurate determination of prognostic histological factors on whole slide images. One of the key concept pathologists want to dispose of now is a numerical estimation of heterogeneity. In this study, the objective is to propose a general framework based on the diffusion maps technique for measuring tissue heterogeneity in whole slide images and to apply this methodology on breast cancer histopathology digital images.
Asunto(s)
Neoplasias de la Mama/clasificación , Neoplasias de la Mama/patología , Citodiagnóstico/métodos , Interpretación de Imagen Asistida por Computador/métodos , Microscopía/métodos , Reconocimiento de Normas Patrones Automatizadas/métodos , Algoritmos , Femenino , Humanos , Aumento de la Imagen/métodos , Reproducibilidad de los Resultados , Sensibilidad y EspecificidadRESUMEN
Cerebral cavernous malformations (CCMs) are described as vascular lesions consisting of endothelial-lined dilated vessels embedded in a connective tissue sheath without intervening parenchyma between them. Their anatomical connections with the normal blood vessels are still enigmatic and the fine three-dimensional (3-D) organization of these vascular lesions remains to be established. Two stacks of serial histological slices, obtained from two brainstem CCM lesions (from the necropsy of a CCM2 male patient), were stained using Masson's trichrome method and then digitized. Stacks of regions of interest underwent quasi-automatic processing: 1) propagative registering using blockmatching algorithms and Brain Visa programs; 2) 3-D segmentation using Aphelion; 3) display with Anatomist or ImageVis3D. These first histological 3-D reconstructions show the external limits of the caverns defined as the external limit of their collagen sheath. These pictures not only reveal the gross spatial organization of the lesions, but due to their high resolution (4 µm) and with the help of simple anaglyphic 3-D rendering, they also allow the visualization of connections between caverns and very small blood vessels.