Scope
A very important clue for the diagnosis of neuromuscular diseases is the histological characterization of biopsy samples. However, the morphological analyses of muscle biopsies are mostly subjective and hard to quantify.
We present a method that captures the useful information contained in a muscle biopsy. The method characterizes muscular tissues by representing each image as a network with cells as nodes and cell contacts as links. The features of individual cells and the attributes of the cellular network that connects them, produce a defining signature for each image. The method allows us to classify and quantify the degree of affection of each sample providing objective useful information for the diagnosis.
Collaborations
Fundación Pública Andaluza para la Gestión de la Investigación en Salud de Sevilla (FISEVI)
Hospitales Universitarios Virgen del Rocío
Instituto de Biomedicina de Sevilla (IBIS)
Images
