This article describes the development of a quantitative method for computer-aided diagnosis (CAD) of intervertebral disc degeneration according to Pfirrmann's scale, a semiquantitative scale with five degrees of degeneration, in T2weighted magnetic resonance images of the lumbar spine. The dataset consists of images of 210 discs obtained from 42 healthy individuals. The intervertebral discs were assigned Pfirrmann's grades based on independent and blind classification. Binary masks of manually segmented discs were used to compute the centroids of the regions, estimate the curvature of the spine by polynomial fitting, normalize intensities, and extract regions of interest. Texture analysis was performed using Haralick's features and moments were computed for each disc. Classification was performed using an artificial neural network using the full vectors of attributes as well as a reduced set obtained using gradient ascent search. An average true-positive rate of 75.2% and an average area under the receiver operating characteristic curve of 0.78 indicate potential application of this technique for CAD of spinal pathology.
Agradeço primeiramente a Deus por sempre guiar meus passos e iluminar meus caminhos. À minha amada esposa, pelo apoio e paciência, sendo uma fonte de inspiração e companheirismo.À minha filha, que com seus abraços amorosos, renovavam meus ânimos.Aos meus pais pelo apoio e ajuda nas horas difíceis mesmo que à distância.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.