The knowledge of the lumbar spine biomechanics is essential for clinical applications. Due to the difficulties to experiment on living people and the irregular results published, simulation based on finite elements (FE) has been developed, making it possible to adequately reproduce the biomechanics of the lumbar spine. A 3D FE model of the complete lumbar spine (vertebrae, discs, and ligaments) has been developed. To verify the model, radiological images (X-rays) were taken over a group of 25 healthy, male individuals with average age of 27.4 and average weight of 78.6 kg with the corresponding informed consent. A maximum angle of 34.40° is achieved in flexion and of 35.58° in extension with a flexion-extension angle of 69.98°. The radiological measurements were 33.94 ± 4.91°, 38.73 ± 4.29°, and 72.67°, respectively. In lateral bending, the maximum angles were 19.33° and 23.40 ± 2.39, respectively. In rotation a maximum angle of 9.96° was obtained. The model incorporates a precise geometrical characterization of several elements (vertebrae, discs, and ligaments), respecting anatomical features and being capable of reproducing a wide range of physiological movements. Application to disc degeneration (L5-S1) allows predicting the affection in the mobility of the different lumbar segments, by means of parametric studies for different ranges of degeneration.
1 October 2007 in Revista Española de Medicina Nuclear
Purpose: The macular ganglion cell layer (mGCL) is a strong potential biomarker of axonal degeneration in multiple sclerosis (MS). For this reason, this study aims to develop a computer‐aided method to facilitate diagnosis and prognosis in MS.Methods: This paper combines a cross‐sectional study of 72 MS patients and 30 healthy control subjects for diagnosis and a 10‐year longitudinal study of the same MS patients for the prediction of disability progression, during which the mGCL was measured using optical coherence tomography (OCT). Deep neural networks were used as an automatic classifier.Results: For MS diagnosis, greatest accuracy (90.3%) was achieved using 17 features as inputs. The neural network architecture comprised the input layer, two hidden layers and the output layer with softmax activation. For the prediction of disability progression 8 years later, accuracy of 81.9% was achieved with a neural network comprising two hidden layers and 400 epochs.Conclusion: We present evidence that by applying deep learning techniques to clinical and mGCL thickness data it is possible to identify MS and predict the course of the disease. This approach potentially constitutes a non‐invasive, low‐cost, easy‐to‐implement and effective method.
1 July 2012 in Revista Española de Medicina Nuclear e Imagen Molecular (English Edition)