Search

Alcohol use disorder (AUD) is a complex condition representing a leading risk factor for death, disease and disability. Its high prevalence and severe health consequences make necessary a better understanding of the brain network alterations to improve diagnosis and treatment. The purpose of this study was to evaluate the potential of resting-state fMRI 3D texture features as a novel source of biomarkers to identify AUD brain network alterations following a radiomics approach. A longitudinal study was conducted in Marchigian Sardinian alcohol-preferring msP rats (N = 36) who underwent resting-state functional and structural MRI before and after 30 days of alcohol or water consumption. A cross-sectional human study was also conducted among 33 healthy controls and 35 AUD patients. The preprocessed functional data corresponding to control and alcohol conditions were used to perform a probabilistic independent component analysis, identifying seven independent components as resting-state networks. Forty-three radiomic features extracted from each network were compared using a Wilcoxon signed-rank test with Holm correction to identify the network most affected by alcohol consumption. Features extracted from this network were then used in the machine learning process, evaluating two feature selection methods and six predictive models within a nested cross-validation structure. The classification was evaluated by computing the area under the ROC curve. Images were quantized using different numbers of gray-levels to test their influence on the results. The influence of ageing, data preprocessing, and brain iron accumulation were also analyzed. The methodology was validated using structural scans. The striatal network in alcohol-exposed msP rats presented the most significant number of altered features. The radiomics approach supported this result achieving good classification performance in animals (AUC = 0.915 ± 0.100, with 12 features) and humans (AUC = 0.724 ± 0.117, with

[EN] Introduction: The pathophysiological process of Alzheimer's disease is thought to begin years before clinical decline, with evidence suggesting prion-like spreading processes of neurofibrillary tangles and amyloid plaques. Methods: Using diffusion magnetic resonance imaging data from the Alzheimer's Disease Neuroimaging Initiative database, we first identified relevant features for dementia diagnosis. We then created dynamic models with the Nathan Kline Institute-Rockland Sample database to estimate the earliest detectable stage associated with dementia in the simulated disease progression. Results: A classifier based on centrality measures provides informative predictions. Strength and closeness centralities are the most discriminative features, which are associated with the medial temporal lobe and subcortical regions, together with posterior and occipital brain regions. Our model simulations suggest that changes associated with dementia begin to manifest structurally at early stages. Discussion: Our analyses suggest that diffusion magnetic resonance imaging-based centrality measures can offer a tool for early disease detection before clinical dementia onset.

[EN] The study of resting-state functional brain networks is a powerful tool to understand the neurological bases of a variety of disorders such as Autism Spectrum Disorder (ASD). In this work, we have studied the differences in functional brain connectivity between a group of 74 ASD subjects and a group of 82 typical-development (TD) subjects using functional magnetic resonance imaging (fMRI). We have used a network approach whereby the brain is divided into discrete regions or nodes that interact with each other through connections or edges. Functional brain networks were estimated using the Pearson's correlation coefficient and compared by means of the Network-Based Statistic (NBS) method. The obtained results reveal a combination of both overconnectivity and underconnectivity, with the presence of networks in which the connectivity levels differ significantly between ASD and TD groups. The alterations mainly affect the temporal and frontal lobe, as well as the limbic system, especially those regions related with social interaction and emotion management functions. These results are concordant with the clinical profile of the disorder and can contribute to the elucidation of its neurological basis, encouraging the development of new clinical approaches.

El cerebro está constituido por numerosos elementos que se encuentran interconectados de forma masiva y organizados en módulos que forman redes jerárquicas. Ciertas patologías cerebrales, como la enfermedad de Alzheimer y el trastorno por consumo de alcohol, se consideran el resultado de efectos en cascada que alteran la conectividad cerebral. La presente tesis tiene como objetivo principal la aplicación de las técnicas de análisis de la ciencia de redes para el estudio de las redes estructurales y funcionales en el cerebro, tanto en un estado control como en un estado patológico. Así, en el primer estudio de la presente tesis se examina la relación entre la conectividad estructural y funcional en la corteza cerebral de la rata. Se lleva a cabo un análisis comparativo entre las conexiones estructurales en la corteza cerebral de la rata y los valores de correlación calculados sobre las mismas regiones. La información acerca de la conectividad estructural se ha obtenido a partir de estudios previos, mientras que la conectividad funcional se ha calculado a partir de imágenes de resonancia magnética funcional. Determinadas propiedades topológicas, y extraídas de la conectividad estructural, se relacionan con la organización modular de las redes funcionales en estado de reposo. Los resultados obtenidos en este primer estudio demuestran que la conectividad estructural y funcional cortical están altamente relacionadas entre sí. Estudios recientes sugieren que el origen de la enfermedad de Alzheimer reside en un mecanismo en el cual depósitos de ovillos neurofibrilares y placas de beta-amiloide se acumulan en ciertas regiones cerebrales, y tienen la capacidad de diseminarse por el cerebro actuando como priones. En el segundo estudio de la presente tesis se investiga si las redes estructurales que se generan con la técnica de resonancia magnética ponderada en difusión podrían ser de utilidad para el diagnóstico de la pre-demencia causada por la enfermedad de Alzheimer. Media, The brain is composed of massively connected elements arranged into modules that form hierarchical networks. Experimental evidence reveals a well-defined connectivity design, characterized by the presence of strategically connected core nodes that critically contribute to resilience and maintain stability in interacting brain networks. Certain brain pathologies, such as Alzheimer's disease and alcohol use disorder, are thought to be a consequence of cascading maladaptive processes that alter normal connectivity. These findings have greatly contributed to the development of network neuroscience to understand the macroscopic organization of the brain. This thesis focuses on the application of network science tools to investigate structural and functional brain networks in health and disease. To accomplish this goal, three specific studies are conducted using human and rodent data recorded with MRI and tracing technologies. In the first study, we examine the relationship between structural and functional connectivity in the rat cortical network. Using a detailed cortical structural matrix obtained from published histological tracing data, we first compare structural connections in the rat cortex with their corresponding spontaneous correlations extracted empirically from fMRI data. We then show the results of this comparison by relating structural properties of brain connectivity to the functional modularity of resting-state networks. Specifically, we study link reciprocity in both intra- and inter-modular connections as well as the structural motif frequency spectrum within functionally defined modules. Overall, our results provide further evidence that structural connectivity is coupled to and shapes functional connectivity in cortical networks. The pathophysiological process of Alzheimer's disease is thought to begin years before clinical decline, with evidence suggesting pahtogenic seeding and subsequent prion-like spreading processes of neurofibrillary tangles and, El cervell està constituït per nombrosos elements que es troben interconnectats de forma massiva i organitzats en mòduls que formen xarxes jeràrquiques. Certes patologies cerebrals, com la malaltia d'Alzheimer i el trastorn per consum d'alcohol, es consideren el resultat d'efectes en cascada que alteren la connectivitat cerebral. La present tesi té com a objectiu principal l'aplicació de les tècniques d'anàlisi de la ciència de xarxes per a l'estudi de les xarxes estructurals i funcionals en el cervell, tant en un estat control com en un estat patològic. Així, en el primer estudi de la present tesi s'examina la relació entre la connectivitat estructural i funcional en l'escorça cerebral de la rata. Es du a terme una anàlisi comparativa entre les connexions estructurals en l'escorça cerebral de la rata i els valors de correlació calculats sobre les mateixes regions. La informació sobre la connectivitat estructural s'ha obtingut a partir d'estudis previs, mentre que la connectivitat funcional s'ha calculat a partir d'imatges de ressonància magnètica funcional. Determinades propietats topològiques, i extretes de la connectivitat estructural, es relacionen amb l'organització modular de les xarxes funcionals en estat de repòs. Els resultats obtinguts en este primer estudi demostren que la connectivitat estructural i funcional cortical estan altament relacionades entre si. Estudis recents suggereixen que l'origen de la malaltia d'Alzheimer resideix en un mecanisme en el qual depòsits d'ovulets neurofibrilars i plaques de beta- miloide s'acumulen en certes regions cerebrals, i tenen la capacitat de disseminar-se pel cervell actuant com a prions. En el segon estudi de la present tesi s'investiga si les xarxes estructurals que es generen amb la tècnica de la imatge per ressonància magnètica ponderada en difusió podrien ser d'utilitat per al diagnòstic de la predemència causada per la malaltia d'Alzheimer. Per mitjà de l'ús d'imatges procedents de la base de dades ADNI, s'apl

[ES] El trastorno del espectro autista (TEA) es un desorden de tipo neurológico cuya prevalencia se ha visto enormemente incrementada en los últimos años, hecho probablemente condicionado a las mejoras en las metodologías diagnósticas, pero que no deja de resultar alarmante. A pesar de su prevalencia, y al igual que ocurre con muchos otros trastornos de tipo neurológico o psiquiátrico, las bases neurológicas del TEA aún no han sido completamente esclarecidas. El objetivo del presente Trabajo Final de Máster es evaluar el potencial de distintas técnicas de aprendizaje automático en el diagnóstico del TEA a partir del análisis de imagen de resonancia magnética funcional en estado de reposo. Dicho de otra manera, dado un conjunto de imágenes cerebrales, deseamos conocer si es posible discriminar aquellos sujetos con TEA de aquellos sujetos de referencia o controles. Para ello se analizarán un total de 157 sujetos (75 sujetos con TEA y 82 controles) de la base de datos ABIDE (Autism Brain Imaging Data Exchange). Para llevar a cabo este estudio, la herramienta de software escogida ha sido Matlab®. Para abordar dicho objetivo, en primer lugar, y para cada uno de los sujetos incluidos en el estudio, se calculará la conectividad funcional, cuantificada a partir del coeficiente de correlación de Pearson, entre cada par de regiones cerebrales a partir de la señal temporal BOLD. Después se llevará a cabo un análisis comparativo previo en un subconjunto de sujetos haciendo uso de la Network-Based Statistic Toolbox (NBS). Este análisis de la conectividad nos proporcionará una serie de enlaces entre regiones que muestran diferencias significativas entre grupos y que, por tanto, resultan clave para determinar el patrón de conectividad funcional asociado al TEA. Los valores de conectividad funcional de cada uno de los enlaces que muestran diferencias significativas entre los dos grupos se utilizarán como características para la clasificación del subconjunto restante de sujetos. Así, [EN] The Autism Spectrum Disorder (ASD) is a neurological disorder with an increasing prevalence, and even though this growth is probably related to the improvements in diagnostic methodologies, the increase in the number of ASD diagnosed patients is an alarming fact. Despite its prevalence, and as it happens in many other neurological and psychiatric disorders, the neurological basis of the ASD have not been completely established yet. The aim of this work is to evaluate the potential of machine learning techniques in ASD diagnosis based on the analysis of resting state functional magnetic resonance images. In other words, we want to determine if it is possible, having a set of brain images, to determine which subjects have ASD, and which ones are subjects with a neurotypical development, or control subjects. In order to address this problem, we have analyzed images pertaining to 157 subjects (75 with ASD and 82 controls) obtained from ABIDE (Autism Brain Imaging Data Exchange). The analysis of these images has been performed using Matlab. To achieve this target, the first step is to obtain the functional brain connectivity for each one of the subjects in the study, using Pearson¿s correlation coefficient of BOLD signal between every pair of regions of the brain. Then, we will perform a comparative analysis in a subset of patients using the Network-Based Statistic Toolbox (NBS). This connectivity analysis will provide us with a group of connections among different regions that usually appear significantly altered in one of the groups, and that are therefore key brain alterations in order to determine the ASD characteristic pattern. The obtained set of altered connections will be used as features to classify the remaining subset of patients. Therefore, we will apply several classification techniques, such as k-Nearest Neighbors (KNN), Support Vector Machines (SVMs) or Artificial Neural Networks, to produce a predictive model that distinguishes between images pertain

[EN] Alcohol use disorders (AUD) are a major public health concern. Understanding the brain network alterations is of the utmost importance to diagnose and develop treatment strategies. Employing resting-state functional magnetic resonance imaging, we have performed a longitudinal study in a rat model of chronic excessive alcohol consumption, to identify functional alterations in brain networks triggered by alcohol drinking. Two time points were considered: 1) before alcohol consumption (control condition) and 2) after 30 days of alcohol drinking (alcohol condition). We first identified nine resting-state networks with group independent component analysis. Afterwards, dual regression was applied to obtain subject-specific time courses and spatial maps. L2-regularized partial correlation analysis between pairs of networks showed that functional connectivity (FC) between the retrosplenial-visual and striatal networks decreases due to alcohol consumption, whereas FC between the prefrontal-cingulate and striatal networks increases. Analysis of subject-specific spatial maps revealed FC decreases within networks after alcohol drinking, including the striatal, motor-parietal, prefrontal-cingulate, retrosplenial-visual and left motor-parietal networks. Overall, our results unveil a generalized decrease in brain FC induced by alcohol drinking in genetically predisposed animals, even after a relatively short period of exposure (1 month). The only exception to this hypo-connectivity state is the functional association between the striatal and prefrontal-cingulate networks, which increases after drinking, supporting evidence in human alcoholics.

[EN] Purpose: The development of automatic and reliable algorithms for the detection and segmentation of the vertebrae are of great importance prior to any diagnostic task. However, an important problem found to accurately segment the vertebrae is the presence of the ribs in the thoracic region. To overcome this problem, a probabilistic atlas of the spine has been developed dealing with the proximity of other structures, with a special focus on ribs suppression. Methods: The data sets used consist of Computed Tomography images corresponding to 21 patients suffering from spinal metastases. Two methods have been combined to obtain the final result: firstly, an initial segmentation is performed using a fully automatic level-set method; secondly, to refine the initial segmentation, a 3D volume indicating the probability of each voxel of belonging to the spine has been developed. In this way, a probability map is generated and deformed to be adapted to each testing case. Results: To validate the improvement obtained after applying the atlas, the Dice coefficient (DSC), the Hausdorff distance (HD), and the mean surface-to-surface distance (MSD) were used. The results showed up an average of 10 mm of improvement accuracy in terms of HD, obtaining an overall final average of 15.51 2.74 mm. Also, a global value of 91.01 3.18% in terms of DSC and a MSD of 0.66 0.25 mm were obtained. The major improvement using the atlas was achieved in the thoracic region, as ribs were almost perfectly suppressed. Conclusion: The study demonstrated that the atlas is able to detect and appropriately eliminate the ribs while improving the segmentation accuracy.

[EN] Identification of brain states measured with electrophysiological methods such as electroencephalography and local field potential (LFP) recordings is of great importance in numerous neuroscientific applications. For instance, in Brain Computer Interface, in the diagnosis of neurological disorders as well as to investigate how brain rhythms stem from synchronized physiological mechanisms (e.g., memory and learning). In this work, we propose a fully automated method with the aim of partitioning LFP signals into stationary segments as well as classifying each detected segment into three different classes (delta, regular theta or irregular theta rhythms). Our approach is computationally efficient since the process of detection and partition of signals into stationary segments is only based on two features (the variance and the so-called spectral error measure) and allow the classification at the same time. We developed the algorithm upon analyzing six anesthetized rats, resulting in a true positive rate of 97.5%, 91.8% and 79.1% in detecting delta, irregular theta and regular theta rhythms, respectively. This preliminary quantitative evaluation offers encouraging results for further research.

[EN] Connectomics data from animal models provide an invaluable opportunity to reveal the complex interplay between structure and function in the mammalian brain. In this work, we investigate the relationship between structural and functional connectivity in the rat brain cortex using a directed anatomical network generated from a carefully curated meta-analysis of published tracing data, along with resting-state functional MRI data obtained from a group of 14 anesthetized Wistar rats. We found a high correspondence between the strength of functional connections, measured as blood oxygen level dependent (BOLD) signal correlations between cortical regions, and the weight of the corresponding anatomical links in the connectome graph (maximum Spearman rank-order correlation rho = 0.48). At the network-level, regions belonging to the same functionally defined community tend to form more mutual weighted connections between each other compared to regions located in different communities. We further found that functional communities in resting-state networks are enriched in densely connected anatomical motifs. Importantly, these higher-order structural subgraphs cannot be explained by lower-order topological properties, suggesting that dense structural patterns support functional associations in the resting brain. Simulations of brain-wide resting-state activity based on neural mass models implemented on the empirical rat anatomical connectome demonstrated high correlation between the simulated and the measured functional connectivity (maximum Pearson correlation rho = 0: 53), further suggesting that the topology of structural connections plays an important role in shaping functional cortical networks.

[EN] The use of functional magnetic resonance imaging (fMRI) to measure spontaneous fluctuations in blood oxygen level dependent (BOLD) signals has become an indispensable tool to investigate how brain regions interact and form longrange networks. Statistical dependency measures between brain regions obtained from BOLD signals can inform about brain functional states in longitudinal studies of neurological and psychiatric disorders. Furthermore, its non-invasive nature allows comparable measurements in clinical and animal studies, providing excellent translational capabilities. In the present study, we apply Network-Based Statistic (NBS) to investigate alterations in the functional connectivity (FC) of the rat brain in a post-dependent (PD) state, an established animal model of clinical relevant features in alcoholism. In contrast to mass-univariate tests, in which comparisons are performed at single link-level, NBS enhances the statistical power by assuming that the connections comprising the effect of interest are interconnected. Brain-wide resting-state fMRI signals were collected in 14 controls and 13 PD rats, and Pearson correlations computed between 47 brain regions of interest (ROIs). The NBS analysis revealed statistically significant differences in a connected network of structures including hippocampus, amygdala, lateral hypothalamus and the raphe nucleus, all regions with known relevance for addictive behaviors. In contrast, no individual connection could be found significant by univariate comparisons with false discovery rate (FDR) correction. Correlations between the structures in the identified subnetwork tend to decrease or become negative (anti-correlated) in the PD state compared to controls. We interpret this result as evidence for a disconnected subnetwork in the PD state.

[ES] El trastorno del espectro autista es un desorden de tipo neurológico cuya prevalencia se ha visto enormemente incrementada en los últimos años, hecho probablemente condicionado a las mejoras en las metodologías diagnósticas, pero que no deja de resultar alarmante. A pesar de su prevalencia, y al igual que ocurre con muchos otros trastornos de tipo neurológico o psiquiátrico, las bases neurológicas del trastorno del espectro autista aún no han sido completamente esclarecidas. En el presente Trabajo Fin de Grado, se ha analizado un conjunto de imágenes de resonancia magnética funcional en estado de reposo con el objetivo de determinar si existen o no diferencias significativas en la conectividad funcional cerebral entre sujetos afectados por el trastorno y sujetos sanos (o control). Para extraer conclusiones a partir de dichas imágenes, se ha utilizado la herramienta de software Matlab, así como diversas toolbox para la misma que han permitido realizar un análisis estadístico de los datos y visualizar los resultados. En total, se han examinado imágenes correspondientes a 183 pacientes, de los cuales 79 pertenecían al grupo autista y 104 al grupo control, y procedentes de la base de datos de ABIDE (Autism Brain Imaging Data Exchange). El análisis se ha llevado a cabo desde el punto de vista de la teoría de grafos y la ciencia de redes, y por tanto, el cerebro ha sido modelado como una red, dividida en nodos que interaccionan entre sí a través de enlaces. Para la segmentación en distintas regiones cerebrales, se ha utilizado la parcelación AAL (Automated Anatomical Labeling), de 116 regiones y definida en base a criterios anatómicos. Para extraer la conectividad cerebral funcional en ambos grupos, se ha utilizado el coeficiente de correlación de Pearson de la señal temporal BOLD, que se ha obtenido para cada par de regiones de la parcelación en un conjunto de matrices de conectividad. Los resultados extraídos muestran que dentro de la red cerebral existen tanto sub, [EN] The Autism Spectrum Disorder (ASD) is a neurological disorder with an increasing prevalence, and even though this grow is probably related to the improvements in diagnostic methodologies, the increase in the number of ASD diagnosed patients is an alarming fact. Despite its prevalence, and as it happens in many other neurological and psychiatric disorders, the neurological basis of the ASD have not been completely established yet. In the present work, a set of resting state functional magnetic resonance images has been analyzed in order to determine if significant differences in brain functional connectivity between an autistic group and a control group of non-ASD affected subjects can be found. To reach conclusions from these images, the software tool Matlab and several toolboxes for it have been used. This tools have allowed a statistical analysis of the data and a visualization of the obtained results. The set contains images of 183 patients, of whom 79 belong to the autistic group and 104 belong to control group, that have been obtained from the ABIDE (Autism Brain Imaging Data Exchange) database. To perform the analysis, the graph theory and network science approach have been used, and the brain has been modeled as a network divided in several nodes connected through edges. The AAL (Automated Anatomical Labeling) atlas has been used to divide the brain in 116 ROIs (Region of Interest) based on anatomical criteria. In order to determine the functional connectivity of both autistic and control groups, the Pearson correlation coefficient of the BOLD signal has been used. This coefficient has been obtained for every single pair of brain regions, and has been stored in a set of connectivity matrices. The obtained results show both increased and reduced connectivity in autistic patients. This results agree with the clinical profile of the disorder, and may contribute to establish the neurological basis of the ASD, fact that will boost the development of new clini

Spine is a structure commonly involved in several prevalent diseases. In clinical diagnosis, therapy, and surgical intervention, the identification and segmentation of the vertebral bodies are crucial steps. However, automatic and detailed segmentation of vertebrae is a challenging task, especially due to the proximity of the vertebrae to the corresponding ribs and other structures such as blood vessels. In this study, to overcome these problems, a probabilistic atlas of the spine, including cervical, thoracic and lumbar vertebrae has been built to introduce anatomical knowledge in the segmentation process, aiming to deal with overlapping gray levels and the proximity to other structures. From a set of 3D images manually segmented by a physician (training data), a 3D volume indicating the probability of each voxel of belonging to the spine has been developed, being necessary the generation of a probability map and its deformation to adapt to each patient. To validate the improvement of the segmentation using the atlas developed in the testing data, we computed the Hausdorff distance between the manually-segmented ground truth and an automatic segmentation and also between the ground truth and the automatic segmentation refined with the atlas. The results are promising, obtaining a higher improvement especially in the thoracic region, where the ribs can be found and appropriately eliminated.

Spine is a structure commonly involved in several diseases. Identification and segmentation of the vertebral structures are of relevance to many medical applications related to the spine such as diagnosis, therapy or surgical intervention. However, the development of automatic and reliable methods are an unmet need. This work presents a fully automatic segmentation method of thoracic and lumbar vertebral bodies from Computed Tomography images. The procedure can be divided into four main stages: firstly, seed points were detected in the spinal canal in order to generate initial contours in the segmentation process, automating the whole process. Secondly, a processing step is performed to improve image quality. Third step was to carry out the segmentation using the Selective Binary Gaussian Filtering Regularized Level Set method and, finally, two morphological operations were applied in order to refine the segmentation result. The method was tested in clinical data coming from 10 trauma patients. To evaluate the result the average value of the DICE coefficient was calculated, obtaining a 90.86 +/- 1.87 % in the whole spine (thoracic and lumbar regions), a 86.08 +/- 1.73 % in the thoracic region and a 95,61 +/- 2,25 % in the lumbar region. The results are highly competitive when compared to the results obtained in previous methods, especially for the lumbar region.

[EN] Cancer is one of the leading causes of death worldwide. Most cancer patients do not die due to primary tumors but metastases, which are frequently localized in the bone tissue and primarily in the spine. The quantification of metastatic burden as well as bone quality and quantity of metastatic vertebrae requires an accurate segmentation of it. In the present work a fully automated method for thoracic and lumbar vertebrae segmentation on Computed Tomography images is proposed. Moreover, fully automated methods for thoracic and lumbar spinal canal detection as well as for thoracic and lumbar spinal canal segmentation are also proposed., [ES] El cáncer es una de las principales causas de mortalidad mundial. La mayoría de pacientes con cáncer no mueren debido al tumor primario sino a las metástasis, localizadas con mayor frecuencia en el tejido óseo y especialmente en la columna vertebral. La cuantificación de la carga tumoral así como de la calidad y cantidad ósea de la vértebra con afectación metastásica requiere de una segmentación precisa de la misma. En el presente Trabajo Fin de Máster se propone un método completamente automático para la segmentación de las vertebras torácicas y lumbares a partir del análisis de imagen de Tomografía Computarizada. Además, también se proponen métodos completamente automáticos para la detección del canal vertebral así como para la segmentación del mismo en las regiones torácica y lumbar

Nowadays, radiotherapy is one of the key techniques for localized cancer treatment. Accurate identification of target volume (TV) and organs at risk (OAR) is a crucial step to therapy success. Spinal cord is one of the most radiosensitive OAR and its localization tends to be an observer-dependent and time-consuming task. Hence, numerous studies have aimed to carry out the contouring automatically. In CT images, there is a lack of contrast between soft tissues, making more challenge the delineation. That is the reason why the majority of researches have focused on spinal canal segmentation rather than spinal cord. In this work, we propose a fully automated method for spinal canal segmentation using a Gradient Vector Flow-based (GVF) algorithm. An experienced radiologist performed the manual segmentation, generating the ground truth. The method was evaluated on three different patients using the Dice coefficient, obtaining the following results: 79.50%, 83.77%, and 81.88%, respectively. Outcome reveals that more research has to be performed to improve the accuracy of the method.

This work presents a new automated method for spinal canal detection in Computed Tomography (CT) images. It uses both 2D and 3D information and the algorithm extracts the spinal canal automatically. The procedure can be divided into three main steps. Firstly, a thresholding and a set of morphological operations were applied. Secondly, 3D connectivity analysis was defined to extract the objects forming part of the spinal canal. Finally, the centroid of each slice constituting the spinal canal object was computed. Furthermore, interpolation and extrapolation of data were performed, if required. The method was applied on two different groups, each one coming from different acquisition systems. A total of 25 patients and 8704 images were used. An experienced radiologist evaluated the method qualitatively supporting the utility of it, as all extracted points fell into the spinal canal. Therefore, our method was able to reduce the workload and detect spinal canal objectively. We expect to carry out a quantitative evaluation in our future research. The qualitative outcome of this work suggests promising results.