Search

Aims Myocardial fibrosis is a hallmark of atrial fibrillation (AF) and its characterization could be used to guide ablation procedures. Late gadolinium enhanced-magnetic resonance imaging (LGE-MRI) detects areas of atrial fibrosis. However, its accuracy remains controversial. We aimed to analyse the accuracy of LGE-MRI to identify left atrial (LA) arrhythmogenic substrate by analysing voltage and conduction velocity at the areas of LGE. Methods and results Late gadolinium enhanced-magnetic resonance imaging was performed before ablation in 16 patients. Atrial wall intensity was normalized to blood pool and classified as healthy, interstitial fibrosis, and dense scar tissue depending of the resulting image intensity ratio. Bipolar voltage and local conduction velocity were measured in LA with high-density electroanatomic maps recorded in sinus rhythm and subsequently projected into the LGE-MRI. A semi-automatic, point-by-point correlation was made between LGE-MRI and electroanatomical mapping. Mean bipolar voltage and local velocity progressively decreased from healthy to interstitial fibrosis to scar. There was a significant negative correlation between LGE with voltage (r = −0.39, P Conclusions Areas with higher LGE show lower voltage and slower conduction in sinus rhythm. The enhancement intensity correlates with bipolar voltage and conduction velocity in a point-by-point analysis. The performance of LGE-MRI in assessing local velocity might be reduced in patients with dilated atria (LA diameter ≥45).

The aim of this study is to create an automatic framework for sustained ventricular arrhythmia (VA) prediction using cardiac computed tomography (CT) images. We built an image processing pipeline and a deep learning network to explore the relation between post-infarct left ventricular myocardium thickness and previous occurrence of VA. Our pipeline generated a 2D myocardium thickness map (TM) from the 3D imaging input. Our network consisted of a conditional variational autoencoder (CVAE) and a classifier model. The CVAE was used to compress the TM into a low dimensional latent space, then the classifier utilised the latent variables to predict between healthy and VA patient. We studied the network on a large clinical database of 504 healthy and 182 VA patients. Using our method, we achieved a mean classification accuracy of \(75\% \pm 4\) on the testing dataset, compared to \(71\% \pm 4\) from the classification using the classical left ventricular ejection fraction (LVEF).

Aims Left atrial (LA) fibrosis is present in patients with atrial fibrillation (AF) and can be visualized by magnetic resonance imaging with late gadolinium enhancement (LGE-MRI). Previous studies have shown that LA fibrosis is not randomly distributed, being more frequent in the area adjacent to the descending aorta (DAo). The objective of this study is to analyse the relationship between fibrosis in the atrial area adjacent to the DAo and the distance to it, as well as the prognostic implications of this fibrosis. Methods and results Magnetic resonance imaging with late gadolinium enhancement was obtained in 108 patients before AF ablation to analyse the extent of LA fibrosis and the distance DAo-to-LA. A high-density electroanatomic map was performed in a subgroup of 16 patients to exclude the possibility of an MRI artifact. Recurrences after ablation were analysed at 1 year of follow-up. The extent of atrial fibrosis in the area adjacent to the DAo was inversely correlated with the distance DAo-to-LA (r = −0.34, P Conclusions Atrial fibrosis was predominantly located in the area adjacent to the DAo, and increased with the proximity between the two structures. Furthermore, this regional fibrosis better predicted recurrence after AF ablation than total atrial fibrosis.

International audience; The short-axis view defined such that a series of slices are perpendicular to the long-axis of the left ventricle (LV) is one of the most important views in cardiovascular imaging. Raw trans-axial Computed Tomography (CT) images must be often reformatted prior to diagnostic interpretation in short-axis view. The clinical importance of this refor-matting requires the process to be accurate and reproducible. It is often performed after manual localization of landmarks on the image (e.g. LV apex, centre of the mitral valve, etc.) being slower and not fully reproducible as compared to automatic approaches. We propose a fast, automatic and reproducible method to reformat CT images from original trans-axial orientation to short-axis view. A deep learning based seg-mentation method is used to automatically segment the LV endocardium and wall, and the right ventricle epicardium. Surface meshes are then obtained from the corresponding masks and used to automatically detect the shape features needed to find the transformation that locates the cardiac chambers on their standard, mathematically defined, short-axis position. 25 datasets with available manual reformatting performed by experienced cardiac radiologists are used to show that our reformatted images are of equivalent quality.

Atrial fibrillation (AF) is nowadays the most common human arrhythmia and it is considered a marker of an increased risk of embolic stroke. It is known that 99% of AF-related thrombi are generated in the left atrial appendage (LAA), an anatomical structure located within the left atrium (LA). Left atrial appendage occlusion (LAAO) has become a good alternative for nonvalvular AF patients with contraindications to anticoagulants. However, there is a non-negligible number of device-related thrombus (DRT) events, created next to the device surface. In silico fluid simulations can be a powerful tool to better understand the relation between LA anatomy, haemodynamics, and the process of thrombus formation. Despite the increasing literature in LA fluid modelling, a consensus has not been reached yet in the community on the optimal modelling choices and boundary conditions for generating realistic simulations. In this line, we have performed a sensitivity analysis of several boundary conditions scenarios, varying inlet/outlet and LA wall movement configurations, using patient-specific imaging data of six LAAO patients (three of them with DRT at follow-up). Mesh and cardiac cycle convergence were also analysed. The boundary conditions scenario that better predicted DRT cases had echocardiography-based velocities at the mitral valve outlet, a generic pressure wave from an AF patient at the pulmonary vein inlets, and a dynamic mesh approach for LA wall deformation, emphasizing the need for patient-specific data for realistic simulations. The obtained promising results need to be further validated with larger cohorts, ideally with ground truth data, but they already offer unique insights on thrombogenic risk in the left atria. This work was supported by the Spanish Ministry of Science, Innovation and Universities under the Retos I+D Programme (RTI2018-101193-B-I00), the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502), the Spanish Ministry of Economy and Competitiveness under the Programme for the Formation of Doctors (PRE2018-084062), and MINECO (RYC-2015-18888). Additionally, this work was supported by the H2020 EU SimCardioTest project (Digital transformation in Health and Care SC1-DTH-06-2020; grant agreement No. 101016496).

Two-dimensional representation of 3D anatomical structures is a simple and intuitive way for analysing patient information across populations and image modalities. While cardiac ventricles, especially the left ventricle, have an established standard representation (bull's eye plot), the 2D depiction of the left atrium (LA) remains challenging due to its sub-structural complexity including the pulmonary veins (PV) and the left atrial appendage (LAA). Quasi-conformal flattening techniques, successfully applied to cardiac ventricles, require additional constraints in the case of the LA to place the PV and LAA in the same geometrical 2D location for different cases. Some registration-based methods have been proposed but surface registration is time-consuming and prone to errors when the geometries are very different. We propose a novel atrial flattening methodology where a 2D standardised map of the LA is obtained quickly and without errors related to registration. The LA is divided into five regions which are then mapped to their analogue two-dimensional regions. 67 human left atria from magnetic resonance images (MRI) were studied to derive a population-based template representing the averaged relative locations of the PVs and LAA. The clinical application of our methodology is illustrated on different use cases including the integration of MRI and electroanatomical data. This study was partially funded by the Spanish Ministry of Economy and Competitiveness (DPI2015-71640-R), by the “Fundació La Marató de TV3” (no20154031) and by European Union Horizon 2020 Programme for Research and Innovation, under grant agreement No. 642676 (CardioFunXion).

Segmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation treatment of atrial fibrillation. However, direct segmentation of LGE-MRIs is challenging due to the varying intensities caused by contrast agents. Since most clinical studies have relied on manual, labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the 2018 Left Atrium Segmentation Challenge using 154 3D LGE-MRIs, currently the world's largest atrial LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show that the top method achieved a Dice score of 93.2% and a mean surface to surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved superior results than traditional methods and machine learning approaches containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field. Furthermore, the findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging community. (C) 2020 Elsevier B.V. All rights reserved.

AIMS: Late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) may define left atrial (LA) anatomy and structural remodelling, and facilitate atrial fibrillation (AF) ablation. We aimed to assess the intra- and inter-observer reproducibility and agreement of LGE-CMR parameters with direct application to AF ablation techniques. METHODS AND RESULTS: One experienced and one non-experienced observer performed complete LGE-CMR data analysis twice, on different days, in 40 randomly selected LGE-CMR examinations [20 performed before ablation (pre-ablation) and 20 performed 3 months after ablation (post-ablation)]. Four additional observers (two experienced and two non-experienced) performed complete LGE-CMR data analysis in a subgroup of 30 patients (15 pre-ablation and 15 post-ablation). All LGE-CMR were performed in sinus rhythm. Intra- and inter-observer reproducibility of LA volume, LA area, and sphericity index (SI) was high: coefficient of variation 0.71. Geometric congruency of repeated reconstruction of LA shape was high: maximal error 0.75) when the scar area was >5 cm2 for a single observer and >15 cm2 for multiple observers. Non-experienced observers performed equally well to experienced observers. CONCLUSION: Late gadolinium enhancement cardiac magnetic resonance measurements of LA area, volume, and SI were reproducible, and geometric congruency of LA shape was high. Location of scar was precise for scar areas >5 cm2 for single observers and >15 cm2 for multiple observers, regardless of the observers' experience. These results may serve as a reference for future studies on the role for substrate-based AF ablation procedures.

The majority of thrombi in non-valvular atrial fibrillation (AF) patients are formed in the left atrial appendage (LAA). The shape of the LAA is highly variable and complex morphologies seem to favour the development of thrombus since they may induce blood stasis. Nevertheless, the relation between LAA shape and risk of thrombus has not been rigorously studied due to the lack of appropriate imaging data and robust tools to characterize LAA morphology. The main goal of this work was to automatically extract simple LAA morphological descriptors and study their relation with the presence of thrombus. LAA shape characterization was based on the computation of its centreline combining a heat transfer-derived distance map and a marching algorithm, once it LAA was segmented from 3D medical images. From the LAA centreline, several morphological descriptors were derived such as its length, tortuosity and major bending angles, among others. Other LAA parameters such as surface area, volume and ostium shape parameters were also obtained. A total of 71 LAA geometries from AF patients were analysed; 33 of them with a history of a thromboembolic event. We performed a statistical analysis to identify morphological descriptors showing differences between patients with and without thrombus history. Ostium size and centreline length were significatively different in both cohorts, with larger average values in thromboembolic cases, which could be related to slower blood flow velocities within the LAA. Additionally, some of the obtained centreline-based LAA parameters could be used for a better planning of LAA occluder implantations.

The left atrial appendage (LAA) is a complex and heterogeneous bulge structure of the left atrium (LA). It is known that, in atrial fibrillation (AF) patients, around 70% to 90% of the thrombi are formed there. However, the exact mechanism of the process of thrombus formation and the role of the LAA in that process are not fully understood yet. The main goal of this work is to perform patient-specific haemodynamics simulations of the LA and LAA and jointly analyse the resulting blood flow parameters with morphological descriptors of these structures in relation with the risk of thrombus formation. Some LAA morphological descriptors such as ostium characteristics and pulmonary configuration were found to influence LAA blood flow patterns. These findings improve our knowledge on the required conditions for thrombus formation in the LAA.

Segmentation of the left atria (LA) from late gadolinium enhanced magnetic resonance imaging (LGE-MRI) is challenging since atrial borders are not easily distinguishable in the images. We propose a method based on multi-atlas whole heart segmentation and shape modeling of the LA. In the training phase we first construct whole heart LGE-MRI atlases and build a principal component analysis (PCA) model able to capture the high variability of the LA shapes. All atlases are clustered according to their LA shape using an unsupervised clustering method which additionally outputs the most representative case in each cluster. All cluster representatives are registered to the target image and ranked using conditional entropy. A small subset of the most similar representatives is used to find LA shapes with similar morphology in the training set that are used to obtain the final LA segmentation. We tested our approach using 80 LGE-MRI data for training and 20 LGE-MRI data for testing obtaining a Dice score of \(0.842 \pm 0.049\).

Pulmonary vein isolation (PVI) is a common procedure for the treatment of atrial fibrillation (AF) since the initial trigger for AF frequently originates in the pulmonary veins. A successful isolation produces a continuous lesion (scar) completely encircling the veins that stops activation waves from propagating to the atrial body. Unfortunately, the encircling lesion is often incomplete, becoming a combination of scar and gaps of healthy tissue. These gaps are potential causes of AF recurrence, which requires a redo of the isolation procedure. Late-gadolinium enhanced cardiac magnetic resonance (LGE-CMR) is a non-invasive method that may also be used to detect gaps, but it is currently a time-consuming process, prone to high inter-observer variability. In this paper, we present a method to semi-automatically identify and quantify ablation gaps. Gap quantification is performed through minimum path search in a graph where every node is a scar patch and the edges are the geodesic distances between patches. We propose the Relative Gap Measure (RGM) to estimate the percentage of gap around a vein, which is defined as the ratio of the overall gap length and the total length of the path that encircles the vein. Additionally, an advanced version of the RGM has been developed to integrate gap quantification estimates from different scar segmentation techniques into a single figure-of-merit. Population-based statistical and regional analysis of gap distribution was performed using a standardised parcellation of the left atrium. We have evaluated our method on synthetic and clinical data from 50 AF patients who underwent PVI with radiofrequency ablation. The population-based analysis concluded that the left superior PV is more prone to lesion gaps while the left inferior PV tends to have less gaps (p .05 in both cases), in the processed data. This type of information can be very useful for the optimization and objective assessment of PVI interventions.

Background: Cardiovascular magnetic resonance (CMR) imaging has been used to visualise post-ablation atrial scar (PAAS), generally employing a three-dimensional (3D) late gadolinium enhancement (LGE) technique. However the reproducibility of PAAS imaging has not been determined. This cross-over study is the first to investigate the reproducibility of the technique, crucial for both future research design and clinical implementation. Methods: Forty subjects undergoing first time ablation for atrial fibrillation (AF) had detailed CMR assessment of PAAS. Following baseline pre-ablation scan, two scans (separated by 48 h) were performed at three months post-ablation. Each scan session included 3D LGE acquisition at 10, 20 and 30 min post administration of gadolinium-based contrast agent (GBCA). Subjects were allocated at second scan post-ablation to identical imaging parameters (‘Repro’, n = 10), 3 T scanner (‘3 T’, n = 10), half-slice thickness (‘Half-slice’, n = 10) or half GBCA dose (‘Half-gad’, n = 10). PAAS was compared to baseline scar and then reproducibility was assessed for two measures of thresholded scar (% left atrial (LA) occupied by PAAS (%LA PAAS) and Pulmonary Vein Encirclement (PVE)), and then four measures of non-thresholded scar (point-by-point assessment of PAAS, four normalisation methods). Thresholded measures of PAAS were evaluated against procedural outcome (AF recurrence). Results: A total of 271 3D acquisitions (out of maximum 280, 96.7%) were acquired. At 20 and 30 min, inter-scan reproducibility was good to excellent (coefficient of variation at 20 min and 30 min: %LA PAAS 0.41 and 0.20; PVE 0.13 and 0.04 respectively for ‘Repro’ group). Changes in imaging parameters, especially reduced GBCA dose, reduced inter-scan reproducibility, but for most measures remained good to excellent (ICC for %LA PAAS 0.454–0.825, PVE 0.618–0.809 at 30 min). For non-thresholded scar, highest reproducibility was observed using blood pool z-score normalisation technique: inter-scan ICC 0.759 (absolute agreement, ‘Repro’ group). There was no significant relationship between indices of PAAS and AF recurrence. Conclusion: PAAS imaging is a reproducible finding. Imaging should be performed at least 20 min post-GBCA injection, and a blood pool z-score should be considered for normalisation of signal intensities. The clinical implications of these findings remain to be established in the absence of a simple correlation with arrhythmia outcome. The research was performed at King’s College London Medical Engineering Centre, funded by the Wellcome Trust and the Engineering and Physical Sciences Research Council (EPSRC). The research was also supported by the National Institute for Health Research (NIHR) Biomedical Research Centre awards to Guy’s and St Thomas’ NHS Foundation Trust in partnership with King’s College London, by the NIHR Healthcare Technology Co-operative for Cardiovascular Disease at Guy’s and St Thomas’ NHS Foundation Trust, and by the Cardiovascular HTC. Work upon the PVE methodology was partially funded by the Spanish Ministry of Economy and Competitiveness (DPI2015-71640-R) and by the “Fundació La Marató de TV3” (no. 20154031).

Aims: Left atrial (LA) fibrosis can be identified by late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) in patients with atrial fibrillation (AF). However, there is limited information about anatomical fibrosis distribution in the left atrium. The aim is to determine whether there is a preferential spatial distribution of fibrosis in the left atrium in patients with AF. Methods and results: A 3-Tesla LGE-CMR was performed in 113 consecutive patients referred for AF ablation. Images were post-processed and analysed using ADAS-AF software (Galgo Medical), which allows fibrosis identification in 3D colour-coded shells. A regional semiautomatic LA parcellation software was used to divide the atrial wall into 12 segments: 1–4, posterior wall; 5–6, floor; 7, septal wall; 8–11, anterior wall; 12, lateral wall. The presence and amount of fibrosis in each segment was obtained for analysis. After exclusions for artefacts and insufficient image quality, 76 LGE-MRI images (68%) were suitable for fibrosis analysis. Segments 3 and 5, closest to the left inferior pulmonary vein, had significantly higher fibrosis (40.42% ± 23.96 and 25.82% ± 21.24, respectively; P 60 years was significantly associated with increased LA fibrosis [95% confidence interval (CI) 0.19–8.39, P = 0.04] and persistent AF approached significance (95% CI −0.19% to 7.83%, P = 0.08). Conclusion: In patients with AF, the fibrotic area is preferentially located at the posterior wall and floor around the antrum of the left inferior pulmonary vein. Age >60 years was associated with increased fibrosis. This work was partially supported by Fondo de Investigaciones Sanitarias-Instituto de Salud Carlos III (PI13/01747 and PI16/00435); Agencia de gestió d´Ajuts Universitaris I de Recerca (AGAUR) Exp: 2014_SGR_471; CERCA programme/Generalitat de Catalunya; European Regional Development Fund (ERDF. European Union. A Way of Making Europe), the European Union's Horizon 2020 research and innovation programme under grant agreement No 633196 (CATCH ME), a grant by La MARATÓ-TV3 (20152730) and the Spanish Ministry of Economy and Competitiveness (DPI2015-71640-R).

The left atrial appendage (LAA) is a complex and heterogeneous protruding structure of the left atrium (LA). In atrial fibrillation patients, it is the location where 90% of the thrombi are formed. However, the role of the LAA in thrombus formation is not fully known yet. The main goal of this work is to perform a sensitivity analysis to identify the most relevant LA and LAA morphological parameters in atrial blood flow dynamics. Simulations were run on synthetic ellipsoidal left atria models where different parameters were individually studied: pulmonary veins and mitral valve dimensions; LAA shape; and LA volume. Our computational analysis confirmed the relation between large LAA ostia, low blood flow velocities and thrombus formation. Additionally, we found that pulmonary vein configuration exerted a critical influence on LAA blood flow patterns. These findings contribute to a better understanding of the LAA and to support clinical decisions for atrial fibrillation patients.

The influence of the left atrial appendage (LAA) and its different possible morphologies in atrial haemodynamics and thrombus formation is not fully known yet. The main goal of this work is to analyse blood flow characteristics in relation with LA/LAA morphologies to better understand conditions that may lead to thrombus formation. We constructed several patient-specific computational meshes of left atrial geometries from medical imaging data. Subsequently, Computational Fluid Dynamics (CFD) methods were run with boundary conditions based on pressure and velocity measurements from literature. Relevant indices characterizing the simulated flows such as local maps of vorticity were related to simple LAA shape parameters. Our in silico study provided different 3D haemodynamics patterns dependent on the patient-specific atrial geometry. It also suggests that areas near the LAA ostium and with presence of lobes are more prone to coagulation due to the presence of low velocities and vortices.

Radiofrequency ablation is a common procedure to treat atrial fibrillation, where the objective is to electrically isolate some regions of the myocardium from others to avoid the transmission of abnormal electrical signals. This is done with a catheter by delivering an RF signal in the targeted regions. Ideally, the signal will create a permanent lesion that would prevent the reappearance of the abnormal electrical signals and therefore terminate AF. There are many parameters involved in the process and naturally in its success. In this paper we present a framework for comparing RF ablation related parameters such as power of the signal, contact force, temperature and impedance with permanent and effective lesion formation. In order to do that we propose to use a standardised unfold map that allows us to directly compare atria with different shapes at different time-points and with different types of information. We tested the method in 8 real cases showing that it facilitates the analysis and comparison of the ablation related parameters with the outcome of the procedure.

Comunicació presentada a la 9th international conference on Functional Imaging and Modeling of the Heart (FIMH 2017), celebrada els dies 11 a 13 de juny de 2017 a Toronto, Canadà. Many cardiac diseases are associated with changes in ventricular shape. However, in daily practice, the heart is mostly assessed by 2D echocardiography only. While 3D techniques are available, they are rarely used. In this paper we analyze to which extent it is possible to obtain the 3D shape of a left ventricle (LV) using measurements from 2D echocardiography. First, we investigate this using synthetic datasets, and afterwards, we illustrate it in clinical 2D echocardiography measurements with corresponding 3D meshes obtained using 3D echocardiography. We demonstrate that standard measurements taken in 2D allow quantifying only the ellipsoidal shape of the ventricle, and that capturing other shape features require either additional geometrical measurements or clinical information related to shape remodelling. We show that noise in the measurements is the primary cause for poor association between the measurements and the LV shape features and that an estimated 10% level of noise on the 2D measurements limits the recoverability of shape. Finally we show that clinical variables relating to the clinical history can substitute the lack of geometric measurements, thus providing alternatives for shape assessment in daily practice. This study was partially supported by the Spanish Ministry of Economy and Competitiveness (grant TIN2014-52923-R; Maria de Maeztu Units of Excellence Programme - MDM-2015-0502), FEDER and the European Union Horizon 2020 Programme for Research and Innovation, under grant agreement No. 642676 (CardioFunXion).

The left atrial appendage (LAA) is a complex and heterogeneous protruding structure of the left atrium (LA). In atrial fibrillation patients, it is the location where 90% of the thrombi are formed. However, the role of the LAA in thrombus formation is not fully known yet. The main goal of this work is to perform a sensitivity analysis to identify the most relevant LA and LAA morphological parameters in atrial blood flow dynamics. Simulations were run on synthetic ellipsoidal left atria models where different parameters were individually studied: pulmonary veins and mitral valve dimensions; LAA shape; and LA volume. Our computational analysis confirmed the relation between large LAA ostia, low blood flow velocities and thrombus formation. Additionally, we found that pulmonary vein configuration exerted a critical influence on LAA blood flow patterns. These findings contribute to a better understanding of the LAA and to support clinical decisions for atrial fibrillation patients.

Resting state fMRI is a powerful method of functional brain imaging, which can reveal information of functional connectivity between regions during rest. In this paper, we present a novel method, called Functional-Anatomical Discriminative Regions FADR, for selecting a discriminative subset of functional-anatomical regions of the brain in order to characterize functional connectivity abnormalities in mental disorders. FADR integrates Independent Component Analysis with a sparse feature selection strategy, namely Elastic Net, in a supervised framework to extract a new sparse representation. In particular, ICA is used for obtaining group Resting State Networks and functional information is extracted from the subject-specific spatial maps. Anatomical information is incorporated to localize the discriminative regions. Thus, functional-anatomical information is combined in the new descriptor, which characterizes areas of different networks and carries discriminative power. Experimental results on the public database ADHD-200 validate the method being able to automatically extract discriminative areas and extending results from previous studies. The classification ability is evaluated showing that our method performs better than the average of the teams in the ADHD-200 Global Competition while giving relevant information about the disease by selecting the most discriminative regions at the same time.