17
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      V-FCNN: Volumetric Fully Convolution Neural Network For Automatic Atrial Segmentation

      Preprint
      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Atrial Fibrillation (AF) is a common electro-physiological cardiac disorder that causes changes in the anatomy of the atria. A better characterization of these changes is desirable for the definition of clinical biomarkers, and thus there is a need of its fully automatic segmentation from clinical images. In this work we present an architecture based in 3D-convolution kernels, a Volumetric Fully Convolution Neural Network (V-FCNN), able to segment the entire volume in one-shot, and consequently integrate the implicit spatial redundancy present in high resolution images. A loss function based on the mixture of both Mean Square Error (MSE) and Dice Loss (DL) is used, in an attempt to combine the ability to capture the bulk shape and the reduction of local errors products by over segmentation. Results demonstrate a reasonable performance in the middle region of the atria, and the impact of the challenges of capturing the variability of the pulmonary veins or the identification of the valve plane that separates the atria to the ventricle.

          Related collections

          Most cited references5

          • Record: found
          • Abstract: found
          • Article: not found

          A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI.

          Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) datasets is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic LV segmentation tool from short-axis cardiac MRI datasets. The method employs deep learning algorithms to learn the segmentation task from the ground true data. Convolutional networks are employed to automatically detect the LV chamber in MRI dataset. Stacked autoencoders are used to infer the LV shape. The inferred shape is incorporated into deformable models to improve the accuracy and robustness of the segmentation. We validated our method using 45 cardiac MR datasets from the MICCAI 2009 LV segmentation challenge and showed that it outperforms the state-of-the art methods. Excellent agreement with the ground truth was achieved. Validation metrics, percentage of good contours, Dice metric, average perpendicular distance and conformity, were computed as 96.69%, 0.94, 1.81 mm and 0.86, versus those of 79.2-95.62%, 0.87-0.9, 1.76-2.97 mm and 0.67-0.78, obtained by other methods, respectively.
            Bookmark
            • Record: found
            • Abstract: not found
            • Book Chapter: not found

            Recurrent Fully Convolutional Neural Networks for Multi-slice MRI Cardiac Segmentation

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Towards personalized computational modelling of the fibrotic substrate for atrial arrhythmia.

              : Atrial arrhythmias involving a fibrotic substrate are an important cause of morbidity and mortality. In many cases, effective treatment of such rhythm disorders is severely hindered by a lack of mechanistic understanding relating features of fibrotic remodelling to dynamics of re-entrant arrhythmia. With the advent of clinical imaging modalities capable of resolving the unique fibrosis spatial pattern present in the atria of each individual patient, a promising new research trajectory has emerged in which personalized computational models are used to analyse mechanistic underpinnings of arrhythmia dynamics based on the distribution of fibrotic tissue. In this review, we first present findings that have yielded a robust and detailed biophysical representation of fibrotic substrate electrophysiological properties. Then, we summarize the results of several recent investigations seeking to use organ-scale models of the fibrotic human atria to derive new insights on mechanisms of arrhythmia perpetuation and to develop novel strategies for model-assisted individualized planning of catheter ablation procedures for atrial arrhythmias.
                Bookmark

                Author and article information

                Journal
                06 August 2018
                Article
                1808.01944
                d4352b30-3632-417b-8dae-0199a7f2cce1

                http://creativecommons.org/licenses/by/4.0/

                History
                Custom metadata
                8 pages, 3 figures, In Proceedings of MICCAI 2018 Atrial Segmentation Challenge
                stat.ML cs.CV cs.LG

                Computer vision & Pattern recognition,Machine learning,Artificial intelligence

                Comments

                Comment on this article