Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Reseña (Review)

The use of sensors to prevent, predict transition to chronic and personalize treatment of Low Back Pain: a systematic review

  • Herrero, Pablo
  • Ríos-Asín, Izarbe
  • Lapuente-Hernández, Diego
  • Pérez, Luis
  • Calvo, Sandra
  • Gil-Calvo, Marina
Non-specific low back pain (NSLBP) is a highly prevalent condition that implies substantial expenses and affects quality of life in terms of occupational and recreational activities, physical and psychological health, and general well-being. The diagnosis and treatment are challenging processes due to the unknown underlying causes of the condition. Recently, sensors have been included in clinical practice to implement its management. In this review, we furthered knowledge about the potential benefits of sensors such as force platforms, video systems, electromyography, or inertial measure systems in the assessment process of NSLBP. We concluded that sensors could identify specific characteristics of this population like impaired range of movement, decreased stability, or disturbed back muscular activation. Sensors could provide sufferers with earlier diagnosis, prevention strategies to avoid chronic transition, and more efficient treatment approaches. Nevertheless, the review has limitations that need to be considered in the interpretation of results.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

3D Segmentation of Multi-contrast Cardiac Magnetic Resonances With Topological Correction and Synthetic Data Augmentation

  • Rosales, Ricardo M.
  • Doblaré, Manuel
  • Pueyo, Esther
Purpose: Automatic segmentation of cardiac magnetic resonance (CMR) images improves the evaluation of heart structure and function, helping clinical diagnosis and the generation of in silico models. Recent advances have introduced synthetic augmentation (SA) using generative adversarial networks (GANs) and topological correction (TC) via persistent homology to enhance segmentation with convolutional neural networks (CNNs). However, their combined effectiveness remains unexplored. Here, we extend and systematically evaluate these techniques, individually and in combination, for the first time in the context of three-dimensional (3D) CMR segmentation across challenging multi-vendor, multi-center, multi-class, and multi-contrast data sets. Methods: Data involved anisotropic, topologically inconsistent cine and late gadolinium-enhanced (LGE) CMRs, and isotropic, topologically consistent ex vivo CMRs. Topological priors were defined in each data set from ground truth label (GTL) assessments, and TC was applied by retraining the baseline 3D CNN with a loss function accounting for topological discrepancies. For SA, deformed GTLs were used to generate synthetic images using trained 3D GANs. Results: Consistent segmentation improvements were observed for the ex vivo data in both overlap with GTLs and topological precision when applying TC and SA individually and in combination. Notably, an enhanced identification of the infarction was obtained when SA and TC were used in the LGE data. Overall, SA increased the predictions overlap with GTLs, while TC reduced the topological discrepancies across all data sets. Conclusion: TC and SA demonstrate strong potential for improving 3D CMR segmentation on complex, real-world data sets, especially when topologically consistent data are available for training.