M
Miguel Ángel González Ballester
Researcher at Pompeu Fabra University
Publications - 218
Citations - 4320
Miguel Ángel González Ballester is an academic researcher from Pompeu Fabra University. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 25, co-authored 194 publications receiving 2913 citations. Previous affiliations of Miguel Ángel González Ballester include T-Systems & Catalan Institution for Research and Advanced Studies.
Papers
More filters
Book ChapterDOI
Double Encoder-Decoder Networks for Gastrointestinal Polyp Segmentation.
TL;DR: In this article, two pretrained encoder-decoder networks are sequentially stacked: the second network takes as input the concatenation of the original frame and the initial prediction generated by the first network, which acts as an attention mechanism enabling the second networks to focus on interesting areas within the image, thereby improving the quality of its predictions.
Book ChapterDOI
Combining Multi-Sequence and Synthetic Images for Improved Segmentation of Late Gadolinium Enhancement Cardiac MRI
Víctor M. Campello,Carlos Martín-Isla,Cristian Izquierdo,Steffen E. Petersen,Miguel Ángel González Ballester,Karim Lekadir +5 more
TL;DR: In this paper, a generative adversarial network is trained for the task of modality-to-modality translation between cine and LGE-MRI sequences to obtain extra synthetic images for both modalities.
Posted Content
Combining Multi-Sequence and Synthetic Images for Improved Segmentation of Late Gadolinium Enhancement Cardiac MRI
Víctor M. Campello,Carlos Martín-Isla,Cristian Izquierdo,Steffen E. Petersen,Miguel Ángel González Ballester,Karim Lekadir +5 more
TL;DR: The results based on three magnetic resonance sequences show that the multi-sequence model training integrating synthetic images and data augmentation improves in the segmentation over conventional training with real datasets.
Journal ArticleDOI
Computational Models for Predicting Outcomes of Neuroprosthesis Implantation: the Case of Cochlear Implants
TL;DR: It is argued that highly detailed computational models that are specifically tailored for a patient can provide useful information to improve the precision of the nervous system electrode interface.
Book ChapterDOI
Medical-based Deep Curriculum Learning for Improved Fracture Classification
Amelia Jiménez-Sánchez,Diana Mateus,Sonja Kirchhoff,Chlodwig Kirchhoff,Peter Biberthaler,Nassir Navab,Miguel Ángel González Ballester,Gemma Piella +7 more
TL;DR: This work proposes and compares several strategies relying on curriculum learning, to support the classification of proximal femur fracture from X-ray images, a challenging problem as reflected by existing intra- and inter-expert disagreement.