Browsing by Subject "Image enhancement"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Open Access
    A Data-Centric Algorithmic Pipeline for Enhancing Cardiac MRI Segmentation Using ViTUNeT and Quality-Aware Filtering
    (MDPI, 2026-03-06) Salvador de Haro; Jesús Cámara; González Férez, María Pilar; José Manuel García; García Carrasco, José Manuel; Bernabé García, Gregorio; Ingeniería y Tecnología de Computadores; Facultades de la UMU::Facultad de Informática
    The performance of deep-learning-based segmentation models is strongly dependent on the quality of the input data, which is frequently heterogeneous or degraded in real-world medical imaging scenarios. This work presents a data-centric algorithmic pipeline designed to improve cardiac MRI segmentation accuracy through systematic image enhancement and automatic slice-quality filtering. The proposed method is formalized as deterministic algorithm that combines image processing and supervised learning components. The approach integrates a contrast- and structure-preserving enhancement stage, based on bilateral filtering and adaptive histogram equalization, with a quality-aware selection algorithm. Slice quality is assessed using anatomical attributes extracted via YOLOv11sbased localization and a supervised classification model trained to identify diagnostically reliable images. When applied to transformer-based segmentation architectures such as ViTUNeT, the pipeline yields consistent improvements across all evaluation metrics without increasing model complexity or training cost. These findings emphasize the importance of algorithmic data curation as an effective strategy for enhancing robustness and stability in deep-learning segmentation pipelines and demonstrate the broader applicability of the proposed approach to computer-vision tasks involving heterogeneous or low-quality image datasets.
  • Thumbnail Image
    Publication
    Restricted
    Optical and visual metrics
    (Taylor & Francis Group, LLC., 2017) Guirao, Antonio; Guirao Piñera, Antonio; Física
    The eye is a complex imaging system whose optical components determine the first step of vision. Quantifying and measuring the ocular quality, and how this affects the quality of the retinal images, can allow us to better understand the visual process and to improve diagnostics and correction methods. The optical quality is lowered by aberrations (consequence of the shape of the refracting surfaces), diffraction at the pupil, and scattering (due to particles and nonuniformities localized in the media). The combined effect of these three factors is that light deviates from the ideal trajectory and spreads over a deteriorated retinal image that will limit the visual performance. In general, a system with less aberrations, scattering, and diffraction will produce images with higher quality. Consequently, one expects to have a better vision when images at the retina are fine. However, although the optics, the retinal image stage, and the visual perception are dependent with each other, there is not a direct or obvious relationship between these three levels. In this context, it is necessary to distinguish between optical quality, optical performance (image quality), and visual performance and to be able to define metrics that quantitatively measure each of these matters