Your browser doesn't support javascript.
loading
LUNet: deep learning for the segmentation of arterioles and venules in high resolution fundus images.
Fhima, Jonathan; Van Eijgen, Jan; Billen Moulin-Romsée, Marie-Isaline; Brackenier, Heloïse; Kulenovic, Hana; Debeuf, Valérie; Vangilbergen, Marie; Freiman, Moti; Stalmans, Ingeborg; Behar, Joachim A.
Afiliación
  • Fhima J; Faculty of Biomedical Engineering, Technion-IIT, Haifa, Israel.
  • Van Eijgen J; Department of Applied Mathematics, Technion-IIT, Haifa, Israel.
  • Billen Moulin-Romsée MI; Research Group of Ophthalmology, Department of Neurosciences, KU Leuven, Leuven, Belgium.
  • Brackenier H; Department of Ophthalmology, University Hospitals UZ Leuven, Leuven, Belgium.
  • Kulenovic H; Research Group of Ophthalmology, Department of Neurosciences, KU Leuven, Leuven, Belgium.
  • Debeuf V; Department of Ophthalmology, University Hospitals UZ Leuven, Leuven, Belgium.
  • Vangilbergen M; Research Group of Ophthalmology, Department of Neurosciences, KU Leuven, Leuven, Belgium.
  • Freiman M; Research Group of Ophthalmology, Department of Neurosciences, KU Leuven, Leuven, Belgium.
  • Stalmans I; Research Group of Ophthalmology, Department of Neurosciences, KU Leuven, Leuven, Belgium.
  • Behar JA; Research Group of Ophthalmology, Department of Neurosciences, KU Leuven, Leuven, Belgium.
Physiol Meas ; 45(5)2024 May 03.
Article en En | MEDLINE | ID: mdl-38599224
ABSTRACT
Objective.This study aims to automate the segmentation of retinal arterioles and venules (A/V) from digital fundus images (DFI), as changes in the spatial distribution of retinal microvasculature are indicative of cardiovascular diseases, positioning the eyes as windows to cardiovascular health.Approach.We utilized active learning to create a new DFI dataset with 240 crowd-sourced manual A/V segmentations performed by 15 medical students and reviewed by an ophthalmologist. We then developed LUNet, a novel deep learning architecture optimized for high-resolution A/V segmentation. The LUNet model features a double dilated convolutional block to widen the receptive field and reduce parameter count, alongside a high-resolution tail to refine segmentation details. A custom loss function was designed to prioritize the continuity of blood vessel segmentation.Main Results.LUNet significantly outperformed three benchmark A/V segmentation algorithms both on a local test set and on four external test sets that simulated variations in ethnicity, comorbidities and annotators.Significance.The release of the new datasets and the LUNet model (www.aimlab-technion.com/lirot-ai) provides a valuable resource for the advancement of retinal microvasculature analysis. The improvements in A/V segmentation accuracy highlight LUNet's potential as a robust tool for diagnosing and understanding cardiovascular diseases through retinal imaging.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Procesamiento de Imagen Asistido por Computador / Aprendizaje Profundo / Fondo de Ojo Límite: Humans Idioma: En Revista: Physiol Meas Asunto de la revista: BIOFISICA / ENGENHARIA BIOMEDICA / FISIOLOGIA Año: 2024 Tipo del documento: Article País de afiliación: Israel Pais de publicación: Reino Unido
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Procesamiento de Imagen Asistido por Computador / Aprendizaje Profundo / Fondo de Ojo Límite: Humans Idioma: En Revista: Physiol Meas Asunto de la revista: BIOFISICA / ENGENHARIA BIOMEDICA / FISIOLOGIA Año: 2024 Tipo del documento: Article País de afiliación: Israel Pais de publicación: Reino Unido