Semi-Supervised Segmentation with Topological Penalization for Quantifying Retinal Degeneration in Histological Sections - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Semi-Supervised Segmentation with Topological Penalization for Quantifying Retinal Degeneration in Histological Sections

Résumé

Retinal degeneration is a hallmark of various degenerative ocular diseases, and its accurate quantification is crucial for nonclinical pharmacological studies. Here, we describe a method to assess retinal atrophy by measuring the layers' thickness in histological sections stained with hematoxylin and eosin. We use a semi-supervised approach with topological penalization to segment layers followed by thickness measurements along the layers' medial axes. The method is tested on mice for four layers, obtaining a high correlation with manual measurements collected by biologists.

Fichier principal
Vignette du fichier
Semi_Supervised_Segmentation_with_Topological_Penalization_for_Quantifying_Retinal_Degeneration_in_Histological_Sections_HAL.pdf (848.21 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04731416 , version 1 (10-10-2024)

Identifiants

Citer

Benjamin Dorra, Giacomo Nardi, Antoine Habis, Jean-Philippe Annereau, Jean-Christophe Olivo-Marin, et al.. Semi-Supervised Segmentation with Topological Penalization for Quantifying Retinal Degeneration in Histological Sections. 2024 IEEE International Symposium on Biomedical Imaging (ISBI), May 2024, Athens, France. pp.1-5, ⟨10.1109/ISBI56570.2024.10635431⟩. ⟨hal-04731416⟩
12 Consultations
16 Téléchargements

Altmetric

Partager

More