Ocular Toxoplasmosis Fundus Images Dataset

  1. Parra, Rodrigo 1
  2. Ojeda, Verena 1
  3. Mello-Román, Julio César 2
  4. Noguera, José Luis Vázquez 1
  5. García-Torres, Miguel 3
  6. Villalba, Cynthia 4
  7. Facon, Jaques 5
  8. Divina, Federico 3
  9. Cardozo, Olivia 6
  10. Castillo, Verónica 7
  11. Castro, Ingrid 7
  1. 1 Universidad Americana, Asunción, Paraguay
  2. 2 Facultad de Ciencias Exactas y Tecnológicas, Universidad Nacional de Concepción, Concepción, Paraguay
  3. 3 Division of Computer Science, Universidad Pablo de Olavide, ES-41013 Seville, Spain
  4. 4 Facultad Politécnica, Universidad Nacional de Asunción, San Lorenzo, Paraguay
  5. 5 Universidade Federal do Espírito Santo, Brazil
  6. 6 Department of Ophthalmology, Hospital General Pediátrico Niños de Acosta Ñu, Paraguay
  7. 7 Departamento de Retina, Cátedra de Oftalmología, Hospital de Clínicas, Facultad de Ciencias Médicas, Universidad Nacional de Asunción, San Lorenzo, Paraguay
Mostrar afiliaciones +

Editor: Zenodo

Año de publicación: 2021

Tipo: Dataset

CC BY 4.0

DOI: 10.5281/ZENODO.4439566 lock_openAcceso abierto editor

Resumen

The <strong>Ocular Toxoplasmosis (OT) Fundus Images Dataset</strong> contains a set of eye images collected at the <em>Hospital de Clínicas</em> and <em>Hospital General Pedriático Acosta Ñu </em>medical centers from Asunción, Paraguay. The dataset is used in the generation of models for automatic detection of ocular toxoplasmosis. Used as a tool for OT diagnosis, a predictive model could save time, help diagnose atypical cases and also assist ophthalmologists, being particularly useful for those with less experience. Dataset structure: <pre><code>+-- Ocular_Toxoplasmosis_Data | +-- masks | +-- images | +-- dataset_labels.csv</code></pre> The dataset contains two major folders, one with all the collected images and another one with the masks for lesions of eyes images with ocular toxoplasmosis. The dataset also includes a <strong>csv</strong> file with the labels for each image: healthy, active and inactive lesions, this two being non healthy. Notes about the masks: the dataset includes masks for all non healthy images (active and inactive lesions). In order to differentiate the active lesions which are less common that the inactive ones, the mask includes the suffix <strong>-a </strong>for all the masks of active lesions.