Mostrar el registro sencillo del ítem

dc.contributor.authorParra, Rodrigo
dc.contributor.authorOjeda, Verena
dc.contributor.authorVázquez Noguera, José Luis 
dc.contributor.authorGarcía Torres, Miguel
dc.contributor.authorMello Román, Julio César
dc.contributor.authorVillalba Cardozo, Cynthia Emilia 
dc.contributor.authorFacon, Jacques
dc.contributor.authorDivina, Federico
dc.contributor.authorCardozo, Olivia
dc.contributor.authorCastillo, Veronica Elisa
dc.contributor.authorCastro Matto, Ingrid
dc.contributor.otherUniversidad Nacional de Asunción - Facultad Politécnicaes
dc.contributor.otherUniversidad Americana (PY)es
dc.contributor.otherUniversidad Pablo de Olavide (ES)es
dc.date.accessioned2022-04-29T23:09:50Z
dc.date.available2022-04-29T23:09:50Z
dc.date.issued2021
dc.identifier.urihttp://hdl.handle.net/20.500.14066/3791
dc.description.abstractIn the automatic diagnosis of ocular toxoplasmosis (OT), Deep Learning (DL) has arisen as a powerful and promising approach for diagnosis. However, despite the good performance of the models, decision rules should be interpretable to elicit trust from the medical community. Therefore, the development of an evaluation methodology to assess DL models based on interpretability methods is a challenging task that is necessary to extend the use of AI among clinicians. In this work, we propose a novel methodology to quantify the similarity between the decision rules used by a DL model and an ophthalmologist, based on the assumption that doctors are more likely to trust a prediction that was based on decision rules they can understand. Given an eye fundus image with OT, the proposed methodology compares the segmentation mask of OT lesions labeled by an ophthalmologist with the attribution matrix produced by interpretability methods. Furthermore, an open dataset that includes the eye fundus images and the segmentation masks is shared with the community. The proposal was tested on three different DL architectures. The results suggest that complex models tend to perform worse in terms of likelihood to be trusted while achieving better results in sensitivity and specificity.es
dc.description.sponsorshipCONACYT - Consejo Nacional de Ciencia y Tecnologíaes
dc.language.isoenges
dc.subject.classification1303 I+D en relación con las Ciencias médicases
dc.subject.otherDEEP LEARNINGes
dc.subject.otherOCULAR TOXOPLASMOSISes
dc.subject.otherMACHINE LEARNING INTERPRETABILITYes
dc.titleA Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images.es
dc.typeresearch articlees
dc.description.fundingtextPROCIENCIAes
dc.journal.titleDiagnosticses
dc.relation.projectCONACYTPINV18-1293es
dc.rights.accessRightsopen accesses
dc.volume.number11es


Ficheros en el ítem

Este ítem aparece en la(s) siguiente(s) colección(ones)

  • Artículos científicos
    La colección comprende artículos científicos, revisiones y artículos de conferencia que son resultados de actividades científicas y de innovación financiadas por los programas PROCIENCIA y PROINNOVA.

Mostrar el registro sencillo del ítem