A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images

In 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 developmen...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Rodrigo Parra, Verena Ojeda, Jose Luis Vázquez Noguera, Miguel García-Torres, Julio César Mello-Román, Cynthia Villalba, Jacques Facon, Federico Divina, Olivia Cardozo, Verónica Elisa Castillo, Ingrid Castro Matto
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/e9222ee88e094a61ab31e5560289cf84
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:e9222ee88e094a61ab31e5560289cf84
record_format dspace
spelling oai:doaj.org-article:e9222ee88e094a61ab31e5560289cf842021-11-25T17:20:11ZA Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images10.3390/diagnostics111119512075-4418https://doaj.org/article/e9222ee88e094a61ab31e5560289cf842021-10-01T00:00:00Zhttps://www.mdpi.com/2075-4418/11/11/1951https://doaj.org/toc/2075-4418In 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.Rodrigo ParraVerena OjedaJose Luis Vázquez NogueraMiguel García-TorresJulio César Mello-RománCynthia VillalbaJacques FaconFederico DivinaOlivia CardozoVerónica Elisa CastilloIngrid Castro MattoMDPI AGarticledeep learningocular toxoplasmosismachine learning interpretabilitytrustMedicine (General)R5-920ENDiagnostics, Vol 11, Iss 1951, p 1951 (2021)
institution DOAJ
collection DOAJ
language EN
topic deep learning
ocular toxoplasmosis
machine learning interpretability
trust
Medicine (General)
R5-920
spellingShingle deep learning
ocular toxoplasmosis
machine learning interpretability
trust
Medicine (General)
R5-920
Rodrigo Parra
Verena Ojeda
Jose Luis Vázquez Noguera
Miguel García-Torres
Julio César Mello-Román
Cynthia Villalba
Jacques Facon
Federico Divina
Olivia Cardozo
Verónica Elisa Castillo
Ingrid Castro Matto
A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images
description In 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.
format article
author Rodrigo Parra
Verena Ojeda
Jose Luis Vázquez Noguera
Miguel García-Torres
Julio César Mello-Román
Cynthia Villalba
Jacques Facon
Federico Divina
Olivia Cardozo
Verónica Elisa Castillo
Ingrid Castro Matto
author_facet Rodrigo Parra
Verena Ojeda
Jose Luis Vázquez Noguera
Miguel García-Torres
Julio César Mello-Román
Cynthia Villalba
Jacques Facon
Federico Divina
Olivia Cardozo
Verónica Elisa Castillo
Ingrid Castro Matto
author_sort Rodrigo Parra
title A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images
title_short A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images
title_full A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images
title_fullStr A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images
title_full_unstemmed A Trust-Based Methodology to Evaluate Deep Learning Models for Automatic Diagnosis of Ocular Toxoplasmosis from Fundus Images
title_sort trust-based methodology to evaluate deep learning models for automatic diagnosis of ocular toxoplasmosis from fundus images
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/e9222ee88e094a61ab31e5560289cf84
work_keys_str_mv AT rodrigoparra atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT verenaojeda atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT joseluisvazqueznoguera atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT miguelgarciatorres atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT juliocesarmelloroman atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT cynthiavillalba atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT jacquesfacon atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT federicodivina atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT oliviacardozo atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT veronicaelisacastillo atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT ingridcastromatto atrustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT rodrigoparra trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT verenaojeda trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT joseluisvazqueznoguera trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT miguelgarciatorres trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT juliocesarmelloroman trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT cynthiavillalba trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT jacquesfacon trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT federicodivina trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT oliviacardozo trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT veronicaelisacastillo trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
AT ingridcastromatto trustbasedmethodologytoevaluatedeeplearningmodelsforautomaticdiagnosisofoculartoxoplasmosisfromfundusimages
_version_ 1718412503016275968