Interpretable multimodal classification for age-related macular degeneration diagnosis.

Explainable Artificial Intelligence (XAI) is an emerging machine learning field that has been successful in medical image analysis. Interpretable approaches are able to "unbox" the black-box decisions made by AI systems, aiding medical doctors to justify their diagnostics better. In this p...

Full description

Saved in:
Bibliographic Details
Main Authors: Carla Vairetti, Sebastián Maldonado, Loreto Cuitino, Cristhian A Urzua
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0311811
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849254154714742784
author Carla Vairetti
Sebastián Maldonado
Loreto Cuitino
Cristhian A Urzua
author_facet Carla Vairetti
Sebastián Maldonado
Loreto Cuitino
Cristhian A Urzua
author_sort Carla Vairetti
collection DOAJ
description Explainable Artificial Intelligence (XAI) is an emerging machine learning field that has been successful in medical image analysis. Interpretable approaches are able to "unbox" the black-box decisions made by AI systems, aiding medical doctors to justify their diagnostics better. In this paper, we analyze the performance of three different XAI strategies for medical image analysis in ophthalmology. We consider a multimodal deep learning model that combines optical coherence tomography (OCT) and infrared reflectance (IR) imaging for the diagnosis of age-related macular degeneration (AMD). The classification model is able to achieve an accuracy of 0.94, performing better than other unimodal alternatives. We analyze the XAI methods in terms of their ability to identify retinal damage and ease of interpretation, concluding that grad-CAM and guided grad-CAM can be combined to have both a coarse visual justification and a fine-grained analysis of the retinal layers. We provide important insights and recommendations for practitioners on how to design automated and explainable screening tests based on the combination of two image sources.
format Article
id doaj-art-9d7738e3152f46f09af53cd8cf54db2b
institution Kabale University
issn 1932-6203
language English
publishDate 2024-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-9d7738e3152f46f09af53cd8cf54db2b2025-08-20T03:56:05ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011911e031181110.1371/journal.pone.0311811Interpretable multimodal classification for age-related macular degeneration diagnosis.Carla VairettiSebastián MaldonadoLoreto CuitinoCristhian A UrzuaExplainable Artificial Intelligence (XAI) is an emerging machine learning field that has been successful in medical image analysis. Interpretable approaches are able to "unbox" the black-box decisions made by AI systems, aiding medical doctors to justify their diagnostics better. In this paper, we analyze the performance of three different XAI strategies for medical image analysis in ophthalmology. We consider a multimodal deep learning model that combines optical coherence tomography (OCT) and infrared reflectance (IR) imaging for the diagnosis of age-related macular degeneration (AMD). The classification model is able to achieve an accuracy of 0.94, performing better than other unimodal alternatives. We analyze the XAI methods in terms of their ability to identify retinal damage and ease of interpretation, concluding that grad-CAM and guided grad-CAM can be combined to have both a coarse visual justification and a fine-grained analysis of the retinal layers. We provide important insights and recommendations for practitioners on how to design automated and explainable screening tests based on the combination of two image sources.https://doi.org/10.1371/journal.pone.0311811
spellingShingle Carla Vairetti
Sebastián Maldonado
Loreto Cuitino
Cristhian A Urzua
Interpretable multimodal classification for age-related macular degeneration diagnosis.
PLoS ONE
title Interpretable multimodal classification for age-related macular degeneration diagnosis.
title_full Interpretable multimodal classification for age-related macular degeneration diagnosis.
title_fullStr Interpretable multimodal classification for age-related macular degeneration diagnosis.
title_full_unstemmed Interpretable multimodal classification for age-related macular degeneration diagnosis.
title_short Interpretable multimodal classification for age-related macular degeneration diagnosis.
title_sort interpretable multimodal classification for age related macular degeneration diagnosis
url https://doi.org/10.1371/journal.pone.0311811
work_keys_str_mv AT carlavairetti interpretablemultimodalclassificationforagerelatedmaculardegenerationdiagnosis
AT sebastianmaldonado interpretablemultimodalclassificationforagerelatedmaculardegenerationdiagnosis
AT loretocuitino interpretablemultimodalclassificationforagerelatedmaculardegenerationdiagnosis
AT cristhianaurzua interpretablemultimodalclassificationforagerelatedmaculardegenerationdiagnosis