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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |