Cargando…
Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers
Problem: An application of Explainable Artificial Intelligence Methods for COVID CT-Scan classifiers is presented. Motivation: It is possible that classifiers are using spurious artifacts in dataset images to achieve high performances, and such explainable techniques can help identify this issue. Ai...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8402377/ https://www.ncbi.nlm.nih.gov/pubmed/34451100 http://dx.doi.org/10.3390/s21165657 |
_version_ | 1783745775209021440 |
---|---|
author | Palatnik de Sousa, Iam Vellasco, Marley M. B. R. Costa da Silva, Eduardo |
author_facet | Palatnik de Sousa, Iam Vellasco, Marley M. B. R. Costa da Silva, Eduardo |
author_sort | Palatnik de Sousa, Iam |
collection | PubMed |
description | Problem: An application of Explainable Artificial Intelligence Methods for COVID CT-Scan classifiers is presented. Motivation: It is possible that classifiers are using spurious artifacts in dataset images to achieve high performances, and such explainable techniques can help identify this issue. Aim: For this purpose, several approaches were used in tandem, in order to create a complete overview of the classificatios. Methodology: The techniques used included GradCAM, LIME, RISE, Squaregrid, and direct Gradient approaches (Vanilla, Smooth, Integrated). Main results: Among the deep neural networks architectures evaluated for this image classification task, VGG16 was shown to be most affected by biases towards spurious artifacts, while DenseNet was notably more robust against them. Further impacts: Results further show that small differences in validation accuracies can cause drastic changes in explanation heatmaps for DenseNet architectures, indicating that small changes in validation accuracy may have large impacts on the biases learned by the networks. Notably, it is important to notice that the strong performance metrics achieved by all these networks (Accuracy, F1 score, AUC all in the 80 to 90% range) could give users the erroneous impression that there is no bias. However, the analysis of the explanation heatmaps highlights the bias. |
format | Online Article Text |
id | pubmed-8402377 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-84023772021-08-29 Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers Palatnik de Sousa, Iam Vellasco, Marley M. B. R. Costa da Silva, Eduardo Sensors (Basel) Article Problem: An application of Explainable Artificial Intelligence Methods for COVID CT-Scan classifiers is presented. Motivation: It is possible that classifiers are using spurious artifacts in dataset images to achieve high performances, and such explainable techniques can help identify this issue. Aim: For this purpose, several approaches were used in tandem, in order to create a complete overview of the classificatios. Methodology: The techniques used included GradCAM, LIME, RISE, Squaregrid, and direct Gradient approaches (Vanilla, Smooth, Integrated). Main results: Among the deep neural networks architectures evaluated for this image classification task, VGG16 was shown to be most affected by biases towards spurious artifacts, while DenseNet was notably more robust against them. Further impacts: Results further show that small differences in validation accuracies can cause drastic changes in explanation heatmaps for DenseNet architectures, indicating that small changes in validation accuracy may have large impacts on the biases learned by the networks. Notably, it is important to notice that the strong performance metrics achieved by all these networks (Accuracy, F1 score, AUC all in the 80 to 90% range) could give users the erroneous impression that there is no bias. However, the analysis of the explanation heatmaps highlights the bias. MDPI 2021-08-23 /pmc/articles/PMC8402377/ /pubmed/34451100 http://dx.doi.org/10.3390/s21165657 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Palatnik de Sousa, Iam Vellasco, Marley M. B. R. Costa da Silva, Eduardo Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers |
title | Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers |
title_full | Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers |
title_fullStr | Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers |
title_full_unstemmed | Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers |
title_short | Explainable Artificial Intelligence for Bias Detection in COVID CT-Scan Classifiers |
title_sort | explainable artificial intelligence for bias detection in covid ct-scan classifiers |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8402377/ https://www.ncbi.nlm.nih.gov/pubmed/34451100 http://dx.doi.org/10.3390/s21165657 |
work_keys_str_mv | AT palatnikdesousaiam explainableartificialintelligenceforbiasdetectionincovidctscanclassifiers AT vellascomarleymbr explainableartificialintelligenceforbiasdetectionincovidctscanclassifiers AT costadasilvaeduardo explainableartificialintelligenceforbiasdetectionincovidctscanclassifiers |