Cargando…

Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators

As deep learning is widely used in the radiology field, the explainability of Artificial Intelligence (AI) models is becoming increasingly essential to gain clinicians’ trust when using the models for diagnosis. In this research, three experiment sets were conducted with a U-Net architecture to impr...

Descripción completa

Detalles Bibliográficos
Autores principales: Watanabe, Akino, Ketabi, Sara, Namdar, Khashayar, Khalvati, Farzad
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365129/
https://www.ncbi.nlm.nih.gov/pubmed/37492678
http://dx.doi.org/10.3389/fradi.2022.991683
_version_ 1785076987923005440
author Watanabe, Akino
Ketabi, Sara
Namdar, Khashayar
Khalvati, Farzad
author_facet Watanabe, Akino
Ketabi, Sara
Namdar, Khashayar
Khalvati, Farzad
author_sort Watanabe, Akino
collection PubMed
description As deep learning is widely used in the radiology field, the explainability of Artificial Intelligence (AI) models is becoming increasingly essential to gain clinicians’ trust when using the models for diagnosis. In this research, three experiment sets were conducted with a U-Net architecture to improve the disease classification performance while enhancing the heatmaps corresponding to the model's focus through incorporating heatmap generators during training. All experiments used the dataset that contained chest radiographs, associated labels from one of the three conditions [“normal”, “congestive heart failure (CHF)”, and “pneumonia”], and numerical information regarding a radiologist's eye-gaze coordinates on the images. The paper that introduced this dataset developed a U-Net model, which was treated as the baseline model for this research, to show how the eye-gaze data can be used in multi-modal training for explainability improvement and disease classification. To compare the classification performances among this research's three experiment sets and the baseline model, the 95% confidence intervals (CI) of the area under the receiver operating characteristic curve (AUC) were measured. The best method achieved an AUC of 0.913 with a 95% CI of [0.860, 0.966]. “Pneumonia” and “CHF” classes, which the baseline model struggled the most to classify, had the greatest improvements, resulting in AUCs of 0.859 with a 95% CI of [0.732, 0.957] and 0.962 with a 95% CI of [0.933, 0.989], respectively. The decoder of the U-Net for the best-performing proposed method generated heatmaps that highlight the determining image parts in model classifications. These predicted heatmaps, which can be used for the explainability of the model, also improved to align well with the radiologist's eye-gaze data. Hence, this work showed that incorporating heatmap generators and eye-gaze information into training can simultaneously improve disease classification and provide explainable visuals that align well with how the radiologist viewed the chest radiographs when making diagnosis.
format Online
Article
Text
id pubmed-10365129
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103651292023-07-25 Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators Watanabe, Akino Ketabi, Sara Namdar, Khashayar Khalvati, Farzad Front Radiol Radiology As deep learning is widely used in the radiology field, the explainability of Artificial Intelligence (AI) models is becoming increasingly essential to gain clinicians’ trust when using the models for diagnosis. In this research, three experiment sets were conducted with a U-Net architecture to improve the disease classification performance while enhancing the heatmaps corresponding to the model's focus through incorporating heatmap generators during training. All experiments used the dataset that contained chest radiographs, associated labels from one of the three conditions [“normal”, “congestive heart failure (CHF)”, and “pneumonia”], and numerical information regarding a radiologist's eye-gaze coordinates on the images. The paper that introduced this dataset developed a U-Net model, which was treated as the baseline model for this research, to show how the eye-gaze data can be used in multi-modal training for explainability improvement and disease classification. To compare the classification performances among this research's three experiment sets and the baseline model, the 95% confidence intervals (CI) of the area under the receiver operating characteristic curve (AUC) were measured. The best method achieved an AUC of 0.913 with a 95% CI of [0.860, 0.966]. “Pneumonia” and “CHF” classes, which the baseline model struggled the most to classify, had the greatest improvements, resulting in AUCs of 0.859 with a 95% CI of [0.732, 0.957] and 0.962 with a 95% CI of [0.933, 0.989], respectively. The decoder of the U-Net for the best-performing proposed method generated heatmaps that highlight the determining image parts in model classifications. These predicted heatmaps, which can be used for the explainability of the model, also improved to align well with the radiologist's eye-gaze data. Hence, this work showed that incorporating heatmap generators and eye-gaze information into training can simultaneously improve disease classification and provide explainable visuals that align well with how the radiologist viewed the chest radiographs when making diagnosis. Frontiers Media S.A. 2022-10-11 /pmc/articles/PMC10365129/ /pubmed/37492678 http://dx.doi.org/10.3389/fradi.2022.991683 Text en © 2022 Watanabe, Ketabi, Namdar and Khalvati. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Radiology
Watanabe, Akino
Ketabi, Sara
Namdar, Khashayar
Khalvati, Farzad
Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators
title Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators
title_full Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators
title_fullStr Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators
title_full_unstemmed Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators
title_short Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators
title_sort improving disease classification performance and explainability of deep learning models in radiology with heatmap generators
topic Radiology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365129/
https://www.ncbi.nlm.nih.gov/pubmed/37492678
http://dx.doi.org/10.3389/fradi.2022.991683
work_keys_str_mv AT watanabeakino improvingdiseaseclassificationperformanceandexplainabilityofdeeplearningmodelsinradiologywithheatmapgenerators
AT ketabisara improvingdiseaseclassificationperformanceandexplainabilityofdeeplearningmodelsinradiologywithheatmapgenerators
AT namdarkhashayar improvingdiseaseclassificationperformanceandexplainabilityofdeeplearningmodelsinradiologywithheatmapgenerators
AT khalvatifarzad improvingdiseaseclassificationperformanceandexplainabilityofdeeplearningmodelsinradiologywithheatmapgenerators