Cargando…
Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation
Convolutional neural networks (CNNs) have been successfully applied to chest x-ray (CXR) images. Moreover, annotated bounding boxes have been shown to improve the interpretability of a CNN in terms of localizing abnormalities. However, only a few relatively small CXR datasets containing bounding box...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365091/ https://www.ncbi.nlm.nih.gov/pubmed/37492389 http://dx.doi.org/10.3389/fradi.2023.1088068 |
_version_ | 1785076979254427648 |
---|---|
author | Bigolin Lanfredi, Ricardo Schroeder, Joyce D. Tasdizen, Tolga |
author_facet | Bigolin Lanfredi, Ricardo Schroeder, Joyce D. Tasdizen, Tolga |
author_sort | Bigolin Lanfredi, Ricardo |
collection | PubMed |
description | Convolutional neural networks (CNNs) have been successfully applied to chest x-ray (CXR) images. Moreover, annotated bounding boxes have been shown to improve the interpretability of a CNN in terms of localizing abnormalities. However, only a few relatively small CXR datasets containing bounding boxes are available, and collecting them is very costly. Opportunely, eye-tracking (ET) data can be collected during the clinical workflow of a radiologist. We use ET data recorded from radiologists while dictating CXR reports to train CNNs. We extract snippets from the ET data by associating them with the dictation of keywords and use them to supervise the localization of specific abnormalities. We show that this method can improve a model’s interpretability without impacting its image-level classification. |
format | Online Article Text |
id | pubmed-10365091 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-103650912023-07-25 Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation Bigolin Lanfredi, Ricardo Schroeder, Joyce D. Tasdizen, Tolga Front Radiol Radiology Convolutional neural networks (CNNs) have been successfully applied to chest x-ray (CXR) images. Moreover, annotated bounding boxes have been shown to improve the interpretability of a CNN in terms of localizing abnormalities. However, only a few relatively small CXR datasets containing bounding boxes are available, and collecting them is very costly. Opportunely, eye-tracking (ET) data can be collected during the clinical workflow of a radiologist. We use ET data recorded from radiologists while dictating CXR reports to train CNNs. We extract snippets from the ET data by associating them with the dictation of keywords and use them to supervise the localization of specific abnormalities. We show that this method can improve a model’s interpretability without impacting its image-level classification. Frontiers Media S.A. 2023-06-22 /pmc/articles/PMC10365091/ /pubmed/37492389 http://dx.doi.org/10.3389/fradi.2023.1088068 Text en © 2023 Bigolin Lanfredi, Schroeder and Tasdizen. 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 Bigolin Lanfredi, Ricardo Schroeder, Joyce D. Tasdizen, Tolga Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation |
title | Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation |
title_full | Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation |
title_fullStr | Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation |
title_full_unstemmed | Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation |
title_short | Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation |
title_sort | localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation |
topic | Radiology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365091/ https://www.ncbi.nlm.nih.gov/pubmed/37492389 http://dx.doi.org/10.3389/fradi.2023.1088068 |
work_keys_str_mv | AT bigolinlanfrediricardo localizationsupervisionofchestxrayclassifiersusinglabelspecificeyetrackingannotation AT schroederjoyced localizationsupervisionofchestxrayclassifiersusinglabelspecificeyetrackingannotation AT tasdizentolga localizationsupervisionofchestxrayclassifiersusinglabelspecificeyetrackingannotation |