Cargando…
Explainable emphysema detection on chest radiographs with deep learning
We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphyse...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9333227/ https://www.ncbi.nlm.nih.gov/pubmed/35900979 http://dx.doi.org/10.1371/journal.pone.0267539 |
_version_ | 1784758826009886720 |
---|---|
author | Çallı, Erdi Murphy, Keelin Scholten, Ernst T. Schalekamp, Steven van Ginneken, Bram |
author_facet | Çallı, Erdi Murphy, Keelin Scholten, Ernst T. Schalekamp, Steven van Ginneken, Bram |
author_sort | Çallı, Erdi |
collection | PubMed |
description | We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong’s test is used to compare with the black-box model ROC and McNemar’s test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392. |
format | Online Article Text |
id | pubmed-9333227 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-93332272022-07-29 Explainable emphysema detection on chest radiographs with deep learning Çallı, Erdi Murphy, Keelin Scholten, Ernst T. Schalekamp, Steven van Ginneken, Bram PLoS One Research Article We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong’s test is used to compare with the black-box model ROC and McNemar’s test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392. Public Library of Science 2022-07-28 /pmc/articles/PMC9333227/ /pubmed/35900979 http://dx.doi.org/10.1371/journal.pone.0267539 Text en © 2022 Çallı et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Çallı, Erdi Murphy, Keelin Scholten, Ernst T. Schalekamp, Steven van Ginneken, Bram Explainable emphysema detection on chest radiographs with deep learning |
title | Explainable emphysema detection on chest radiographs with deep learning |
title_full | Explainable emphysema detection on chest radiographs with deep learning |
title_fullStr | Explainable emphysema detection on chest radiographs with deep learning |
title_full_unstemmed | Explainable emphysema detection on chest radiographs with deep learning |
title_short | Explainable emphysema detection on chest radiographs with deep learning |
title_sort | explainable emphysema detection on chest radiographs with deep learning |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9333227/ https://www.ncbi.nlm.nih.gov/pubmed/35900979 http://dx.doi.org/10.1371/journal.pone.0267539 |
work_keys_str_mv | AT callıerdi explainableemphysemadetectiononchestradiographswithdeeplearning AT murphykeelin explainableemphysemadetectiononchestradiographswithdeeplearning AT scholtenernstt explainableemphysemadetectiononchestradiographswithdeeplearning AT schalekampsteven explainableemphysemadetectiononchestradiographswithdeeplearning AT vanginnekenbram explainableemphysemadetectiononchestradiographswithdeeplearning |