Cargando…
Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs
Accurate image interpretation of Waters’ and Caldwell view radiographs used for sinusitis screening is challenging. Therefore, we developed a deep learning algorithm for diagnosing frontal, ethmoid, and maxillary sinusitis on both Waters’ and Caldwell views. The datasets were selected for the traini...
Autores principales: | , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7914751/ https://www.ncbi.nlm.nih.gov/pubmed/33562764 http://dx.doi.org/10.3390/diagnostics11020250 |
_version_ | 1783657076821590016 |
---|---|
author | Jeon, Yejin Lee, Kyeorye Sunwoo, Leonard Choi, Dongjun Oh, Dong Yul Lee, Kyong Joon Kim, Youngjune Kim, Jeong-Whun Cho, Se Jin Baik, Sung Hyun Yoo, Roh-eul Bae, Yun Jung Choi, Byung Se Jung, Cheolkyu Kim, Jae Hyoung |
author_facet | Jeon, Yejin Lee, Kyeorye Sunwoo, Leonard Choi, Dongjun Oh, Dong Yul Lee, Kyong Joon Kim, Youngjune Kim, Jeong-Whun Cho, Se Jin Baik, Sung Hyun Yoo, Roh-eul Bae, Yun Jung Choi, Byung Se Jung, Cheolkyu Kim, Jae Hyoung |
author_sort | Jeon, Yejin |
collection | PubMed |
description | Accurate image interpretation of Waters’ and Caldwell view radiographs used for sinusitis screening is challenging. Therefore, we developed a deep learning algorithm for diagnosing frontal, ethmoid, and maxillary sinusitis on both Waters’ and Caldwell views. The datasets were selected for the training and validation set (n = 1403, sinusitis% = 34.3%) and the test set (n = 132, sinusitis% = 29.5%) by temporal separation. The algorithm can simultaneously detect and classify each paranasal sinus using both Waters’ and Caldwell views without manual cropping. Single- and multi-view models were compared. Our proposed algorithm satisfactorily diagnosed frontal, ethmoid, and maxillary sinusitis on both Waters’ and Caldwell views (area under the curve (AUC), 0.71 (95% confidence interval, 0.62–0.80), 0.78 (0.72–0.85), and 0.88 (0.84–0.92), respectively). The one-sided DeLong’s test was used to compare the AUCs, and the Obuchowski–Rockette model was used to pool the AUCs of the radiologists. The algorithm yielded a higher AUC than radiologists for ethmoid and maxillary sinusitis (p = 0.012 and 0.013, respectively). The multi-view model also exhibited a higher AUC than the single Waters’ view model for maxillary sinusitis (p = 0.038). Therefore, our algorithm showed diagnostic performances comparable to radiologists and enhanced the value of radiography as a first-line imaging modality in assessing multiple sinusitis. |
format | Online Article Text |
id | pubmed-7914751 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-79147512021-03-01 Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs Jeon, Yejin Lee, Kyeorye Sunwoo, Leonard Choi, Dongjun Oh, Dong Yul Lee, Kyong Joon Kim, Youngjune Kim, Jeong-Whun Cho, Se Jin Baik, Sung Hyun Yoo, Roh-eul Bae, Yun Jung Choi, Byung Se Jung, Cheolkyu Kim, Jae Hyoung Diagnostics (Basel) Article Accurate image interpretation of Waters’ and Caldwell view radiographs used for sinusitis screening is challenging. Therefore, we developed a deep learning algorithm for diagnosing frontal, ethmoid, and maxillary sinusitis on both Waters’ and Caldwell views. The datasets were selected for the training and validation set (n = 1403, sinusitis% = 34.3%) and the test set (n = 132, sinusitis% = 29.5%) by temporal separation. The algorithm can simultaneously detect and classify each paranasal sinus using both Waters’ and Caldwell views without manual cropping. Single- and multi-view models were compared. Our proposed algorithm satisfactorily diagnosed frontal, ethmoid, and maxillary sinusitis on both Waters’ and Caldwell views (area under the curve (AUC), 0.71 (95% confidence interval, 0.62–0.80), 0.78 (0.72–0.85), and 0.88 (0.84–0.92), respectively). The one-sided DeLong’s test was used to compare the AUCs, and the Obuchowski–Rockette model was used to pool the AUCs of the radiologists. The algorithm yielded a higher AUC than radiologists for ethmoid and maxillary sinusitis (p = 0.012 and 0.013, respectively). The multi-view model also exhibited a higher AUC than the single Waters’ view model for maxillary sinusitis (p = 0.038). Therefore, our algorithm showed diagnostic performances comparable to radiologists and enhanced the value of radiography as a first-line imaging modality in assessing multiple sinusitis. MDPI 2021-02-05 /pmc/articles/PMC7914751/ /pubmed/33562764 http://dx.doi.org/10.3390/diagnostics11020250 Text en © 2021 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Jeon, Yejin Lee, Kyeorye Sunwoo, Leonard Choi, Dongjun Oh, Dong Yul Lee, Kyong Joon Kim, Youngjune Kim, Jeong-Whun Cho, Se Jin Baik, Sung Hyun Yoo, Roh-eul Bae, Yun Jung Choi, Byung Se Jung, Cheolkyu Kim, Jae Hyoung Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs |
title | Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs |
title_full | Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs |
title_fullStr | Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs |
title_full_unstemmed | Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs |
title_short | Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs |
title_sort | deep learning for diagnosis of paranasal sinusitis using multi-view radiographs |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7914751/ https://www.ncbi.nlm.nih.gov/pubmed/33562764 http://dx.doi.org/10.3390/diagnostics11020250 |
work_keys_str_mv | AT jeonyejin deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT leekyeorye deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT sunwooleonard deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT choidongjun deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT ohdongyul deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT leekyongjoon deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT kimyoungjune deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT kimjeongwhun deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT chosejin deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT baiksunghyun deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT yooroheul deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT baeyunjung deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT choibyungse deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT jungcheolkyu deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs AT kimjaehyoung deeplearningfordiagnosisofparanasalsinusitisusingmultiviewradiographs |