Can Deep Learning-Based Volumetric Analysis Predict Oxygen Demand Increase in Patients with COVID-19 Pneumonia?

<i>Background and Objectives</i>: This study aimed to investigate whether predictive indicators for the deterioration of respiratory status can be derived from the deep learning data analysis of initial chest computed tomography (CT) scans of patients with coronavirus disease 2019 (COVID...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Marie Takahashi, Tomoyuki Fujioka, Toshihiro Horii, Koichiro Kimura, Mizuki Kimura, Yurika Hashimoto, Yoshio Kitazume, Mitsuhiro Kishino, Ukihide Tateishi
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/8b2884b6076343c2995406c06af04faf
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:8b2884b6076343c2995406c06af04faf
record_format dspace
spelling oai:doaj.org-article:8b2884b6076343c2995406c06af04faf2021-11-25T18:18:05ZCan Deep Learning-Based Volumetric Analysis Predict Oxygen Demand Increase in Patients with COVID-19 Pneumonia?10.3390/medicina571111481648-91441010-660Xhttps://doaj.org/article/8b2884b6076343c2995406c06af04faf2021-10-01T00:00:00Zhttps://www.mdpi.com/1648-9144/57/11/1148https://doaj.org/toc/1010-660Xhttps://doaj.org/toc/1648-9144<i>Background and Objectives</i>: This study aimed to investigate whether predictive indicators for the deterioration of respiratory status can be derived from the deep learning data analysis of initial chest computed tomography (CT) scans of patients with coronavirus disease 2019 (COVID-19). <i>Materials and Methods</i>: Out of 117 CT scans of 75 patients with COVID-19 admitted to our hospital between April and June 2020, we retrospectively analyzed 79 CT scans that had a definite time of onset and were performed prior to any medication intervention. Patients were grouped according to the presence or absence of increased oxygen demand after CT scan. Quantitative volume data of lung opacity were measured automatically using a deep learning-based image analysis system. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of the opacity volume data were calculated to evaluate the accuracy of the system in predicting the deterioration of respiratory status. <i>Results</i>: All 79 CT scans were included (median age, 62 years (interquartile range, 46–77 years); 56 (70.9%) were male. The volume of opacity was significantly higher for the increased oxygen demand group than for the nonincreased oxygen demand group (585.3 vs. 132.8 mL, <i>p</i> < 0.001). The sensitivity, specificity, and AUC were 76.5%, 68.2%, and 0.737, respectively, in the prediction of increased oxygen demand. <i>Conclusion:</i> Deep learning-based quantitative analysis of the affected lung volume in the initial CT scans of patients with COVID-19 can predict the deterioration of respiratory status to improve treatment and resource management.Marie TakahashiTomoyuki FujiokaToshihiro HoriiKoichiro KimuraMizuki KimuraYurika HashimotoYoshio KitazumeMitsuhiro KishinoUkihide TateishiMDPI AGarticlechest imagingCOVID-19deep learningradiologychest CToxygen demandMedicine (General)R5-920ENMedicina, Vol 57, Iss 1148, p 1148 (2021)
institution DOAJ
collection DOAJ
language EN
topic chest imaging
COVID-19
deep learning
radiology
chest CT
oxygen demand
Medicine (General)
R5-920
spellingShingle chest imaging
COVID-19
deep learning
radiology
chest CT
oxygen demand
Medicine (General)
R5-920
Marie Takahashi
Tomoyuki Fujioka
Toshihiro Horii
Koichiro Kimura
Mizuki Kimura
Yurika Hashimoto
Yoshio Kitazume
Mitsuhiro Kishino
Ukihide Tateishi
Can Deep Learning-Based Volumetric Analysis Predict Oxygen Demand Increase in Patients with COVID-19 Pneumonia?
description <i>Background and Objectives</i>: This study aimed to investigate whether predictive indicators for the deterioration of respiratory status can be derived from the deep learning data analysis of initial chest computed tomography (CT) scans of patients with coronavirus disease 2019 (COVID-19). <i>Materials and Methods</i>: Out of 117 CT scans of 75 patients with COVID-19 admitted to our hospital between April and June 2020, we retrospectively analyzed 79 CT scans that had a definite time of onset and were performed prior to any medication intervention. Patients were grouped according to the presence or absence of increased oxygen demand after CT scan. Quantitative volume data of lung opacity were measured automatically using a deep learning-based image analysis system. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of the opacity volume data were calculated to evaluate the accuracy of the system in predicting the deterioration of respiratory status. <i>Results</i>: All 79 CT scans were included (median age, 62 years (interquartile range, 46–77 years); 56 (70.9%) were male. The volume of opacity was significantly higher for the increased oxygen demand group than for the nonincreased oxygen demand group (585.3 vs. 132.8 mL, <i>p</i> < 0.001). The sensitivity, specificity, and AUC were 76.5%, 68.2%, and 0.737, respectively, in the prediction of increased oxygen demand. <i>Conclusion:</i> Deep learning-based quantitative analysis of the affected lung volume in the initial CT scans of patients with COVID-19 can predict the deterioration of respiratory status to improve treatment and resource management.
format article
author Marie Takahashi
Tomoyuki Fujioka
Toshihiro Horii
Koichiro Kimura
Mizuki Kimura
Yurika Hashimoto
Yoshio Kitazume
Mitsuhiro Kishino
Ukihide Tateishi
author_facet Marie Takahashi
Tomoyuki Fujioka
Toshihiro Horii
Koichiro Kimura
Mizuki Kimura
Yurika Hashimoto
Yoshio Kitazume
Mitsuhiro Kishino
Ukihide Tateishi
author_sort Marie Takahashi
title Can Deep Learning-Based Volumetric Analysis Predict Oxygen Demand Increase in Patients with COVID-19 Pneumonia?
title_short Can Deep Learning-Based Volumetric Analysis Predict Oxygen Demand Increase in Patients with COVID-19 Pneumonia?
title_full Can Deep Learning-Based Volumetric Analysis Predict Oxygen Demand Increase in Patients with COVID-19 Pneumonia?
title_fullStr Can Deep Learning-Based Volumetric Analysis Predict Oxygen Demand Increase in Patients with COVID-19 Pneumonia?
title_full_unstemmed Can Deep Learning-Based Volumetric Analysis Predict Oxygen Demand Increase in Patients with COVID-19 Pneumonia?
title_sort can deep learning-based volumetric analysis predict oxygen demand increase in patients with covid-19 pneumonia?
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/8b2884b6076343c2995406c06af04faf
work_keys_str_mv AT marietakahashi candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
AT tomoyukifujioka candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
AT toshihirohorii candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
AT koichirokimura candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
AT mizukikimura candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
AT yurikahashimoto candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
AT yoshiokitazume candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
AT mitsuhirokishino candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
AT ukihidetateishi candeeplearningbasedvolumetricanalysispredictoxygendemandincreaseinpatientswithcovid19pneumonia
_version_ 1718411394377842688