Predicting COVID-19 Pneumonia Severity on Chest X-ray with Deep Learning
Purpose: The need to streamline patient management for COVID-19 has become more pressing than ever. Chest X-rays provide a non-invasive (potentially bedside) tool to monitor the progression of the disease. In this study, we present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images. Such a tool can gauge severity of COVID-19 lung infections (and pneumonia in general) that can be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the ICU. Methods: Images from a public COVID-19 database were scored retrospectively by three blinded experts in terms of the extent of lung involvement as well as the degree of opacity. A neural network model that was pre-trained on large (non-COVID-19) chest X-ray datasets is used to construct features for COVID-19 images which are predictive for our task. Results: This study finds that training a regression model on a subset of the outputs from an this pre-trained chest X-ray model predicts our geographic extent score (range 0-8) with 1.14 mean absolute error (MAE) and our lung opacity score (range 0-6) with 0.78 MAE. Conclusions: These results indicate that our model's ability to gauge severity of COVID-19 lung infections could be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the intensive care unit (ICU). A proper clinical trial is needed to evaluate efficacy. To enable this we make our code, labels, and data available online at https://github.com/mlmed/torchxrayvision/tree/master/scripts/covid-severity and https://github.com/ieee8023/covid-chestxray-dataset.
Medienart: |
Preprint |
---|
Erscheinungsjahr: |
2020 |
---|---|
Erschienen: |
2020 |
Enthalten in: |
arXiv.org - (2020) vom: 24. Mai Zur Gesamtaufnahme - year:2020 |
---|
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Cohen, Joseph Paul [VerfasserIn] |
---|
Links: |
Volltext [kostenfrei] |
---|
Förderinstitution / Projekttitel: |
|
---|
PPN (Katalog-ID): |
XAR017990874 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | XAR017990874 | ||
003 | DE-627 | ||
005 | 20230429070934.0 | ||
007 | cr uuu---uuuuu | ||
008 | 200526s2020 xx |||||o 00| ||eng c | ||
035 | |a (DE-627)XAR017990874 | ||
035 | |a (arXiv)2005.11856 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | |a 000 |q DE-84 | |
082 | 0 | |a 620 |q DE-84 | |
082 | 0 | |a 570 |q DE-84 | |
082 | 0 | |a 510 |q DE-84 | |
100 | 1 | |a Cohen, Joseph Paul |e verfasserin |4 aut | |
245 | 1 | 0 | |a Predicting COVID-19 Pneumonia Severity on Chest X-ray with Deep Learning |
264 | 1 | |c 2020 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a Purpose: The need to streamline patient management for COVID-19 has become more pressing than ever. Chest X-rays provide a non-invasive (potentially bedside) tool to monitor the progression of the disease. In this study, we present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images. Such a tool can gauge severity of COVID-19 lung infections (and pneumonia in general) that can be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the ICU. Methods: Images from a public COVID-19 database were scored retrospectively by three blinded experts in terms of the extent of lung involvement as well as the degree of opacity. A neural network model that was pre-trained on large (non-COVID-19) chest X-ray datasets is used to construct features for COVID-19 images which are predictive for our task. Results: This study finds that training a regression model on a subset of the outputs from an this pre-trained chest X-ray model predicts our geographic extent score (range 0-8) with 1.14 mean absolute error (MAE) and our lung opacity score (range 0-6) with 0.78 MAE. Conclusions: These results indicate that our model's ability to gauge severity of COVID-19 lung infections could be used for escalation or de-escalation of care as well as monitoring treatment efficacy, especially in the intensive care unit (ICU). A proper clinical trial is needed to evaluate efficacy. To enable this we make our code, labels, and data available online at https://github.com/mlmed/torchxrayvision/tree/master/scripts/covid-severity and https://github.com/ieee8023/covid-chestxray-dataset | ||
700 | 1 | |a Dao, Lan |e verfasserin |4 aut | |
700 | 1 | |a Morrison, Paul |e verfasserin |4 aut | |
700 | 1 | |a Roth, Karsten |e verfasserin |4 aut | |
700 | 1 | |a Bengio, Yoshua |e verfasserin |4 aut | |
700 | 1 | |a Shen, Beiyi |e verfasserin |4 aut | |
700 | 1 | |a Abbasi, Almas |e verfasserin |4 aut | |
700 | 1 | |a Hoshmand-Kochi, Mahsa |e verfasserin |4 aut | |
700 | 1 | |a Ghassemi, Marzyeh |e verfasserin |4 aut | |
700 | 1 | |a Li, Haifang |e verfasserin |4 aut | |
700 | 1 | |a Duong, Tim Q |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t arXiv.org |g (2020) vom: 24. Mai |
773 | 1 | 8 | |g year:2020 |g day:24 |g month:05 |
856 | 4 | 0 | |u https://arxiv.org/abs/2005.11856 |z kostenfrei |3 Volltext |
912 | |a GBV_XAR | ||
912 | |a SSG-OLC-PHA | ||
951 | |a AR | ||
952 | |j 2020 |b 24 |c 05 | ||
953 | |2 045F |a 000 | ||
953 | |2 045F |a 620 | ||
953 | |2 045F |a 570 | ||
953 | |2 045F |a 510 |