Literature DB >> 33259441

A Deep-Learning Diagnostic Support System for the Detection of COVID-19 Using Chest Radiographs: A Multireader Validation Study.

Matthias Fontanellaz1, Lukas Ebner2, Adrian Huber2, Alan Peters2, Laura Löbelenz2, Cynthia Hourscht2, Jeremias Klaus2, Jaro Munz2, Thomas Ruder2, Dionysios Drakopoulos3, Dominik Sieron3, Elias Primetis3, Johannes T Heverhagen2, Stavroula Mougiakakou, Andreas Christe.   

Abstract

MATERIALS AND METHODS: Five publicly available databases comprising normal CXR, confirmed COVID-19 pneumonia cases, and other pneumonias were used. After the harmonization of the data, the training set included 7966 normal cases, 5451 with other pneumonia, and 258 CXRs with COVID-19 pneumonia, whereas in the testing data set, each category was represented by 100 cases. Eleven blinded radiologists with various levels of expertise independently read the testing data set. The data were analyzed separately with the newly proposed artificial intelligence-based system and by consultant radiologists and residents, with respect to positive predictive value (PPV), sensitivity, and F-score (harmonic mean for PPV and sensitivity). The χ2 test was used to compare the sensitivity, specificity, accuracy, PPV, and F-scores of the readers and the system.
RESULTS: The proposed system achieved higher overall diagnostic accuracy (94.3%) than the radiologists (61.4% ± 5.3%). The radiologists reached average sensitivities for normal CXR, other type of pneumonia, and COVID-19 pneumonia of 85.0% ± 12.8%, 60.1% ± 12.2%, and 53.2% ± 11.2%, respectively, which were significantly lower than the results achieved by the algorithm (98.0%, 88.0%, and 97.0%; P < 0.00032). The mean PPVs for all 11 radiologists for the 3 categories were 82.4%, 59.0%, and 59.0% for the healthy, other pneumonia, and COVID-19 pneumonia, respectively, resulting in an F-score of 65.5% ± 12.4%, which was significantly lower than the F-score of the algorithm (94.3% ± 2.0%, P < 0.00001). When other pneumonia and COVID-19 pneumonia cases were pooled, the proposed system reached an accuracy of 95.7% for any pathology and the radiologists, 88.8%. The overall accuracy of consultants did not vary significantly compared with residents (65.0% ± 5.8% vs 67.4% ± 4.2%); however, consultants detected significantly more COVID-19 pneumonia cases (P = 0.008) and less healthy cases (P < 0.00001).
CONCLUSIONS: The system showed robust accuracy for COVID-19 pneumonia detection on CXR and surpassed radiologists at various training levels.
Copyright © 2020 Wolters Kluwer Health, Inc. All rights reserved.

Entities:  

Year:  2021        PMID: 33259441     DOI: 10.1097/RLI.0000000000000748

Source DB:  PubMed          Journal:  Invest Radiol        ISSN: 0020-9996            Impact factor:   6.016


  8 in total

1.  Development and validation of bone-suppressed deep learning classification of COVID-19 presentation in chest radiographs.

Authors:  Ngo Fung Daniel Lam; Hongfei Sun; Liming Song; Dongrong Yang; Shaohua Zhi; Ge Ren; Pak Hei Chou; Shiu Bun Nelson Wan; Man Fung Esther Wong; King Kwong Chan; Hoi Ching Hailey Tsang; Feng-Ming Spring Kong; Yì Xiáng J Wáng; Jing Qin; Lawrence Wing Chi Chan; Michael Ying; Jing Cai
Journal:  Quant Imaging Med Surg       Date:  2022-07

2.  Pneumonia Transfer Learning Deep Learning Model from Segmented X-rays.

Authors:  Amal H Alharbi; Hanan A Hosni Mahmoud
Journal:  Healthcare (Basel)       Date:  2022-05-26

3.  The application of a deep learning system developed to reduce the time for RT-PCR in COVID-19 detection.

Authors:  Yoonje Lee; Yu-Seop Kim; Da-In Lee; Seri Jeong; Gu-Hyun Kang; Yong Soo Jang; Wonhee Kim; Hyun Young Choi; Jae Guk Kim; Sang-Hoon Choi
Journal:  Sci Rep       Date:  2022-01-24       Impact factor: 4.379

4.  Artificial Intelligence-Based Detection of Pneumonia in Chest Radiographs.

Authors:  Judith Becker; Josua A Decker; Christoph Römmele; Maria Kahn; Helmut Messmann; Markus Wehler; Florian Schwarz; Thomas Kroencke; Christian Scheurig-Muenkler
Journal:  Diagnostics (Basel)       Date:  2022-06-14

5.  Clinically focused multi-cohort benchmarking as a tool for external validation of artificial intelligence algorithm performance in basic chest radiography analysis.

Authors:  Jan Rudolph; Balthasar Schachtner; Nicola Fink; Vanessa Koliogiannis; Vincent Schwarze; Sophia Goller; Lena Trappmann; Boj F Hoppe; Nabeel Mansour; Maximilian Fischer; Najib Ben Khaled; Maximilian Jörgens; Julien Dinkel; Wolfgang G Kunz; Jens Ricke; Michael Ingrisch; Bastian O Sabel; Johannes Rueckel
Journal:  Sci Rep       Date:  2022-07-27       Impact factor: 4.996

Review 6.  Application of Deep Learning Techniques in Diagnosis of Covid-19 (Coronavirus): A Systematic Review.

Authors:  Yogesh H Bhosale; K Sridhar Patnaik
Journal:  Neural Process Lett       Date:  2022-09-16       Impact factor: 2.565

7.  Intubation and mortality prediction in hospitalized COVID-19 patients using a combination of convolutional neural network-based scoring of chest radiographs and clinical data.

Authors:  Aileen O'Shea; Matthew D Li; Nathaniel D Mercaldo; Patricia Balthazar; Avik Som; Tristan Yeung; Marc D Succi; Brent P Little; Jayashree Kalpathy-Cramer; Susanna I Lee
Journal:  BJR Open       Date:  2022-03-24

Review 8.  Study of Different Deep Learning Methods for Coronavirus (COVID-19) Pandemic: Taxonomy, Survey and Insights.

Authors:  Lamia Awassa; Imen Jdey; Habib Dhahri; Ghazala Hcini; Awais Mahmood; Esam Othman; Muhammad Haneef
Journal:  Sensors (Basel)       Date:  2022-02-28       Impact factor: 3.576

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.