Deep transfer learning artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs

Jocelyn Zhu; Beiyi Shen; Almas Abbasi; Mahsa Hoshmand-Kochi; Haifang Li; Tim Q. Duong

doi:10.1371/journal.pone.0236621

Peer Review History

Original SubmissionMay 27, 2020
5 Jun 2020 Decision Letter - Dilbag Singh, Editor PONE-D-20-16042 Deep learning artificial intelligence accurately stages COVID-19 disease severity on portable chest radiographs PLOS ONE Dear Dr. Duong, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Jul 20 2020 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols We look forward to receiving your revised manuscript. Kind regards, Dilbag Singh Academic Editor PLOS ONE Additional Editor Comments: I think authors should add more recent literature from the PLOS One journal. Journal requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. We note that you have included the phrase “data not shown” in your manuscript. Unfortunately, this does not meet our data sharing requirements. PLOS does not permit references to inaccessible data. We require that authors provide all relevant data within the paper, Supporting Information files, or in an acceptable, public repository. Please add a citation to support this phrase or upload the data that corresponds with these findings to a stable repository (such as Figshare or Dryad) and provide and URLs, DOIs, or accession numbers that may be used to access these data. Or, if the data are not a core part of the research being presented in your study, we ask that you remove the phrase that refers to these data. 3. We note that you have stated that you will provide repository information for your data at acceptance. Should your manuscript be accepted for publication, we will hold it until you provide the relevant accession numbers or DOIs necessary to access your data. If you wish to make changes to your Data Availability statement, please describe these changes in your cover letter and we will update your Data Availability statement to reflect the information you provide. 4. Thank you for stating the following in your Competing Interests section: 'No' a. Please complete your Competing Interests statement to state any Competing Interests. If you have no competing interests, please state "The authors have declared that no competing interests exist.", as detailed online in our guide for authors at http://journals.plos.org/plosone/s/submit-now b. This information should be included in your cover letter; we will change the online submission form on your behalf. Please know it is PLOS ONE policy for corresponding authors to declare, on behalf of all authors, all potential competing interests for the purposes of transparency. PLOS defines a competing interest as anything that interferes with, or could reasonably be perceived as interfering with, the full and objective presentation, peer review, editorial decision-making, or publication of research or non-research articles submitted to one of the journals. Competing interests can be financial or non-financial, professional, or personal. Competing interests can arise in relationship to an organization or another person. Please follow this link to our website for more details on competing interests: http://journals.plos.org/plosone/s/competing-interests [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes Reviewer #3: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes Reviewer #3: Yes ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes Reviewer #3: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: No Reviewer #3: Yes ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: 1. There are some grammatical and typo mistakes in the entire manuscript such as: “predict continuous values. (Figure 1).” described by Wong et al (7) 2. Use consistent words such as either COVID19 or COVID-19 in entire manuscript. 3. Please write suitable background of Deep-learning convolutional neural network (CNN) and deep transfer learning? 4. Add more mathematical background of CNN. 5. Add suitable diagrammatic flow in the paper. 6. Authors have use CNN or deep transfer learning? If deep transfer learning is used, then title should be improved. 7. Recently, many studies have been used for diagnosis of COVID-19, so, I suggest authors to add a related work about those studies such as: 10.1148/radiol.2020200432,10.1007/s10096-020-03901-z, 10.1142/S0217984919500222, 10.1049/iet-syb.2019.0116, 10.1148/radiol.2020200642, 10.1148/radiol.2020200463, 10.1148/radiol.2020200370 8. Do improve abstract such as kappa is simply used as k. Also, authors should use present sentences rather than was were. 9. Figure 1 should be improved it seems directly copied from some source. Reviewer #2: In this paper deep-learning convolutional neural networks has been implemented for novel COVID-19 . Problem has a great significance. The content is written well and the results are promising. The paper needs some improvement in terms of the following recommendations: 1. Main objective need to be explained in a specific way. 2. Introduction is week, need to include some more similar modeling approaches and related work on other nonlinear modeling approaches should be extended with the following papers: Apostolopoulos, I. D., & Mpesiana, T. A. (2020). Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine, 1. Singh, D., Kumar, V., & Kaur, M. (2020). Classification of COVID-19 patients from chest CT images using multi-objective differential evolution–based convolutional neural networks. European Journal of Clinical Microbiology & Infectious Diseases, 1-11. Rahimzadeh, M., & Attar, A. (2020). A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2. Informatics in Medicine Unlocked, 100360. Hall, L. O., Paul, R., Goldgof, D. B., & Goldgof, G. M. (2020). Finding covid-19 from chest x-rays using deep learning on a small dataset. arXiv preprint arXiv:2004.02060. 3. Methodology need to be written in more detail with respect of each step involved. Statistical methods and performance evaluation is also required more information. 4. Results need to be compared with exiting works. Reviewer #3: This paper is nicely written and idea is novel, but I have following recommendations The choice of the number of layers and neurons per layer given in section III A is not argued. The database is weak to draw a conclusion. Taking into account the uncertainties given in the various analyzes, the results are comparable. In addition, the efficiencies must be revised downwards. Please explain how this manuscript advances this field of research and/or contributes something new to the literature. ****** 6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review?** For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: No Reviewer #3: No [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0236621.r001
Revision 1
10 Jun 2020 Author Response Pls see attachment for easier read. Dear Reviewers, We thank you for your constructive comments. Please find the attached point-by-point response below. We believe we have addressed all comments positively. We have also carefully edited throughout. We have revised/removed statement of “data not shown.” Note that we also added the mean absolute error as another measure. Reviewer #1: 1. There are some grammatical and typo mistakes in the entire manuscript such as: “predict continuous values. (Figure 1).” described by Wong et al (7) Thank you. Corrected. It was incorrectly stated, it should have been Wang et al. 2. Use consistent words such as either COVID19 or COVID-19 in entire manuscript. Thank you. Corrected. 3. Please write suitable background of Deep-learning convolutional neural network (CNN) and deep transfer learning? The following is added. Deep-learning artificial intelligence (AI) has become increasingly popular for analyzing diagnostic images [10, 11]. AI has the potential to facilitate disease diagnosis of disease, diseases severity staging, and longitudinal monitoring of disease progression. One common machine-learning algorithm is the convolutional neural network (CNN) [12, 13], which takes an input image, learns important features in the image such as size or intensity, and saves these parameters as weights and bias to differentiate types of images [14, 15]. CNN architecture is ideally suited for analyzing images. The majority of machine learning algorithms to date are trained to solve specific tasks, working in isolation. Models have to be rebuilt from scratch if the feature-space distribution changes. Transfer learning overcomes the isolated learning paradigm by utilizing knowledge acquired for one task to solve related ones. Transfer learning in AI is particularly important for small sample size data because the pre-trained weights enables more efficient training and better performance [16, 17]. There are many AI algorithms that have already been developed for CXR applications (see review [18]) and these AI algorithms can be repurposed to study COVID-19 lung infection. A few studies have already reported AI applications to classify COVID-19 versus non-COVID-19 lung infection using CXR [19-22] and CT [23-26]. Many of these publications are pre-print, non-peer reviewed publications. These studies aimed to classify (not stage) COVID-19 versus non-COVID-19 images. Classification (i.e., for the purpose of diagnosis) of COVID-19 versus non-COVID-19 made by AI unfortunately has poor specificity. The reverse-transcription polymerase chain reaction test of a nasopharyngeal or oropharyngeal swab is still needed for definitive diagnosis. By contrast, deep-learning AI is well suited to stage disease severity. To our knowledge, there have been no studies to date that use deep-learning AI to stage disease severity on CXR of COVID-19 lung infection. The goal of this study was to employ deep-learning CNN to stage disease severity of COVID-19 infection on CXR (as opposed to classify COVID-19 versus non-COVID-19 lung infection). The ground truths were the disease severity scores determined by expert chest radiologists. Comparison was made with traditional and transfer learning. This approach has the potential to provide frontline physicians an efficient and accurate means to triage patients, assess risk, allocate resources, as well as to monitor disease progression and treatment response. This approach is timely and urgent because of the anticipated widespread shortage of ICU beds and mechanical ventilators. 4. Add more mathematical background of CNN. This paper deals with an innovative CNN application to stage lung disease severity based on portable CXRs of COVID-19 patients. The CNN algorithm and transferring methods are standard. We feel that to add a mathematical background of CNN would be repeating as the literature has already described it in a much more eloquent and precise manner. We only provide a brief qualitative description and cited references instead. 5. Add suitable diagrammatic flow in the paper. A flowchart diagram for analysis is added. 6. Authors have use CNN or deep transfer learning? If deep transfer learning is used, then title should be improved. The new title is: Deep transfer learning methods in artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs 7. Recently, many studies have been used for diagnosis of COVID-19, so, I suggest authors to add a related work about those studies such as: 10.1148/radiol.2020200432, 10.1007/s10096-020-03901-z, 10.1142/S0217984919500222, 10.1049/iet-syb.2019.0116, 10.1148/radiol.2020200642, 10.1148/radiol.2020200463, 10.1148/radiol.2020200370 Thank you for the references. They are cited. Our study employed deep learning to stage disease severity of COVID-19 infection on CXR (as opposed to classify COVID-19 versus non-COVID-19 lung infection that are in the literature). To our knowledge, there have been no studies to date that use deep-learning AI to stage disease severity on CXR of COVID-19 lung infection. 8. Do improve abstract such as kappa is simply used as k. Also, authors should use present sentences rather than was were. Thank you. ��is used more often in the clinical literature so we spelled it out instead. We changed to present tense where appropriate but past tense is used more often in the clinical literature. 9. Figure 1 should be improved it seems directly copied from some source. This figure was created by us. It was not copied. Reviewer #2: In this paper deep-learning convolutional neural networks has been implemented for novel COVID-19. Problem has a great significance. The content is written well and the results are promising. The paper needs some improvement in terms of the following recommendations: 1. Main objective need to be explained in a specific way. Thank you. Pls see the response to Reviewer 1, comment #3 for the extensively revised Introduction. 2. Introduction is week, need to include some more similar modeling approaches and related work on other nonlinear modeling approaches should be extended with the following papers: Apostolopoulos, I. D., & Mpesiana, T. A. (2020). Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine, 1. Singh, D., Kumar, V., & Kaur, M. (2020). Classification of COVID-19 patients from chest CT images using multi-objective differential evolution–based convolutional neural networks. European Journal of Clinical Microbiology & Infectious Diseases, 1-11. Rahimzadeh, M., & Attar, A. (2020). A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2. Informatics in Medicine Unlocked, 100360. Hall, L. O., Paul, R., Goldgof, D. B., & Goldgof, G. M. (2020). Finding covid-19 from chest x-rays using deep learning on a small dataset. arXiv preprint arXiv:2004.02060. Pls see the response to Reviewer 1, comment #3 for the extensively revised Introduction. Thank you for the references. They are cited. 3. Methodology need to be written in more detail with respect of each step involved. Statistical methods and performance evaluation is also required more information. Thank you. We have expanded the Methods in multiple places and included a flowchart. 4. Results need to be compared with exiting works. Thank you. We expanded the discussion of the results generally. There are currently no studies to date that use deep-learning AI to stage disease severity on CXR of COVID-19 lung infection. There are no similar works to compare quantitatively. Reviewer #3: This paper is nicely written and idea is novel, but I have following recommendations The choice of the number of layers and neurons per layer given in section III A is not argued. Thank you. The following is added. CNN: A convolutional neural network (Figure 2A)[12, 13] with an additional regression layer was utilized to predict disease severity scores of CXR on a graded scale. The images were normalized, converted to RGB images, resized to 64x64 pixel images, and separated into 80% training and 20% testing datasets. This model architecture included Convolutional, Activation, Batch Normalization, Max Pooling, Dense layers, and a final Dense regression layer to fit the model to predict continuous values. Specifically, for convolutional neural networks, deep learning models are well-suited to learn complex functions, and optimize performance of regularization methods. Batch normalization layers served to stabilize the learning process by standardizing inputs, and standard rectified linear activation layers for CNNs were used to optimize performance. In general, the number of layers and nodes depends heavily on the input data and prediction goals, therefore heuristics were used to generate a standard CNN model for image analysis, the model was then fine-tuned based on performance on the testing dataset. This resulted in three 3x3 kernel sized convolutional layers. L2 regularization and Dropout layers, using a parametric probability of 0.3 as determined by analyzing performance results, were used to prevent overfitting. An optimal batch size of 8 was determined by five-fold cross validation, and the model was trained for 110 epochs. The loss function was measured by mean squared error as the model predicted continuous values, and the learning rate was set to 0.001, as it proved to perform more positively than the standard 0.01 rate in early training, and the Adam optimizer proved the most successful in minimizing loss. The database is weak to draw a conclusion. We agree that the available CXR data are of small sample size and have limited information. We emphasized these in the Limitations section. We hope that future studies will include larger multi-institutional dataset. Taking into account the uncertainties given in the various analyzes, the results are comparable. In addition, the efficiencies must be revised downwards. Thank you. We toned down efficiency claim. Please explain how this manuscript advances this field of research and/or contributes something new to the literature. Thank you. We have revised the last paragraph of the Introduction and Discussion to reflect your comments. Attachments Attachment Submitted filename: Response.docx https://doi.org/10.1371/journal.pone.0236621.r002
13 Jul 2020 Decision Letter - Dilbag Singh, Editor Deep transfer learning artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs PONE-D-20-16042R1 Dear Dr. Duong, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Dilbag Singh Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: All comments have been addressed Reviewer #2: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: Yes ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: (No Response) Reviewer #2: The recommendations given previously have been addressed successfully. The paper is Accepted as it is. ****** 7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review?** For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: No https://doi.org/10.1371/journal.pone.0236621.r003
Formally Accepted
20 Jul 2020 Acceptance Letter - Dilbag Singh, Editor PONE-D-20-16042R1 Deep transfer learning artificial intelligence accurately stages COVID-19 lung disease severity on portable chest radiographs Dear Dr. Duong: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org. If we can help with anything else, please email us at plosone@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Dilbag Singh Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0236621.r004

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .