A deep learning approach to private data sharing of medical images using conditional generative adversarial networks (GANs)

Hanxi Sun; Jason Plawinski; Sajanth Subramaniam; Amir Jamaludin; Timor Kadir; Aimee Readie; Gregory Ligozio; David Ohlssen; Mark Baillie; Thibaud Coroller

doi:10.1371/journal.pone.0280316

Peer Review History

Original SubmissionFebruary 1, 2022
3 Aug 2022 Decision Letter - Stavros I. Dimitriadis, Editor PONE-D-22-03138A deep learning approach to private data sharing of medical images using conditional generative adversarial networks (GANs)PLOS ONE Dear Dr. Coroller, 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. Dear authors Based on the comments raised from the reviewer and my evaluation, I recommend a major revision of the manuscript. The reviewer raised very important parameters in the evaluation of your method that should be addressed before further recommendation of the manuscript. Please submit your revised manuscript by Sep 15 2022 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: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Stavros I. Dimitriadis Academic Editor PLOS ONE 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. Please provide in your manuscript text information on the location of the A2209 dataset, either as a literature reference or as a URL link to the location of the dataset. 3. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match. When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section. 4. Thank you for stating the following in the Competing Interests: “I have read the journal's policy and HS, AJ, TK declared no competing interests. I have read the journal's policy and TC, MB, JP, SS, GL, AR, DO are employees of Novartis.” We note that one or more of the authors have an affiliation to the commercial funders of this research study : Novartis a. Please provide an amended Funding Statement declaring this commercial affiliation, as well as a statement regarding the Role of Funders in your study. If the funding organization did not play a role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript and only provided financial support in the form of authors' salaries and/or research materials, please review your statements relating to the author contributions, and ensure you have specifically and accurately indicated the role(s) that these authors had in your study. You can update author roles in the Author Contributions section of the online submission form. Please also include the following statement within your amended Funding Statement. “The funder provided support in the form of salaries for authors [insert relevant initials], but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific roles of these authors are articulated in the ‘author contributions’ section.” If your commercial affiliation did play a role in your study, please state and explain this role within your updated Funding Statement. b. Please also provide an updated Competing Interests Statement declaring this commercial affiliation along with any other relevant declarations relating to employment, consultancy, patents, products in development, or marketed products, etc. Within your Competing Interests Statement, please confirm that this commercial affiliation does not alter your adherence to all PLOS ONE policies on sharing data and materials by including the following statement: "This does not alter our adherence to PLOS ONE policies on sharing data and materials.” (as detailed online in our guide for authors http://journals.plos.org/plosone/s/competing-interests). If this adherence statement is not accurate and there are restrictions on sharing of data and/or materials, please state these. Please note that we cannot proceed with consideration of your article until this information has been declared. Please include both an updated Funding Statement and Competing Interests Statement in your cover letter. We will change the online submission form on your behalf. 5. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager. Please see the following video for instructions on linking an ORCID iD to your Editorial Manager account: https://www.youtube.com/watch?v=_xcclfuvtxQ 6. Thank you for stating the following in the Acknowledgments Section of your manuscript: “The authors thank the study investigators for their contributions. The studies were funded by Novartis Pharma AG, Basel, Switzerland, in accordance with Good Publication Practice (GPP3) guidelines (http://www.ismpp.org/gpp3). “ We note that you have provided additional information within the Acknowledgements Section that is not currently declared in your Funding Statement. Please note that funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form. Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows: “The study was sponsored by Novartis Pharma AG. Novartis personnel and academic advisors from Oxford Big Data Institute (BDI) designed the project.” Please include your amended statements within your cover letter; we will change the online submission form on your behalf. 7. Please amend your manuscript to include your abstract after the title page. 8. Please include captions for your Supporting Information files at the end of your manuscript, and update any in-text citations to match accordingly. Please see our Supporting Information guidelines for more information: http://journals.plos.org/plosone/s/supporting-information. Additional Editor Comments (if provided): Dear authors Based on the comments raised from the reviewer and my evaluation, I recommend a major revision of the manuscript. The reviewer raised very important parameters in the evaluation of your method that should be addressed before further recommendation of the manuscript. [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 ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: 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: No ****** 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 ****** 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: Thank you for writing and submitting this manuscript entitled, ““GANs for developing synthetic MRIs.” Sharing sensitive data under strict privacy regulations remains a crucial challenge in advancing medical research and especially deep learning systems that require large amounts of data to learn meaningful representations robustly. Recently, generative adversarial networks (GANs), have demonstrated the capability to generate realistic, high-resolution synthetic image datasets as a potentially viable approach to privacy-preserving data sharing. In this study the authors trained an auxiliary classifier GAN to generate partial images of the spine, called vertebral units (VUs), to generate synthetic dataset and conduct an analysis on its three core properties: image fidelity, sample diversity and dataset privacy. I think the study offers valuable practical models under which insights derived from synthetic images are similar to those that would have been derived from real data. Several limitations/comments: - Lack of large enough dataset preventing investigation of full spine images instead of vertebral units. - Difficulty to use the pGAN on clinical metrics which is clinically important. It is also important to note that despite several tested scenarios the presented study does not provide any mathematical guarantees for the privacy of the synthetic data, and there are likely cases in which privacy would be breached in practice. - Assessment of fidelity is not presented in a reader study, just by one figure. -Why aren't the training and validation datasets from F2305 study and test dataset from A2209 study divided by 23 VUs of each patient? How were the numbers of VUs generated? - How many patients were used for the test datasets? - I guess Fig 2 in the text is fig 5 in the actual images, Fig 3/4/5 in the text are Fig 2/3/4? – please revise. -I guess that cases with spinal hardware have been excluded? ****** 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 ******** [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.0280316.r001
Revision 1
18 Oct 2022 Author Response Responses to editorial comments: When submitting your revision, we need you to address these additional requirements. We thank the editor for the feedback. We have edited the manuscript accordingly. 1. We have made the necessary formatting changes as per the template provided. 2. We have added reference in the manuscript line 122 - Baeten et al. Anti-interleukin-17A monoclonal antibody secukinumab in treatment of ankylosing spondylitis: a randomised, double-blind, placebo-controlled trial. Lancet 2013 3. We have added “Novartis Pharma AG” as the funder in the appropriate section in the submission site 4. We have included the updated funding statement and competing interest statement in the revised cover letter 5. We have linked the corresponding author’s ORCID ID with the manuscript 6. We have removed the funding statement from Acknowledgement and included the funding statement and competing interest statement in the revised cover letter 7. Abstract has been included in the manuscript 8. Captions for Supporting Information has been updated and added at the end of the manuscript. Reviewer's Responses to Questions We thank the reviewer for the constructive feedbacks. We edited the manuscript accordingly to them. 1. Lack of large enough dataset preventing investigation of full spine images instead of vertebral units. We agree with the reviewer. The lack of data for full synthetic MRIs was the main reason why we focused on vertebras units (VUs) instead of whole images. By using VUs, we increased our effective sample size by pooling all time steps and VU locations together. We acknowledge this in the Limitations (line 421). Following-up on the comment, we added further comments on the issue (line 422). We acknowledged the data limitation to generate 21 vertebras units (VUs) at once (i.e., a whole spine) at line 447 in the Discussion. 2. Difficulty to use the pGAN on clinical metrics which is clinically important. We added further detail on these results. To follow good science practices, we shared negative results from this experiment as well as successful one (i.e., VU location). We also added our interpretation of why the clinical conditioning failed as opposed to the location. We edited the manuscript accordingly in the Limitation (line 428) 3. It is also important to note that despite several tested scenarios the presented study does not provide any mathematical guarantees for the privacy of the synthetic data, and there are likely cases in which privacy would be breached in practice. We tested the most common scenario under clear condition. The manuscript does not make a claim for a mathematically guaranteed privacy model, but rather demonstrates how the model was tested under real scenarios (pairwise and distribution attacks). 4. Assessment of fidelity is not presented in a reader study, just by one figure. We agree with the reviewer. The fidelity was indeed assessed by generating synthetic images. We generated many images and presented it internally. While this approach is by no means meant to quantify their fidelity, it gave us a high confidence on their visual quality. We then exhaustively tested our images to train a model from scratch (diversity) to ensure that they are representative and informative. 5. Why aren't the training and validation datasets from F2305 study and test dataset from A2209 study divided by 23 VUs of each patient? How were the numbers of VUs generated? We thank the reviewer for this question. The number of samples is counted as VUs and not as patient because VUs were treated as independent of their spinal location to increase our effective sample size. We edited the manuscript accordingly in the methods and discussion. 6. How many patients were used for the test datasets? The independent test set (A2209) included 27 patients. We edited the manuscript line 122 to reflect this information. We added the reference to the manuscript as well: Baeten et al. Anti-interleukin-17A monoclonal antibody secukinumab in treatment of ankylosing spondylitis: a randomised, double-blind, placebo-controlled trial. Lancet 2013. 7. guess Fig 2 in the text is fig 5 in the actual images, Fig 3/4/5 in the text are Fig 2/3/4? – please revise. We thank the reviewer for this comment and apologize with the mistake done during submission time. We changed the figure numbers and edited the text accordingly. 8. guess that cases with spinal hardware have been excluded? During the collection of the MRI scans, patients with pacemakers, aneurysm clips, artificial heart valves, ear implants, metal fragments or foreign objects in the eyes, skin or body that rendered the patient unable to undergo MRI were excluded from submitting MRI scans, therefore patient scans utilized in this analysis are not likely to include spinal hardware. Attachments Attachment Submitted filename: Response to reviewers.docx https://doi.org/10.1371/journal.pone.0280316.r002
27 Dec 2022 Decision Letter - Sathishkumar V E, Editor A deep learning approach to private data sharing of medical images using conditional generative adversarial networks (GANs) PONE-D-22-03138R1 Dear Dr. Coroller, 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, Sathishkumar V E Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: <quillbot-extension-portal></quillbot-extension-portal> https://doi.org/10.1371/journal.pone.0280316.r003
Formally Accepted
26 Jan 2023 Acceptance Letter - Sathishkumar V E, Editor PONE-D-22-03138R1 A deep learning approach to private data sharing of medical images using conditional generative adversarial networks (GANs) Dear Dr. Coroller: 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. Sathishkumar V E Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0280316.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 .