How much off-the-shelf knowledge is transferable from natural images to pathology images?

Xingyu Li; Konstantinos N. Plataniotis

doi:10.1371/journal.pone.0240530

Peer Review History

Original SubmissionJune 3, 2020
18 Aug 2020 Decision Letter - Tao Song, Editor PONE-D-20-16898 How Much Off-The-Shelf Knowledge Is Transferable From Natural Images To Pathology Images? PLOS ONE Dear Dr. Li, 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 Oct 02 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, Tao Song 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 revise the typographical error on page 2, line 22: the text should read "data-hungry" not "hungary". [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: Partly ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: 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 ****** 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: 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: The questions raised in the introduction are properly answered in the conclusion. The results are efficient and promising. However, I don't think the images (c)-(d) in Figure 1 makes sense. Image (a) corresponds to a normal tissue and image (b) contains abnormal breast cancer tissue, while (c) and (d) contain two separate species. In my opinion, natural images of two separate species should be used for comparison, rather than images of the same specie. Reviewer #2: In the paper, authors focus on transferability of knowledge in deep learning. They define a framework to measure information gain and the experiment results are good. However, there are some details should be noticed. Since you mentioned there are two studies before, did you compare the results with them? You should improve the quality of the figures in the paper. Some of them are dim. Take care of the use of punctuation from line 75 to 78. ****** 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 [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.0240530.r001
Revision 1
25 Aug 2020 Author Response We would like to thank the AE and reviewers for the time taken to both read the document and make criticism on it. Their inputs are well received and taken into consideration in preparing our revision, which has resulted in a manuscript that is clearer and much improved. In addition, we would like to thank the Academic Editor for the time taken to organize this review process. This document provides a point-by-point feedback to the concerns raised by AE and reviewers and indicates how these comments haven been incorporated in the revised manuscript. The reviewers’ comments are started with the letter Q. Answers to the reviewers’ questions are started with the letter R. Correspondingly, in the revised marked-up manuscript, all alterations made due to the reviewers’ considerations are highlighted by yellow lettering to ease further reviewing. All references and citations included below corresponds to the revised manuscript. --------------------------------------------------------------------------------------------------------------------- AE: When submitting your revision, we need you to address these additional requirements. Q1: 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 R1: Point well taken. In light of AE’s comment, the title page and main body of the manuscript are reformatted accordingly. Q2: Please revise the typographical error on page 2, line 22: the text should read "data-hungry" not "hungary". R2: Point well taken. We would like to thank the AE for pointing out this typo. --------------------------------------------------------------------------------------------------------------------- Review 1: The questions raised in the introduction are properly answered in the conclusion. The results are efficient and promising. Q1: However, I don't think the images (c)-(d) in Figure 1 makes sense. Image (a) corresponds to a normal tissue and image (b) contains abnormal breast cancer tissue, while (c) and (d) contain two separate species. In my opinion, natural images of two separate species should be used for comparison, rather than images of the same species. R1: We would like to thank the review for this comment. We agree with the reviewer that using images of separate species for demonstration is better. In Fig 1, we use a cat image (c) and a dog image (d) as examples of natural images. In my opinion, these images do contain objects from separate species. --------------------------------------------------------------------------------------------------------------------- Review 2: In the paper, authors focus on transferability of knowledge in deep learning. They define a framework to measure information gain and the experiment results are good. However, there are some details should be noticed. Q1: Since you mentioned there are two studies before, did you compare the results with them? R1: We would like to thank the review for this comment. Though there are two prior works on evaluating transfer learning performance on medical images, neither of them discusses the transferability of off-the-shelf representations by layers. Because the focuses of prior works and our study are completely different, it is non-trivial to setup an experimental benchmark for result comparison. Specifically, as stated in the original manuscript, - the study in [26] compares fine-tuning a pre-trained net and training a CNN from scratch in medical image analysis. Their experimentation does not include any pathology image sets. - Recent study in [29] investigates different strategies to combine off-the-shelf features in pathology image centered transfer learning. Since this study focuses on comparison of different pre-trained models (i.e. VGG16, ResNet, DenseNet, et al.), it is non-trivial to infer the descriptive power of off-the-shelf representations by layers directly from its results. - Our work proposes a quantitative framework to investigate the transferability of off-the-shelf representations by layers within a pre-trained model. In sum, the different themes of the three studies make it difficult to directly compare the results under one experimental setting. Q2: You should improve the quality of the figures in the paper. R2: Point well taken. In the revision, we have improved the quality of figures (e.g. Fig 2 and Fig 5). Thank you. Q3: Take care of the use of punctuation from line 75 to 78. R3: Point well taken. The structures of the manuscript from line 75-78 has been revised and is reproduced below for ease of review: “The rest of this paper is organized as follows. The proposed method to measure knowledge gain of a particular layer in transfer learning is presented in the Methodology Section. Experimental results and discussions are presented in the Experimentation Section, followed by conclusions.” Attachments Attachment Submitted filename: Response to Reviewers .pdf https://doi.org/10.1371/journal.pone.0240530.r002
29 Sep 2020 Decision Letter - Tao Song, Editor How Much Off-The-Shelf Knowledge Is Transferable From Natural Images To Pathology Images? PONE-D-20-16898R1 Dear Dr. Li, 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, Tao Song Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: https://doi.org/10.1371/journal.pone.0240530.r003
Formally Accepted
5 Oct 2020 Acceptance Letter - Tao Song, Editor PONE-D-20-16898R1 How much off-the-shelf knowledge is transferable from natural images to pathology images? Dear Dr. Li: 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. Tao Song Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0240530.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 .