PONE-D-24-39869

AI-Assisted identification of sex-specific patterns in diabetic retinopathy using retinal fundus images

PLOS ONE

Dear Dr. Delavari,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we have decided that your manuscript does not meet our criteria for publication and must therefore be rejected.

Specifically:

==============================

• The manuscript is concerned with the application of the VGG16 architecture for analysis of fundus images in the context of gender-specific diabetic retinopathy, coupled with Guided Grad-CAM to support the interpretability of the results, through the analysis of the associated feature maps. The application area of this research is interesting, however, there are a few major concerns.
• Overall, beyond the application area, there is a lack of novelty as both techniques are very well known in the state-of-art.
• VGG16 is relatively shallow, which may limit its ability to capture the complex patterns and subtle features that are critical for detecting early signs of diabetic retinopathy, especially when factoring in gender-specific variations. Moreover, it employs a series of max-pooling layers that downsample the input images progressively. This aggressive downsampling can lead to a loss of fine spatial details that are crucial for detecting small lesions, microaneurysms, or subtle gender-specific retinal features associated with diabetic retinopathy.
• If VGG16 misclassifies a fundus image due to its inherent limitations (e.g., poor handling of small-scale features), Guided Grad-CAM will still produce a heatmap, but the highlighted areas may be misleading, pointing to regions that have no relation to diabetic retinopathy or gender-specific features. This is problematic in medical contexts, where misinterpretation can affect diagnosis and treatment decisions.
• Importantly, the results of Guided Grad-CAM are affected by the choice of the CNN structure. Since Guided Grad-CAM generates visual explanations by analyzing gradients flowing through the network and highlighting important regions based on the activation maps of the convolutional layers, the CNN architecture plays a critical role in shaping the output.
• Instead, additional experiments with a vareity of CNN architectures are needed, or alternatively, to consider approaches such as attention mechanisms, self-supervised learning and integrated gradients.

==============================

I am sorry that we cannot be more positive on this occasion, but hope that you appreciate the reasons for this decision.

Kind regards,

Panos Liatsis, PhD

Academic Editor

PLOS ONE

[Note: HTML markup is below. Please do not edit.]

[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.]

- - - - -

For journal use only: PONEDEC3

PONE-D-24-39869R1AI-Assisted identification of sex-specific patterns in diabetic retinopathy using retinal fundus imagesPLOS ONE

Dear Dr. Delavari,

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.

The manuscript has been evaluated by two reviewers, and their comments are available below.

The reviewers have raised a number of major concerns. They request improvements to the reporting of methodological aspects of the study, clarification on the interpretation of the results and further discussion.

Could you please carefully revise the manuscript to address all comments raised?

We also note that one or more reviewers has recommended that you cite specific previously published works. As always, we recommend that you please review and evaluate the requested works to determine whether they are relevant and should be cited. It is not a requirement to cite these works. We appreciate your attention to this request.

Please submit your revised manuscript by Jan 27 2025 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,

Helen Howard

Staff Editor

PLOS ONE

Journal Requirements:

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 note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

3. Please expand the acronym “NSERC” (as indicated in your financial disclosure) so that it states the name of your funders in full.

This information should be included in your cover letter; we will change the online submission form on your behalf.

4. We note that you have indicated that there are restrictions to data sharing for this study. For studies involving human research participant data or other sensitive data, we encourage authors to share de-identified or anonymized data. However, when data cannot be publicly shared for ethical reasons, we allow authors to make their data sets available upon request. For information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions.

Before we proceed with your manuscript, please address the following prompts:

a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially identifying or sensitive patient information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., a Research Ethics Committee or Institutional Review Board, etc.). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent.

b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. Please see http://www.bmj.com/content/340/bmj.c181.long for guidelines on how to de-identify and prepare clinical data for publication. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. You also have the option of uploading the data as Supporting Information files, but we would recommend depositing data directly to a data repository if possible.

Please update your Data Availability statement in the submission form accordingly.

Additional Editor Comments (if provided):

[Note: HTML markup is below. Please do not edit.]

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: (No Response)

**********

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: Partly

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: No

**********

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: No

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: • The rationale for identifying sex-specific patterns in diabetic retinopathy is not well-justified. The authors should provide a stronger explanation of the clinical relevance and potential impact of their findings.

• It is unclear how this approach contributes to improving diagnosis or treatment strategies compared to traditional methods.

• The dataset used for training and validation is not described in detail. Critical information such as sample size, class balance, preprocessing steps, and demographic distribution is missing.

• Include more recent references that are relevant to the topic, such as

• Al-hazaimeh, Obaida M., Ashraf A. Abu-Ein, Nedal M. Tahat, Ma'moun A. Al-Smadi, and Malek M. Al-Nawashi. "Combining Artificial Intelligence and Image Processing for Diagnosing Diabetic Retinopathy in Retinal Fundus Images." International Journal of Online & Biomedical Engineering 18, no. 13 (2022).

• Gharaibeh, Nasr, Obaida M. Al-Hazaimeh, Bassam Al-Naami, and Khalid MO Nahar. "An effective image processing method for detection of diabetic retinopathy diseases from retinal fundus images." International Journal of Signal and Imaging Systems Engineering 11, no. 4 (2018): 206-216.

Reviewer #2: It is a good study with a reasonably good sample size of retinal images, which is age and gender adjusted.

1. While the conclusions mentions that diabetic macular edema (DME) appears to be more common in women and PDR in men as assessed by the AI system, I do not find any information on DME in the tables supporting the conclusion. Can you kindly provide the same?

2. If the duration of diabetes is available, that information can be added as it is one of the key factors in DR irrespective of the gender

3. Kindly add in the discussion the advantages of knowing the gender based on the use of AI with retinal images.

How does it help in planning screening / management of DR? These points have to be there to support the study in the discussion section

**********

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

**********

[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.

Attachments

Attachment

Submitted filename: PONE-D-24-39869R1.docx

PONE-D-24-39869R2AI-Assisted identification of sex-specific patterns in diabetic retinopathy using retinal fundus imagesPLOS ONE

Dear Dr. Delavari,

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.

Few comments:- The discussion suggests females may be more prone to ME and males to PDR, but the model only identifies regions of attention, not pathology. There are details comments from this from one of the reviewers that need to be addressed for the manuscript to be accepted.- For future research, have you consider validation on an external dataset (e.g., Messidor or IDRiD) to enhance generalizability. This could be ackonwledged in the discussion.- Though the dataset is stratified by ethnicity, the discussion does not explore whether observed sex-specific differences vary across ethnic groups. This is an opportunity for future research but should be acknowledged.

Please submit your revised manuscript by Jun 09 2025 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,

Tomo Popovic, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

[Note: HTML markup is below. Please do not edit.]

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 #2: All comments have been addressed

Reviewer #3: (No Response)

**********

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 #2: Yes

Reviewer #3: Partly

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #2: Yes

Reviewer #3: 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 #2: Yes

Reviewer #3: No

**********

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 #2: Yes

Reviewer #3: 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 #2: the comments have been addressed satisfactorily by the authors. The revised manuscript reads well. showing sex differences in DME AND PDR

Reviewer #3: This manuscript explores the important and timely topic of sex-specific differences in diabetic retinopathy (DR), a complication of diabetes that remains a major cause of vision impairment worldwide. To investigate this, the authors employ an original and creative approach—training convolutional neural networks (CNNs) to classify fundus images as either male or female in patients with DR. The underlying hypothesis is that if DR manifests differently by sex, those differences would be recognized by the CNN as distinguishing features, and subsequently highlighted in saliency (heat) maps.

This manuscript addresses a novel and clinically relevant question using innovative AI-based methodology. The work is technically sound and the results are intriguing.

However, I recommend revisions to ensure consistency in terminology, more cautious interpretation of findings, and a clearer discussion of the study’s limitations. With these adjustments, the paper will make a meaningful contribution to the growing field of AI in ophthalmology and precision medicine.

Comments:

1. Clarification of Sex vs. Gender Terminology: The manuscript would benefit from a more consistent and accurate use of terminology. Sex is a biological classification based on physiological and anatomical characteristics (e.g., chromosomes, hormone profiles, reproductive anatomy), and is indeed relevant to metabolic processes and disease manifestations—as is the focus of this study. In contrast, gender refers to social and cultural roles, personal identity, and lived experience, and is relevant to factors such as access to healthcare, health-seeking behavior, and exposure to stigma or stress—all of which can also impact health outcomes.

However, because the study compares only two groups—male and female—based solely on retinal morphology, and does not include gender identity or sociocultural data, it is more accurate to frame the findings strictly in terms of sex differences. Including both sex and gender as interchangeable terms risks introducing conceptual ambiguity and potentially overextends the claims.

For clarity and scientific precision, I recommend that the manuscript use the term sex consistently throughout and revise or remove references to gender unless supported by appropriate demographic or behavioral data. This will improve the coherence and readability of the text and avoid conflating two distinct dimensions of identity.

2. Scope of Analysis and Grouping Strategy: If the intent were to explore both sex and gender differences, the analysis would require more than two comparison groups (e.g., accounting for intersex, transgender, or non-binary individuals), which would significantly increase complexity and demand an entirely different dataset. Since the current study includes only biologically classified males and females, it is appropriate to keep the analysis focused accordingly. Clarifying this in the introduction and discussion will help anchor the scientific message and prevent misinterpretation.

3. Absence of Healthy Controls: One notable limitation, which should be more explicitly acknowledged, is the lack of healthy control images in the primary analysis. While the authors cite previous work involving healthy eyes, this study exclusively includes DR-affected eyes. Without healthy controls, it is difficult to determine whether the CNN is identifying sex-specific differences in DR pathology or simply general sex-based anatomical differences that persist regardless of disease. Addressing this limitation more directly in the discussion would enhance the manuscript’s rigor.

4. Interpretation of AI Output and Causality: The strongest concern lies in the interpretation of the saliency maps and AI-derived findings. Saliency maps indicate the regions of the image that influenced the model’s classification decision, but they do not reveal which specific features or pathological changes were used in that decision. Thus, while the CNNs successfully distinguish male from female fundus images with moderate accuracy, this does not confirm the presence of sex-specific disease patterns in DR.

For example, the observed focus on the macular region in female eyes does not necessarily indicate an increased risk of macular edema in women. At most, the findings support that the macula in diabetic females has a distinct appearance compared to diabetic males. To establish a causal link between these imaging features and specific clinical outcomes (e.g., macular edema or progression to PDR), longitudinal studies would be required. This paper does not provide such outcome data or analysis and should avoid implying it does.

Therefore, the current claims regarding differential risk (e.g., "females may be at higher risk for macular edema") are speculative and should be clearly presented as hypotheses for future study, not as conclusions drawn from the present data.

5. Recommendation on Framing and Language: The manuscript would benefit from more cautious phrasing when presenting its conclusions. Statements such as "these findings suggest..." should be tempered with language like "these findings raise the hypothesis that..." or "these findings may indicate...". This will align better with the nature of the data and the exploratory design of the study.

**********

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 #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.

AI-Assisted identification of sex-specific patterns in diabetic retinopathy using retinal fundus images

PONE-D-24-39869R3

Dear Dr. Delavari,

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 will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, 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,

Tomo Popovic, Ph.D.

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments: