PONE-D-25-43021Improving micromorphological analysis with CNN-based segmentation of flint/obsidian, bone and charcoalPLOS ONE

Dear Dr. Hernández-Aceituno,

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.

Major Revision, grounded in PLOS ONE’s criteria of methodological soundness, transparency and reproducibility rather than novelty; specific content-level comments follow below.

For acceptance, the authors must provide repository DOIs for a minimal, reproducible dataset and all author-generated code, and restructure the manuscript by separating Results from Discussion and tempering the Conclusions; the remaining language, formatting and minor presentation edits are recommended to improve clarity.

Please submit your revised manuscript by Oct 04 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,

Przemysław Mroczek, Dr. hab.

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. In your manuscript, please provide additional information regarding the specimens used in your study. Ensure that you have reported human remain specimen numbers and complete repository information, including museum name and geographic location.

If permits were required, please ensure that you have provided details for all permits that were obtained, including the full name of the issuing authority, and add the following statement:

'All necessary permits were obtained for the described study, which complied with all relevant regulations.'

If no permits were required, please include the following statement:

'No permits were required for the described study, which complied with all relevant regulations.'

For more information on PLOS One's requirements for paleontology and archeology research, see https://journals.plos.org/plosone/s/submission-guidelines#loc-paleontology-and-archaeology-research.

3. 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.

4. We note that you have indicated that there are restrictions to data sharing for this study. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly. For more 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. 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.

We will update your Data Availability statement on your behalf to reflect the information you provide.

5. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Additional Editor Comments:

Having read the manuscript carefully—and as archaeological micromorphology is close to my area of expertise—I consider that the submission requires both substantive and technical revisions before it can proceed to external review. It is difficult to recruit a specialist reviewer for a paper that visibly needs structural and policy-aligned polishing; therefore, I am listing here only the content-level points that must be addressed first.

Title. Appropriate and broadly aligned with the study’s scope; no change required at this stage.

Abstract. Needs tightening and rebalancing. Please use British spelling (Palaeolithic), expand abbreviations at first mention (e.g., intersection over union (IoU)), and avoid overloading the abstract with architecture names—retain a generic “state-of-the-art CNNs” and, if essential, the single best configuration. The abstract currently foregrounds only the top metric (IoU = 0.96 for flint/obsidian); include representative values for bone and charcoal to avoid selective emphasis. Add minimal dataset context (e.g., number of thin sections, imaging modes) and provide at least one numeric value to substantiate the claim of “high balanced accuracy” for abundance classification. Stylistically, “flint (including obsidian)” reads more clearly than “flint/obsidian”.

Keywords. Streamline for discoverability. Avoid duplicating title phrases (e.g., “CNN-based”, “semantic segmentation”, “archaeological micromorphology”), avoid acronyms, standardise to UK spelling and lower case for common nouns, and remove slash forms. Keep a concise set focused on the paper’s domain/material scope without repeating title terms.

Structure (Results vs Discussion). Please separate Results and Discussion into distinct, substantive sections. The current combined section mainly reports metrics with limited interpretation, which blurs what was found versus what those findings mean. Results should be strictly descriptive (dataset composition, training/evaluation set-up, per-class/per-image performance, ablations, error rates). A standalone Discussion should interpret performance differences between classes, typical failure modes and their causes, the influence of annotation quality and class imbalance, risks of data leakage, and the extent of generalisability; situate outcomes within the literature, state limitations and potential biases, and outline practical implications for archaeological micromorphology and directions for future work.

Conclusion. Serviceable as a brief recap but currently too general and overly optimistic relative to the dataset’s constraints. The headline claim that the approach “reduces subjectivity and increases reproducibility” is not demonstrated: code and data are not yet public and validation is narrow. The Conclusion should explicitly state limitations and the bounds of generalisability (single-lab, 57 thin sections, strong PPL bias, pronounced class imbalance), and qualify any extension to “other microremains”. Assertions about reproducibility should be conditional on releasing the minimal dataset and code, with transparent train/validation/test splits and fixed random seeds. Please articulate the practical “so what?” (how segmentations and abundance classes map onto Stoops’ standards and support laboratory/field decisions) and acknowledge key methodological risks (merging flint with obsidian due to small sample size; potential split leakage; absence of uncertainty estimates across runs). The tone should be tempered to reflect disparate class performance—excellent for flint/obsidian, clearly lower for bone and charcoal—so that conclusions align with the evidence presented.

Selected technical/clarity items (for the next revision).

– Several tables use comma decimal separators (e.g., “0,60”) rather than the journal’s conventional full stop (e.g., “0.60”), and one caption truncation is visible (“Freqe”). Please standardise decimals and fix caption typos.

– Ensure consistent British spelling throughout (e.g., behaviour, organisation, optimisation). There are a few typographical slips (e.g., “structed” → “structured”).

– You note use of LabelMe and acknowledge volunteers/interns for tagging. Please add brief details on who annotated, any training, and quality control (e.g., spot checks, inter-annotator agreement), as these directly affect dataset validity.

– The dataset comprises scans of 57 thin sections curated at AMBILAB (University of La Laguna). Clarify ownership of the images and permissions to redistribute them. If the institution owns the images, please secure permission for public sharing; if not, detail the rights holder and the access mechanism.

Please revise the manuscript in line with the substantive points above. When resubmitting, include (i) a point-by-point response to every item, (ii) a clean manuscript and a marked version showing changes, and (iii) repository DOIs for the minimal dataset and author-generated code together with an updated, reader-facing Data Availability Statement. I will reassess the submission for external peer review under a decision of Major Revision once these materials are provided.

[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.]

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.

PONE-D-25-43021R1Improving micromorphological analysis with CNN-based segmentation of flint/obsidian, bone and charcoalPLOS ONE

Dear Dr. Hernández-Aceituno,

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 single external review obtained for this revision was clearly positive and raised only minor points requiring clarification. My own re-evaluation confirms that the manuscript is technically sound, adheres to PLOS ONE’s data and methodological transparency requirements, and has been substantially improved in response to both the reviewer’s comments and the initial editorial screening. The remaining issues concern only brief clarifications regarding material classification and sample provenance, which are required for acceptance.

Please submit your revised manuscript by Jan 02 2026 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,

Przemysław Mroczek, Dr. hab.

Academic Editor

PLOS ONE

Journal Requirements:

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

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.

Additional Editor Comments:

Dear Authors,

Thank you very much for submitting the revised version of your manuscript and for your careful and constructive responses to the comments raised during the evaluation process. One external review was obtained for this revision, and the reviewer was clearly positive regarding the scientific soundness, methodological transparency, data availability and clarity of presentation. The reviewer recommended only minor revisions and highlighted that the manuscript is well structured, innovative in its application of CNN-based segmentation to micromorphological materials, and valuable for improving reproducibility in archaeological micromorphology. I appreciate the considerable effort you have made to address both the reviewer’s suggestions and the earlier editorial requirements.

I have re-evaluated the revised manuscript in full, including the supplementary materials and the publicly accessible code and dataset repositories, and I also conducted an internal check of consistency, terminology and compliance with PLOS ONE policy. The manuscript has improved substantially, and in its present form it is close to being suitable for acceptance. Before proceeding, however, I kindly request that you address two minor issues in a final revision. First, although you explain why flint and obsidian were merged into a single class, it would be helpful to state explicitly whether the model performs equally well on both materials and whether this merging was driven exclusively by sample size or also by their practical indistinguishability in PPL/XPL imagery. This brief clarification, which the reviewer also noted, will be useful for future users of the dataset. Second, the manuscript currently describes the thin sections as originating from “different contexts, regions and time periods”. For transparency and archaeological replicability, please provide one additional clarifying sentence indicating at least the broad geographic areas or approximate chronological ranges represented in the dataset. This does not require detailed provenance information, merely a minimal contextual indication.

I look forward to receiving your revised version.

With best regards,

Przemysław Mroczek

Academic Editor

[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: (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

**********

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

Reviewer #1: 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

**********

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

**********

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 manuscript “Improving micromorphological analysis with CNN-based segmentation of flint/obsidian, bone and charcoal” presents an innovative application of CNNs to archaeological micromorphology. Overall, the study demonstrates the potential of deep learning for improving reproducibility and consistency in archaeological micromorphology, while also acknowledging dataset limitations, class imbalance, and annotation challenges. The work is clearly structured, the dataset and methods are transparent, and the results are promising. I appreciate the effort to make code and data openly available. However, there are aspects that would benefit from clarification and reorganisation, mainly concerning consistency in terminology, the structure of the introduction and results, and the archaeological contextualisation.

Major comments

Abstract

The phrase “(…) flint (including obsidian)” suggests that obsidian is a subtype of flint. Please rephrase to clarify that they were clustered together for methodological reasons, not because of material taxonomy. Correct it throughout.

Moreover, are flint and obsidian truly indistinguishable in this approach? Is the model equally reliable with both, or could there be differences? Since not all Palaeolithic contexts contain obsidian, and many use other types of chert, this limitation should be acknowledged.

Introduction

Lines 14-17: add references.

Lines 22-23: explain the statement and cite if not your own reasoning.

Lines 24-25: this does not need a new paragraph.

Lines 35-51: this is the core of the introduction, but it is currently diffuse. Please rewrite to highlight clearly the aim, how, and significance of the study.

Lines 44-48: add references.

Lines 52-58: the tone is too didactic; I suggest trimming or rephrasing. The last paragraph of the introduction should state succinctly: what you propose, why it matters, and what novelty it brings to the field.

Related work

As written, this section feels isolated. Consider integrating the discussion of ML applications into Introduction, Methods, or Discussion instead of leaving it standalone.

Lines 66-74 (Big Data vs Slow Data): this paragraph is disconnected. If you keep it, please explain why this distinction matters. Line 71 needs a reference.

Materials and methods

In Fig. 1 use the same terminology (Flint/Obsidian) as in the text.

Table 2: unify the number format and apply a consistent rounding rule across rows.

Line 183: no need to re-explain the acronym after the first mention; please correct throughout.

Please provide more detail about the origin of contexts and the experimental samples: where do they come from, and how were they created?

Results

Table 6: write Flint/obsidian or explain the abbreviation.

This section contains methodological notes and interpretive comments that should be moved to Methods and/or Discussion. The Results section should be reserved for data only.

Lines 273-275: this partly duplicates the caption of Fig. 5. Please integrate or remove repetition.

Discussion

Lines 339-341: the phrasing is too promotional; please reword to avoid sensational tone.

The archaeological impact would benefit from more concrete examples: how exactly would this tool improve interpretation of hearth features, stratigraphic complexity, or activity areas?

The limitations section should note that charcoal, in particular, requires more samples and more morphological variability to improve training.

Other comments

In figure titles, you can avoid phrasing such as “Results of …”.

Avoid one-sentence paragraphs throughout the text; merge with adjacent ones for smoother reading.

A workflow figure (dataset → annotation → model training → results) would improve accessibility.

Standardise terminology: Flint/Obsidian throughout.

Ensure all abbreviations are expanded at first use (IoU, PPL, XPL) and no need to expand them in the following occurrences (e.g., line 183).

Improve figure/table captions so they are more self-explanatory.

**********

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

**********

[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.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

Improving micromorphological analysis with CNN-based segmentation of flint/obsidian, bone and charcoal

PONE-D-25-43021R2

Dear Dr. Hernández-Aceituno,

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. For questions related to billing, please contact billing support.

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,

Przemysław Mroczek, Dr. hab.

Academic Editor

PLOS One

Additional Editor Comments (optional):

Dear Dr. Hernández-Aceituno,

thank you for submitting the revised version of your manuscript, “Improving micromorphological analysis with CNN-based segmentation of flint/obsidian, bone and charcoal” (PONE-D-25-43021R2), to PLOS ONE.

I have now completed my editorial assessment of the revised manuscript and the authors’ responses to the previous comments. I am pleased to inform you that your manuscript is accepted for publication in PLOS ONE.

The revised version adequately and clearly addresses all substantive points raised during the review process. In particular, the manuscript now demonstrates improved focus and structure, a more balanced and appropriate tone in the Discussion, clearer articulation of methodological choices and limitations, and full compliance with PLOS ONE’s policies on data availability, transparency, and reporting. The study meets the journal’s criteria for methodological soundness and reproducibility, and it represents a valuable contribution to the development of quantitative and computational approaches in archaeological micromorphology.

Before the manuscript proceeds to production, please note the following minor editorial observations, which are offered for your information only and do not require a revised submission or formal response:

-The Conclusion section contains some thematic overlap between consecutive paragraphs; light streamlining during copyediting may further improve clarity.

-Where applicable, copyediting may slightly harmonise phrasing related to model limitations and generalisability, without altering the substance of your conclusions.

These points will be handled, as appropriate, during the production and copyediting stages.

I thank you for submitting your work to the journal and for your careful and constructive engagement throughout the review process. I look forward to seeing your article published.

Kind regards,

Przemysław Mroczek, Dr hab.

Academic Editor

Reviewers' comments: