All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Thank you for your thorough and comprehensive revisions. As neither reviewer responded in this round, I carefully evaluated your rebuttal letter and the revised manuscript.
You have addressed all reviewer and editorial comments in full, including clarifying the research gaps and hypothesis, strengthening methodological detail, adding pseudocode and equations, improving figure annotations, refining language, updating references, expanding justification and limitations, and ensuring reproducibility through code and documentation. The revised manuscript is much clearer and technically stronger.
I am satisfied that all required revisions have been completed, and the manuscript is now suitable for publication. Congratulations on the acceptance of your work!
**PeerJ Staff Note:** Please ensure that all review, editorial, and staff comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
- Mostly, the abstract is written or refined with the help of AI. First, combine the abstract into one paragraph. Second, remove the last paragraph starting with "In conclusion, ..." (this is the AI summary in most answers).
- The "Research Gaps" and "Research Hypothesis" should be explicitly defined.
- Remove "Proposed Method" in L.186.
- Equation numbers are missing.
- The Research Method section is very shallow, resembling a narrative non-scientific talk. This section must be rewritten with in-depth details for the system, including pseudocode/flowcharts, and relative equations/formulas in detail, etc.
- One example; in "Vessel segmentation was performed using ....", you are just listing what was done without reasoning or presenting the flow of information. For example, "Isodata thresholding was then applied to generate a binary vessel mask." Why? Why not other methods? Reference? Input/Output data flow? etc.
- After reading the discussion, I feel that many parts of the manuscript are written by AI (not just refined content).
- The extensive usage of em-dashes reflects an AI pattern. Please avoid that.
- Annotate Figures 8, 10, 12, and 14; not just a, b, and c. Add more details to the figures.
- Where are the framework details? Figure 1? I don't find any details.
- Ensure the code is fully available for replication. Also, add README.md file to describe the code.
- Add the overall pseudocode for the suggested approach to improve clarity and reproducibility.
- Include a clear justification for the research to strengthen the rationale behind the study.
- What distinguishes the current study from related research? This should be explicitly stated to emphasize the study's uniqueness.
- Discuss the limitations of the current study to provide a balanced perspective on its scope and applicability.
- Incorporate recent citations from 2023 to 2025 to ensure the manuscript reflects the latest advancements and developments in the field.
- Include a table of abbreviations in the revised manuscript to improve reader comprehension, especially for readers who may not be familiar with all the terms used.
Refer to the "Basic reporting" section.
Refer to the "Basic reporting" section.
Refer to the "Basic reporting" section.
The manuscript is well written and is appropriately professional and technical.
The scientific background on which it is based is solid. The authors have done a good job in providing a comprehensive and up-to-date review of the supporting literature. They have well contextualized the clinical role of retinal vascular tortuosity as a biomarker. The manuscript presents a logical and coherent structure. The figures and tables are relevant and explanatory. However, the captions of some figures (e.g., Figures 7-14) could be further improved to allow easier interpretation for the clinical reader. The only suggestion might be to emphasize graphically the principal differences in arterial and venous tortuosity, where possible of course.
The manuscript represents original research that fits well with the objectives of the journal. The research question is clearly formulated namely that of improving the measurement of retinal vascular tortuosity by introducing a reproducible and vessel-specific method. The authors successfully identify gaps in the current literature and provide a suitable alternative. The use of three different publicly available datasets (DRIVE, HRF, LES-AV) allows strengthening the robustness of the results. In addition, stratification by disease type (glaucoma and diabetic retinopathy) allows for added clinical relevance to the analysis. The methodology is described in detail, which allows for possible replication. However, the authors should more clearly articulate the rationale behind the choice of the Breadth-First Search (BFS) algorithm over alternatives. Overall, however, the experimental design is well conceived.
The results presented in the study are clear and supported by appropriate statistical analysis
The methodological approach ensures a high degree of reproducibility.
The conclusions of the study are logically derived from the data and respond appropriately to the initial research objective. In addition, adequate discussion of the influence of pathologies and imaging parameters is appreciated
However, the authors should encourage future replication of their approach in clinical settings. This aspect would further strengthen the practical impact of their work.
The study is appreciable for its clear exposition and well-organized structure; these aspects make it accessible to a wide audience. Despite the technical complexity of the topic, the authors have succeeded commendably in presenting their methodology in a clear but rigorous manner.
The exclusive use of public datasets is particularly appreciable, as it provides transparency and reproducibility to the study.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.