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.
The authors successfully implemented the reviewers' comments. The manuscript can now be acceptable as it is. I would like to congratulate the authors once again for their work.
[# PeerJ Staff Note - this decision was reviewed and approved by Paula Soares, a PeerJ Section Editor covering this Section #]
The author has resolved all comments from the first round of review. The author has rearranged the section and focused more on recent technologies for cell analysis. The same applies to the DIP and machine learning approaches. More recent development has been discussed. The author has removed the story about Alan Turing and artificial intelligence which is not relevant to the theme of this paper.
Thank you for providing the description of the survey methodology. The method is described in detail. The articles cited in this manuscript have been quoted in other studies as well. The first paragraph was unnecessary but the author has made the change to improve it.
The author has added discussion about future directions to the manuscript.
None, apart from the ones above.
The authors have shorted the history of stem cell analysis - I am satisfied with the length of the article as it stands. As I remarked previously, this article is approachable to readers with varied backgrounds, and I think that is a strong prerequisite for a good review article. I congratulate the authors for producing this manuscript.
- The authors have cut down a lot of extraneous sentences that were not helping with the logical flow of the article.
- They have also added more references to background articles, which is all the more helpful. I am especially happy about the inclusion of Table 1 and Table 2, which very comprehensively describe the present state of the art in stem cell research. I thank the authors for considering this suggestion.
- Between lines 260 and 274, the authors have added reference to more work on cell analysis using ML - I am glad about this,.
No new comments here.
I commend the authors for this article, and I support the article's publication.
After the first round of review, the expert reviewers have suggested some critical minor revisions. I would like the authors to revise their manuscript to these valuable comments.
[# PeerJ Staff Note: Please ensure that all review and editorial comments are addressed in a response letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. #]
The first paragraph in the introduction seems to be mostly unnecessary. This manuscript is about stem cell analysis. Too much introduction on cells, in general, is not needed.
Thank you for providing a detailed review of cell analysis since the 16th century. I suggest focusing on the more recent technology. For example, the content from line 261 would be more of interest to the reader of this journal.
Same for the cell analysis using DIP and machine learning approaches, I recommend focusing on the content from line 357, which discusses more recent development.
The automated cell analysis using deep learning is the most interesting part of this manuscript. I recommend staying focused. For example, from lines 401-404, the story about Alan Turing and artificial intelligence is not relevant to the theme of this paper.
The literature research method used in this manuscript is thorough. The related studies were identified and summarized.
Thank you for providing the description of the survey methodology. The method is described in detail.
- This present manuscript is a broad-stroked review of the field of stem cell analysis using modern machine learning and image processing techniques. As such, it is a well-written article with cross-disciplinary interests.
- While I am aware of reviews on ML techniques for cell analysis, I am unaware of an article quite as comprehensive as the present article. I have, however, suggested several ways in which readability of this article can be improved.
- This article is approachable to readers with varied backgrounds, and I think that is a strong prerequisite for a good review article. I congratulate the authors for producing this manuscript.
- Clear and crisp usage of English throughout the text. I congratulate the authors for producing this manuscript. The section on survey methodology clearly indicates the body of reference papers that the present survey analyses and summarizes – which, by itself, is very thorough.
- The sections on overview and evolution of stem cell research does very good justice to reviewing most relevant work, starting from early 2000s to 2020. However, I recommend that the summary of older work (lines 182-336) be shortened to no more than 2 paragraphs.
- In the section on DIP and ML approaches, the authors again mention work from a long time ago – I would advise removing them (lines 345-356). Also, only a couple of lines are dedicated to ML techniques (and only SVM, at that). I recommend either expanding to review more work on ML (not DL) or coalesce this with the section on deep learning techniques.
- In lines 399-405, I think this can be safely removed without the risk of incompleteness for this review. I also wonder if the performance results of this section can instead be summarized in a table – it is indeed difficult to follow the results across various techniques that have been reviewed. Say, the columns are: [year, technique/algorithm, model parameters, results, reference]. It would be easier for the readers to follow the evolution of cell analysis using ML.
- The present article concludes with challenges in cell analysis approaches. While this section is well-written, I would also like to see some commentary on future directions.
- There has been a lot of work on image processing that has come up over the past year or so. However, the work punctuates references on ML until 2020 – I might suggest reviewing any work that uses more recent ML work; this however is not mandatory.
None, apart from the ones above.
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.