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.
This work is novel in the sense that it examines how well orthogonal moments are able to produce good classification of benign and malignant states. The authors have sufficiently improved the manuscript in the light of reviewer's comments and provided adequate rebuttal. The revised version is in a good shape to be published in PeerJ.
NA
NA
Thank you for the rebuttal letter. However, I noticed my comments have not been addressed carefully.
1. If there is no novelty in the paper, it is worthless to publish the paper.
2. To publish the paper and disseminate the scientific claims, we need to evaluate thoroughly, for example, using more evaluation measures, etc.
3. We also need to compare our model with contending methods available in the literature although the dataset is new.
Given such questions unanswered sufficiently by the authors, the reviewer is inclined to clear rejection.
NA
No comment.
No comment.
No comment.
No comment.
No comment other than my previous comments.
No comment other than my previous comments.
No comment other than my previous comments.
The paper needs thorough language improvements. Choice of the data sets should be justified. The authors need to add a detailed comparative analysis of the proposed technique with existing methods.
[# PeerJ Staff Note: Please ensure that all review 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. It is a common mistake to address reviewer questions in the response letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the response letter. Directions on how to prepare a response letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
[# PeerJ Staff Note: The Academic Editor has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at copyediting@peerj.com for pricing (be sure to provide your manuscript number and title) #]
The authors use Krawtchouk moments and Generalized
Pseudo-Zernike moments for the classification of fly wing
images and breast cancer mammograms. Experimental results reveal that the proposed feature extraction method produces prominent accuracy on both domains.
NA
The authors have produced some interesting results. However, I found the following lacking in the paper.
1. The performance has not compared with existing methods.
2. More evaluation methods may be used for the comparison
3. Additional papers related to breast cancer paper can enhance the quality of the paper:
Sitaula, C., Aryal, S. Fusion of whole and part features for the classification of histopathological image of breast tissue. Health Inf Sci Syst 8, 38 (2020). https://doi.org/10.1007/s13755-020-00131-7
The reviewer found lacking novelty in the paper. Specifically, the paper just utilizes well-established features without any novelty. Also, the performance comparison is insufficient. Rather than focussing on multiple datasets, I suggest working on only one with a deeper research understanding. I believe that the paper is unable to meet the expectation of the PeerJ Computer Science journal.
- English should be improved. There still have some unclear or ambiguous parts.
- Literature review should be re-organized to group some similar papers into one paragraph.
- Quality of the figures should be improved.
- The authors indeed had two case studies on fly wing images and breast cancer mammograms. Why did they use the title as 'a case study'? Also, the same in the whole text.
- The two case studies are also big questions. Why did they use these two datasets since they are not relevant to each other?
- DCOM format is at 2D or 3D?
- How did the authors deal with hyperparameter optimization of the models?
- Measurement metrics (i.e., accuracy, sensitivity, specificity, ...) have been used in previous biomedical studies such as PMID: 33816830, PMID: 33735760, and PMID: 33260643. Therefore, the authors are suggested to refer to more works in this description.
- Source codes should be provided for replicating the methods.
- In Figure 4, the text is not displayed clearly.
- Besides training, the authors should have some validation data.
- ROC curves and AUC values should be reported in binary classification.
- The authors should compare the predictive performance to previous studies on the same problem/data.
No comment.
The manuscript is clear and professional language is used.
Literature references and field background is sufficient.
Raw data is shared, results are relevant to the hypotheses.
The study is within the aims and scope of the journal.
Research question is well defined, relevant and meaningful. The research aims to fill the gap of predicting between fly species by their wing patterns and between benign or malignant masses in in mammograms. The study provides a model with a broad application area. The model is described with sufficient detail to replicate.
The limitations are clearly stated in the discussion. All data were provided, statistically sound and controlled. Benefit to the literature is stated, conslusions are linked to the scientific question at hand and limited to results.
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.