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.
Following the reviewers' comments and your response, and after full consideration, it is decided to accept.
[# PeerJ Staff Note - this decision was reviewed and approved by Jyotismita Chaki, a PeerJ 'Computer Science' Section Editor covering this Section #]
no comment
no comment
no comment
The author has solved all the problems and I agree to the publication of this paper.
From the response letter, the paper has been well revised, and the current version of the manuscript is acceptable for publication.
no comment
no comment
no comment
Please make revisions to the paper based on the reviewer's comments.
Reviewer 1 has requested that you cite specific references. You may add them if you believe they are especially relevant. However, I do not expect you to include these citations, and if you do not include them, this will not influence my decision.
[# PeerJ Staff Note: It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors are in agreement that they are relevant and useful #]
The author has solved all my problems last time, but there is still a lack of relevant introduction in the introduction.
In the introduction, it is suggested that the authors conduct a comprehensive survey of intelligent algorithms and neural network methods in the literature and analyze existing work, such as(doi.org/10.1016/j.compbiomed.2022.106269, DOI: 10.1093/bib/bbac524. https://doi.org/10.1016/j.isci.2023.106231,)
Reasonable experimental design.
This paper results are valid.
From the response letter, the paper has been well revised, and the current version of the manuscript is acceptable for publication.
no comment
no comment
no comment
Revise according to the comments of reviewers.
[# PeerJ Staff Note: It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors are in agreement that they are relevant and useful #]
[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal 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 rebuttal 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 rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
The main work of this paper is to compare the diagnostic efficiency of single-mode and multi-mode classification of benign and malignant breast mass lesions. The topic selection of this paper is relatively appropriate and the viewpoint is correct, but it lacks original ideas, and the argumentation content is sufficient, but the argumentation depth is lacking. Meanwhile, it is deficient in the following aspects. I hope the author can modify it to improve the overall readability.
1. The data set selected by the author has too few pictures. It is hoped that transfer learning or data enhancement operations can be attempted to enhance the number of data sets, so as to better evaluate the model.
2. It is suggested to highlight the good results in the table to improve the visualization of the paper and help readers to better understand it.
3. Suggest the author to view the journal template, if you want to compare the results of the table and figure are placed in the results section, so that it can be easy for readers to understand.
4. As mentioned in the discussion section, unimodal and multimodal forms establish an attentional mechanism, which can be elaborated on a little more, for example, by describing its functions.
5. It is hoped that comparative experiments can be added to prove why Sobel gradient is added
The authors compare the diagnostic efficiencies of deep learning single-modal and multi-modal for the classification of benign and malignant breast mass lesions. The experimental results show that multi-modal fusion deep learning models with Sobel operator had excellent diagnostic value in the classification of breast masses, with an AUC of 0.887, sensitivity of 79.8%, specificity of 86.1 %, and positive prediction value of 85.6 %. The paper is well-structured and logical. However, I think the innovation point of this paper is not enough, meanwhile, the credibility of the experiment needs to be further confirmed. Next, let me enumerate these problems:
1. For abbreviations, the full name should be given when it first appears, and abbreviations should be used thereafter. For example, MRI is abbreviated in the Introduction Section, but its full name appears later in the Materials and Methods Section.
2. In Section 1.4, the 'where' leading sentence after the formula is in the same paragraph as the formula, so it should not be preceded by a space.
3. The formula alignment in the manuscript is not uniform. In Section 1.4, the first formula is aligned to the left, while the other formulas are displayed in the middle, and it is recommended to unify the alignment method.
4. The variable should use italics. For example, in Section 1.4, the variables ' X ' and ' x ' do not use italics.
5. Part of the image quality is poor, the font is too small, and difficult to identify. For example, Figure 4.
1. There are grammatical and expressive flaws in the manuscript. For example, the word "Figures" is used in the caption of Figure 1, but as a single figure, the word "Figure" should be used, as is the case with Figure 2.
2. Please perform more analysis on Figures 1 and 2.
3. Please give a reasonable explanation as to why you chose a five-fold cross-validation instead of a ten-fold cross-validation.
I suggest the authors to make a comprehensive investigation on the multi-modal methods in the literature in the introduction part and give the analysis to the existing works such as (https://doi.org/10.1016/j.compbiomed.2022.106164，https://doi.org/10.1016/j.compbiomed.2022.106457，https://doi.org/10.1016/j.compbiomed.2020.103823，https://doi.org/10.1016/j.compbiomed.2022.105877，https://doi.org/10.1016/j.compbiomed.2022.106088) to make the whole work more in-depth.
no comment
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.