A Self-Supervised Detail-Sensitive ViT-Based Model for COVID-19 X-ray Image Diagnosis: SDViT

Round 1

Reviewer 1 Report

A Self-supervised Detail-sensitive ViT-Bsed Model for

COVID-19 X-ray Image Diagnosis: SDViT

----

1. Why is SDViT required instead of several other well-established methods for CXR  image analysis? Please highlight those things in the abstract.

2. The quantitative result summary should be mentioned in the abstract.

3. The literature on CXR image analysis for COVID-19 is very limited. Please mention and explain the current SOTA methods. eg.

https://link.springer.com/article/10.1007/s10489-020-02055-x

 

4. COVID-19 causes mental health complications and related issues according to: 

https://www.hindawi.com/journals/cin/2021/2158184/

so, it is good to explain this paper in the background or introduction.

 

5. The paper does not compare the proposed method with the SOTA methods. Please compare with them.

 

6. Use more data, please. There are large datasets in this domain already. So, implement them and compare each other.

7. The dataset is CXR, but it has mentioned CT in the dataset. Please correct them. 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

The detailed comments on the proposed approach are enlisted in the attached document. Although the authors have written a sound and detailed approach, still, some comments are proposed below to improve the quality of the manuscript. 

Regards

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

It looks the the paper never used CT images (only CXR image have been used) in the experiment, but the author reiterated that they used CT images. Please delete the CT image information from where they have been mentioned and mention the CXR image only in the caption (eg. Figs 11 and 12, it looks like they are CXR images, not CT images) of the image before publication. It shows that [27] in the manuscript is a chest xray image dataset, not CT image dataset. Please correct it.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors improved the quality of the paper by incorporating all the reviews and suggestions. Therefore, the paper is accepted in its current form. However, Figure 1 should be a Table, not a figure. Also, by replication, I mean how to reproduce the proposed result. It should be shared somewhere on GitHub etc. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf