Classification of High-Resolution Chest CT Scan Images Using Adaptive Fourier Neural Operators for COVID-19 Diagnosis

Round 1

Reviewer 1 Report

Abstract should describe population and more precisely: material and methods and results.

Population based on a dataset is acceptable however it requires better description than citation only

The Covid -19 HRCT findings differs at different time periods- therefore used scans should be described from which period the CT scans are obtained

The discussion part is poorly written it partial overlaps with introduction whereas there are no citations – which is scares for typical discussion model. I would suggest to test the AFNO (in a double blinded way) on a different population that it was initially trained and resubmit the manuscript

Figure 1 only pulmonary scans should be left – in such a large dataset I would recommend to show scans performed at the same level (raw 2 and 4)

Author Response

The comments are very helpful to improve our paper. We try our best to address all the comments and made change accordingly to our revised paper. I have attached the responses for those comments here as a word document.

Author Response File: Author Response.pdf

Reviewer 2 Report

The paper has some implications for the development of AI-powered diagnostic tools, particularly in environments where access to high-quality imaging data is scarce and the computational burden is a critical concern. The presented study's findings suggest that AFNO could serve as a powerful model for analyzing HRCT images, potentially leading to improved diagnosis and understanding of COVID-19, a critical step in combating the pandemic. From the current presentation, it has been seen that the AFNO model 248 has proven to be a formidable tool.

The method consists of implementing an existing method. For this reason, its originality is limited. The contribution to the literature should be stated in more detail in Section 2.

Author Response

The comments are very helpful to improve our paper. We try our best to address all the comments and made change accordingly to our revised paper. I have attached the responses for those comments here as a word document.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Dear Authors,

Thank you for your corrections.

I do accept all responses however it is difficult to believe that the Figure one cannot be improved. In case you are not available to add scans from the same level. I would suggest to delete mediastinal scans which seems to be not relevant in terms of interstitial analysis.

Best Wishes

Dear Authors,

Thank you for your corrections.

I do accept all responses however it is difficult to believe that the Figure one cannot be improved. In case you are not available to add scans from the same level. I would suggest to delete mediastinal scans which seems to be not relevant in terms of interstitial analysis.

Best Wishes

 

Author Response

Reviewer 1:

 

Comment :

Thank you for your corrections.

I do accept all responses however it is difficult to believe that the Figure one cannot be improved. In case you are not available to add scans from the same level. I would suggest to delete mediastinal scans which seems to be not relevant in terms of interstitial analysis.

 

Response:

The authors would like to thank the reviewer for the positive response and time to consider this manuscript.

 

The dataset consists of several hundreds of images for each patient from each class. The information of the scans for these large number of images are not provided with clear labels. Thus, it is difficult to find the scans from the same level. As recommended by the reviewer, the mediastinal scans in row 3 of Figure 1 are removed from the revised manuscript.

 

Reviewer 2:

 

Comment :

It has been determined that the authors made major corrections and changes appropriately.

 

Response:

The authors would like to thank the reviewer for the positive response and time to consider this manuscript.

Reviewer 2 Report

It has been determined that the authors made major corrections and changes appropriately.

It has been determined that the authors made major corrections and changes appropriately.

Author Response

Reviewer 1:

 

Comment :

Thank you for your corrections.

I do accept all responses however it is difficult to believe that the Figure one cannot be improved. In case you are not available to add scans from the same level. I would suggest to delete mediastinal scans which seems to be not relevant in terms of interstitial analysis.

 

Response:

The authors would like to thank the reviewer for the positive response and time to consider this manuscript.

 

The dataset consists of several hundreds of images for each patient from each class. The information of the scans for these large number of images are not provided with clear labels. Thus, it is difficult to find the scans from the same level. As recommended by the reviewer, the mediastinal scans in row 3 of Figure 1 are removed from the revised manuscript.

 

Reviewer 2:

 

Comment :

It has been determined that the authors made major corrections and changes appropriately.

 

Response:

The authors would like to thank the reviewer for the positive response and time to consider this manuscript.