PONE-D-22-05608Deep Learning-Assisted Algorithm for Automated Overscan Determination in Low-dose Chest CT: A Nationwide Study on Korean CT Accreditation ProgramPLOS ONE

Dear Dr. Chun,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please pay particular attention to and explain the highly asymmetric confidence intervals in Results.

Please submit your revised manuscript by Aug 04 2022 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Mingwu Jin, Ph.D.

Academic Editor

PLOS ONE

Journal requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf.

2. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match. When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section.

3. Thank you for stating the following financial disclosure:

“This work was supported by the Korea Medical Device Development Fund grant funded by the Korean government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711138600, 1711138601, KMDF_PR_20200901_0267).”

Please state what role the funders took in the study.  If the funders had no role, please state: ""The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.""

If this statement is not correct you must amend it as needed.

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf

4. Thank you for stating the following in the Funding Section of your manuscript:

“This work was supported by the Korea Medical Device Development Fund grant funded by the Korean government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711138600, 1711138601, KMDF_PR_20200901_0267).”

We note that you have provided funding information that is not currently declared in your Funding Statement. However, funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form.

Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows:

“This work was supported by the Korea Medical Device Development Fund grant funded by the Korean government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711138600, 1711138601, KMDF_PR_20200901_0267).”

Please include your amended statements within your cover letter; we will change the online submission form on your behalf.

5. We note that you have stated that you will provide repository information for your data at acceptance. Should your manuscript be accepted for publication, we will hold it until you provide the relevant accession numbers or DOIs necessary to access your data. If you wish to make changes to your Data Availability statement, please describe these changes in your cover letter and we will update your Data Availability statement to reflect the information you provide.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Partly

Reviewer #2: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: No

Reviewer #2: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: No

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: This paper proposed an AI-based target organ segmentation (plus logical operation) method to automatically determine the overscan of LDCT of chest screening. The authors used a relatively small data set (without details on the patient cohort information, age, size, only mentioned sex in the results). My main concern is on the handling of the under scan. As the authors stated in the introduction, under scan actually has more negative dose concerns than the overscan if a new scan has to be repeated. But in the current study, underscdan is also considered as “pass”. I understand that for underscan you might not be able to detect the target organ slices, or only part of them, using the AI. But equal effort should be spent on the under scan if the purpose is to avoid extra dose.

Following the above comment, would suggest the authors report on the dose increases in real values for over scan/under scans they detected. This will put the value of this study into content. How much of dose increases are we detecting?

Another follow up question is that it is not clear to me exactly how the target organ information is used after detection, if there’s space, more figures/graphs showing the exact boundary of the organs in regard to a specific scan range will be very helpful.

A few minor comments:

Line 67-69, redundant statement as Line 55-57. Only need to keep one place.

Line 257-258, it seems from Table 3 that the p values are the numbers determined, not a range, should be something like, p = 0.431, not p<0.431. Please double check.

For all the statistical results with CI, not sure why quite some values are very skewed, i.e. not close to the center of the CI. For example, Table 3, Odds ratio, typically should be symmetric for the estimated value within the CI. And Table 2, sensitivity for external data, with such a large CI, 69% to 99%, the estimated value is still 93%? Can you double check?

S1 Table, for Philips scanner, iDose is the iterative recon strength level, not the recon kernel. Same problem for S2 Table, ASiR-V is the algorithm, not the kernel. On the opposite side, S3 Table 3, all the recon kernels were correctly reported, but under the “reconstruction method” column. Please correct those.

Reviewer #2: Overall review: The novelty of the manuscript is the determination of overscan using axial slices. The U-net-based segmentation is not novel but is suitable for the work. It is made clear by the authors that this automated tool is developed for the purpose of retrospectively monitoring scan range selection in clinical practices, and it cannot be used to set the scan range for the patient before the scan.

Major points:

1. As the ultimate goal is to reduce radiation exposure for the benefit of the patients, I'd like to know the reasons why the authors chose to focus on monitoring the scan range retrospectively instead of predicting the appropriate scan range before the scan.

2. Theoretically, the method of deep learning segmentation and using landmarks to identify scan range can be applied to tomograms as well. If topograms were used, they could potentially be used to prevent overscan. What is the main reason to use axial slices over topograms besides the lack of images?

3. When presenting the segmentation results, please provide example images segmented by the DL algorithm and the radiologist.

4. Please provide the confusion table before you calculate the accuracy, sensitivity, specificity, PPV, and NPV in Table 2, since all those metrics came from the same confusion table. Please provide the contingency table for your Fisher's exact test as well. Similarly, please provide the contingency tables for your univariate OR analysis as an addition to Table 3.

5. It is good to see the univariate analysis in Table 3. But it is also important to know when your automated tool fails, especially when a deep learning algorithm is involved. Therefore, I'd love to see an error analysis. You have acknowledged that segmentation may affect it. If so, please add a couple of image examples along with the dice scores to Discussion. If the segmentation performance is correlated with any of the variables listed in Table 3, please add the dice scores to Table 3 as well.

6. The figure and table captions are not self-explanatory. Please explain what's in the figure/table in the caption with more details.

Minor points:

1. Typo on line 242: The accuracy of internal data ranges from 93.24% while the number is 93.25% in Table 2.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

PONE-D-22-05608R1Development of Deep Learning-Assisted Overscan Decision Algorithm in Low-dose Chest CT: Application to Lung Cancer Screening in Korean National CT Accreditation ProgramPLOS ONE

Dear Dr. Chun,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Oct 24 2022 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Mingwu Jin, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: All comments have been addressed

Reviewer #2: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: No

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: I Don't Know

Reviewer #2: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: I want to thank the authors for their effort on the revised manuscript. Most of my previous comments are addressed.

Just have two more comments related to the added/revised components:

1. Fig. 3, very nice visualization. Just why there are two acceptable locations for the inferior side (C and D)? Need a little more explanation in the text. I saw some descriptions on the supplemental materials about the AI failing in 2D. But still not clear why there are two acceptable positions shown in Fig. 3. Also do you have any over scan images for the inferior side?

2. The overall additional dose from overscan. As I have expected, the mean added effective dose due to overscan is really low. 0.02 mSv should not be any concern when the opposite side is underscan with missed information. I see that the authors tried to defend that the dose is not low in order to justify the value of the study. I kind of disagree with that logic. It is a good news that after this study, we found out that the dose from overscan is really low, not to any concern. The study is still valuable. It is not necessary to overstate the dose issue to justify the study.

Reviewer #2: In this revision, the authors clarified that the purpose of the work is to reduce subjectivity of auditing of overscans (by radiologists) and save time/cost/resources. However,

1) The gold standard used in this study was from only 1 radiologist.

2) If the authors wish to reduce the radiologists' burden to audit overscans, it is probably better to completely eliminate the false negatives (algorithm = None, radiologist = Overscan) so that the radiologists do not need to review every single non-overscan cases to confirm that 1 false negative (according to Table 2, there is 1 with internal data and 1 with external data). Therefore, I suggest the authors do a more in-depth analysis on why the false negatives occurred and maybe also tune your network to prioritize the elimination of false negatives even if it means the false positive cases (algorithm = Overscan, radiologist = None) may increase greatly. Note that this comment is based on my assumption that overscans are rare compared to appropriate scan range and that no overscan case can be missed (therefore the review by radiologist).

3) I assume that the every overscan case decided by the algorithm would be reviewed by radiologists so that no operator would be wrongfully accused. I am not sure how often/rare overscan occurs in routine LDCT lung scans, but the authors can probably provide an estimate on how much time it could save by only having to review the overscans brought up by the algorithm.

I believe the algorithm proposed by the authors is potentially useful. However, I do not think the authors have explained how to realistically help reduce the burden of auditing overscans on radiologists. Just having an algorithm that has good overall accuracy is not enough because radiologists would still need to review all the cases.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

Development of Deep Learning-Assisted Overscan Decision Algorithm in Low-dose Chest CT: Application to Lung Cancer Screening in Korean National CT Accreditation Program

PONE-D-22-05608R2

Dear Dr. Chun,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Mingwu Jin, Ph.D.

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: All comments have been addressed

Reviewer #2: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: I Don't Know

Reviewer #2: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Both my comments are addressed. Thank you.

This is to fill up the required 100 character counts. Sorry.

Reviewer #2: I agree with reviewer #1 that 0.02 mSv excessive effective dose is very little compared to a normal lung screening scan, which is about 1.5 mSv, not to mention the shakiness of the non-threshold linear radiation safety model that ALARA is based on. Underscan is definitely a much bigger concern and a 'safety range' should be allowed for the operators. This DL-based algorithm provided good overall accuracy for overscan determination. In the future, I would love to see an algorithm that can make decisions for at least 3 conditions: underscan, normal range, (maybe a safety range), and severe overscan, not necessarily by DL algorithms alone.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

**********