Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI

Atsushi Hamabe; Masayuki Ishii; Rena Kamoda; Saeko Sasuga; Koichi Okuya; Kenji Okita; Emi Akizuki; Yu Sato; Ryo Miura; Koichi Onodera; Masamitsu Hatakenaka; Ichiro Takemasa

doi:10.1371/journal.pone.0269931

Peer Review History

Original SubmissionAugust 9, 2021
2 Feb 2022 Decision Letter - Kumaradevan Punithakumar, Editor PONE-D-21-25683Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRIPLOS ONE Dear Dr. Takemasa, 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 Mar 19 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, Kumaradevan Punithakumar 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. In your Data Availability statement, you have not specified where the minimal data set underlying the results described in your manuscript can be found. PLOS defines a study's minimal data set as the underlying data used to reach the conclusions drawn in the manuscript and any additional data required to replicate the reported study findings in their entirety. All PLOS journals require that the minimal data set be made fully available. For more information about our data policy, please see http://journals.plos.org/plosone/s/data-availability. Upon re-submitting your revised manuscript, please upload your study’s minimal underlying data set as either Supporting Information files or to a stable, public repository and include the relevant URLs, DOIs, or accession numbers within your revised cover letter. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories. Any potentially identifying patient information must be fully anonymized. Important: If there are ethical or legal restrictions to sharing your data publicly, please explain these restrictions in detail. Please see our guidelines for more information on what we consider unacceptable restrictions to publicly sharing data: http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. Note that it is not acceptable for the authors to be the sole named individuals responsible for ensuring data access. We will update your Data Availability statement to reflect the information you provide in your cover letter. 3. Please clarify the nature of these restrictions, ie. If due to ethical or legal reasons. 4. Please amend your Methods section to include the information provided in your Ethics Statement that informed consent was not required due to the fact that data was anonymized. 5. Thank you for stating the following in the Funding Section of your manuscript: “This study was funded by the FUJIFILM Corporation” 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 study was funded by the FUJIFILM Corporation (https://www.fujifilm.com). The funder had no role in study design, data collection and analysis, or decision to publish, but supported the analysis using deep learning and the preparation of manuscript related to deep learning. No authors received personal support from the funder.” Please include your amended statements within your cover letter; we will change the online submission form on your behalf. 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. 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 ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes 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: The entitled "Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI " is well organized. Literature review and methodology explained by author is appreciable. minor revision is suggested. Author should address following queries: 1.in introduction section(3rd paragraph), some recent papers of this area should be covered which uses U-net in MRI images or other techniques apart from your used technique. 2.In method section, automatic segmentation algorithm part, Author should add more detail about the algorithm and qualitatively analyse the scales of images before and after the application of segmentation algorithm. 3.In line 148, proper citations are missing. Please place the appropriate citations for evaluation coefficients. 4. in figure 5, pearson correlation coefficient and p value should be noted in the figure,and the y-axis is fuzzy. Reviewer #2: This manuscript presents a new high-resolution MRI semi-automatic rectal cancer segmentation technology based on deep learning. I believe this work will contribute to the accuracy of adjuvant therapy. However, I hope the author will revise the manuscript and solve the following problems before publishing it in the journal. 1. Firstly, the description of the research status is not perfect, especially the research status of deep learning in medical image aided diagnosis, including two-dimensional image and three-dimensional image. 2. Secondly, it is necessary to make a detailed description of the hardware configuration and super parameter configuration of network training. 3. Finally, some other networks should be added to the experimental part as a contrast, so as to make the experimental results more convincing. ****** 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. https://doi.org/10.1371/journal.pone.0269931.r001
Revision 1
11 Apr 2022 Author Response Responses to the reviewers’ comments We thank the reviewers for their fair comments and useful suggestions for improving our manuscript. As indicated below, we have considered all comments and suggestions, and we made corrections on a proof in red for the revised parts of the manuscript. Reviewer's Responses to Questions Comments to the Author 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 Response: According to the suggestion, we uploaded the underlying dataset for the findings as supporting information files. Reviewer #1: The entitled "Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI " is well organized. Literature review and methodology explained by author is appreciable. minor revision is suggested. Author should address following queries: 1.In introduction section (3rd paragraph), some recent papers of this area should be covered which uses U-net in MRI images or other techniques apart from your used technique. Response: We thank the reviewer for the constructive comment. We updated the current status regarding the U-net based segmentation techniques for MRI in introduction section (page 7, line 99-105). We additionally cited the following 6 references herein. #18. Ronneberger O, Fischer, P., Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:1505.04597 2015. #19. Milletari F, Navab, N., Ahmadi, S.A. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. arXiv:1606.04797. #20. Dolz J, Xu X, Rony J et al. Multiregion segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks. Med Phys 2018; 45: 5482-5493. #21. Hodneland E, Dybvik JA, Wagner-Larsen KS et al. Automated segmentation of endometrial cancer on MR images using deep learning. Sci Rep 2021; 11: 179. #22. Trebeschi S, van Griethuysen JJM, Lambregts DMJ et al. Author Correction: Deep Learning for Fully-Automated Localization and Segmentation of Rectal Cancer on Multiparametric MR. Sci Rep 2018; 8: 2589. #23. Huang YJ, Dou Q, Wang ZX et al. 3-D RoI-Aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation. IEEE Trans Cybern 2021; 51: 5397-5408. 2. In method section, automatic segmentation algorithm part, Author should add more detail about the algorithm and qualitatively analyse the scales of images before and after the application of segmentation algorithm. Response: According to the indication, we added proposed algorithm features and implementation details (page 14, line 213-218). The salient feature of the algorithm is that we introduced a novel loss which can directly maximize T-staging accuracies in model training, thereby showing better performance than usual segmentation methods which try to optimize the volume overlap with the ground truth label images. We additionally compared the T-stage diagnostic accuracy by comparing the above two algorithm in this revision, and clearly stated the strength of this algorithm in the results section (page 19, line 311-page 20, line 315). 3.In line 148, proper citations are missing. Please place the appropriate citations for evaluation coefficients. Response: We decided that the indicated point was described in line 248. We used Dice similarity coefficients (DSC) to assess the segmentation accuracy, and in this revision, we cited a reference #25 to explain this method (page 17, line 265). #25. Zou KH, Warfield SK, Bharatha A et al. Statistical validation of image segmentation quality based on a spatial overlap index. Acad Radiol 2004; 11: 178-189. 4. In figure 5, pearson correlation coefficient and p value should be noted in the figure,and the y-axis is fuzzy. Response: Thank you very much for your suggestions. Pearson correlation coefficient was 0.2418 and P value was 0.0081, which were added in the figure 5(c). In addition, y-axis “Dice similarity coefficients” was made clearly in this revision. Additional revision We cited a previous report from our institution showing the method for “transverse slicing of a semi-opened rectal specimen” in this revision (page 11, line 157). #24. Ishii M, Takemasa I, Okita K et al. A modified method for resected specimen processing in rectal cancer: Semi-opened with transverse slicing for measuring of the circumferential resection margin. Asian J Endosc Surg 2021. Reviewer #2: This manuscript presents a new high-resolution MRI semi-automatic rectal cancer segmentation technology based on deep learning. I believe this work will contribute to the accuracy of adjuvant therapy. However, I hope the author will revise the manuscript and solve the following problems before publishing it in the journal. 1. Firstly, the description of the research status is not perfect, especially the research status of deep learning in medical image aided diagnosis, including two-dimensional image and three-dimensional image. Response: We thank the reviewer for the constructive comment. We have added the current status regarding the tumor segmentation using 2D and 3D U-net in introduction section (page 7, line 99-105). We additionally cited the following 6 references herein. #18. Ronneberger O, Fischer, P., Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:1505.04597 2015. #19. Milletari F, Navab, N., Ahmadi, S.A. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. arXiv:1606.04797. #20. Dolz J, Xu X, Rony J et al. Multiregion segmentation of bladder cancer structures in MRI with progressive dilated convolutional networks. Med Phys 2018; 45: 5482-5493. #21. Hodneland E, Dybvik JA, Wagner-Larsen KS et al. Automated segmentation of endometrial cancer on MR images using deep learning. Sci Rep 2021; 11: 179. #22. Trebeschi S, van Griethuysen JJM, Lambregts DMJ et al. Author Correction: Deep Learning for Fully-Automated Localization and Segmentation of Rectal Cancer on Multiparametric MR. Sci Rep 2018; 8: 2589. #23. Huang YJ, Dou Q, Wang ZX et al. 3-D RoI-Aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation. IEEE Trans Cybern 2021; 51: 5397-5408. 2. Secondly, it is necessary to make a detailed description of the hardware configuration and super parameter configuration of network training. Response: Thank you very much for your suggestions. The indicated comment is important, and we added the implementation details for network training as follows; The parameter λ in the loss function was experimentally determined to be 0.02. To minimize the loss function, the Adam optimizer with a base learning rate of 0.003, beta1 0.9, beta2 0.999, epsilon 1e-8. Batch-size was 5 samples which consisted of 3 cases with ground-truth segmentation labels and 2 cases with only ground-truth staging. All experiments are conducted on an NVIDIA DGX-2 machine using the NVIDIA V100 GPU with 80GBs of memory. During the training iteration, the performance of the network was evaluated every 100 iterations on the validation dataset. We chose the best network parameter for the validation dataset using the sum of dice score, sensitivity and specificity, then applied it to the evaluation dataset. This information was added in the materials and methods section (page 16, line 241, line 244-247, and page 17, line 259-260.). 3. Finally, some other networks should be added to the experimental part as a contrast, so as to make the experimental results more convincing. Response: According to the indication, we added the comparative analysis between general methods and ours. The salient feature of the algorithm is a novel loss which can directly maximize T-staging accuracies in model training. To reveal the effectiveness of the proposed loss function, we evaluated a baseline model which was trained by using a standard dice loss with the ground truth label images. We additionally compared the T-stage diagnostic accuracy by comparing the above two algorithms in this revision, and clearly stated the strength of this algorithm in the results section (page 14, line 213-218, and page 19, line 311-page 20, line 315). Additional revision We cited a previous report from our institution showing the method for “transverse slicing of a semi-opened rectal specimen” in this revision (page 11, line 157). #24. Ishii M, Takemasa I, Okita K et al. A modified method for resected specimen processing in rectal cancer: Semi-opened with transverse slicing for measuring of the circumferential resection margin. Asian J Endosc Surg 2021. Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0269931.r002
1 Jun 2022 Decision Letter - Kumaradevan Punithakumar, Editor Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI PONE-D-21-25683R1 Dear Dr. Takemasa, 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, Kumaradevan Punithakumar 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 #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 #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? 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 #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 #2: Yes ****** 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 #2: No https://doi.org/10.1371/journal.pone.0269931.r003
Formally Accepted
9 Jun 2022 Acceptance Letter - Kumaradevan Punithakumar, Editor PONE-D-21-25683R1 Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI Dear Dr. Takemasa: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. 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. If we can help with anything else, please email us at plosone@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Professor Kumaradevan Punithakumar Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0269931.r004

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .