Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle

Martin Magnéli; Petter Ling; Jacob Gislén; Johan Fagrell; Yilmaz Demir; Erica Domeij Arverud; Kristofer Hallberg; Björn Salomonsson; Max Gordon

doi:10.1371/journal.pone.0289808

Peer Review History

Original SubmissionApril 1, 2023
12 May 2023 Decision Letter - Hans-Peter Simmen, Editor PONE-D-23-08539Deep learning classification of shoulder fractures and dislocations on plain radiographs of the humerus, scapula and claviclePLOS ONE Dear Dr. Magneli, 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. Both reviewers pointed out a great potential of this interesting study. However, a minor revision was recommended. Please, follow their instructions to improve the manuscript. Please submit your revised manuscript by Jun 26 2023 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, Hans-Peter Simmen, M.D., Professor of Surgery 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. We note that Figures 1 and 2 in your submission contain copyrighted images. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright. We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission: a. You may seek permission from the original copyright holder of Figures 1 and 2 to publish the content specifically under the CC BY 4.0 license. We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text: “I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.” Please upload the completed Content Permission Form or other proof of granted permissions as an "Other" file with your submission. In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].” b. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only. 4. 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: I Don't Know ****** 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: Yes 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: 1) General comment The authors show in their study “Deep learning classification of shoulder and dislocations on plain radiographs of the humerus, scapula and clavicle” that their deep learning model based on a convolutional neural network (CNN) perfom promising results in fracture-classification and degenerative conditions. I guess the artificial intelligence (AI) is coming a key player in prevention, diagnosis, treatment, patient monitoring and data management in medicine. Therefore machine learning/neuronal networks and deep neuronal networks are very important methodical approaches in the future. The applied CNN is one type of deep neuronal networks which based on different hidden layers with billions of nodes and is a further development of neuronal networks. In this way CNN are used in recognizing of images. All in all, it is an interesting study about fracture classification based on artificial intelligence using a CNN. An overall area under the curve (AUC) has a good performance for fracture classification related to proximal and diaphyseal humerus fractures. Additionally the authors show good to excellent AUC for clavicule, and scapula fractures. Overall this study is a good example as the algorhythms of deep neuronal networks can work with unstructured data without processing to structured data. The algorhythms are extracting itself the essential characteristics to differentiate the data. Finally, this CNN model recognize patterns and interpret the variations. The demonstrated application of AI in fracture classification is a very interesting example in medicine. And the possible applications will probably expand to other medical fields. 2) Specific suggestions Abstract Line 32: ……………………results for both fractures adn degenerative conditions The study conducted by the authors focuses on applying CNN to fracture-classification and not to degenerative bone changes. So I would omit the remarks about degenerative conditions of bone. Introduction Line 59:……………………anterior dislocation of the shoulder is a common ….. The topic of shoulder dislocation injuries does not fit into the topic of fraucture classifications genereated using deep neuronal networks (DNN). In addition, the current classification of shoulder dislocation injuries often does not contribute to the indication for surgery and they are discussed controversially. Material and Methods Line 129:………………………dislocations of the acromioclavicular joint were classified The classification of dislocation injuries of acromioclavicular joints is missing from Table 1. But I would omit it altogether anyway as this entity does not contribute anything significant to the main topic. Results Line 225/226…………………………The training data included 432 dislocations……. The entity of acromioclavicular joint injuries particularly Type III injuries (Rockwood) , is not sufficiently present in the test group for an adequate assessment of CNN For the reasons already mentioned above and clarity, I would omit this Discussion Line 270/271………………..AI might give birth to new ways of classifiyng fractures, ideally moving from a system where the classification describes the look of the fracture to a system based…… This sentence is misleading. A diagnostic tool should generate a diagnosis that can be used a decision-making aid in order to make a possible indication for surgery. This means that you don`t need AI to record how the fracture behaves under a specific type of treatment. Reviewer #2: The authors present a study on the learning ability of artificial intelligence to assess radiographs of the proximal humerus. The learned network showed excellent accuracy in the classification of fractures according to AO/OTA. The study reads smoothly, is written in standard English, and has potential great value in the future of medicine. AI and neuronal networks are not my area of specialization, comments regarding the method section from this reviewer are therefore not free of doubt. Nevertheless, the statistics used are common in clinical practice to provide valuable information about the value of an investigation. Comments: Line 59: The upbringing of shoulder dislocations comes quite surprisingly at this point. Until here it was not clear, that dislocations should be evaluated as well. Therefore, it is recommended to elaborate this paragraph further. Line 270 ff: This sentence is not supported by the data provided. The study is all about the in orthopedic surgery very standard AO/OTA classification, which by the way is used, at least from my side, even in everyday practice. New ways of classification of fractures is something completely different compared to training AI with an already existing fracture classification system. And how should such a new system change existing treatment. This brings the discussion to a level, were the data can not support the authors in their arguing. Nevertheless I would love to be proven wrong. But in this case much further elaboration on this is needed. ****** 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: Yes: Samuel Haupt ******** [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.0289808.r001
Revision 1
3 Jul 2023 Author Response Dear Professor Simmen, I appreciate the opportunity to revise our manuscript entitled "Deep learning classification of shoulder fractures and dislocations on plain radiographs of the humerus, scapula and clavicle" for potential publication in PLOS ONE. My team and I are grateful for the reviewers' constructive feedback, and we believe that their comments have significantly improved our paper. We have revised the manuscript addressing each point raised by the reviewers and have provided a detailed response to the comments below. Reviewer 1 Comments 1) General comment The authors show in their study “Deep learning classification of shoulder and dislocations on plain radiographs of the humerus, scapula and clavicle” that their deep learning model based on a convolutional neural network (CNN) perfom promising results in fracture-classification and degenerative conditions. I guess the artificial intelligence (AI) is coming a key player in prevention, diagnosis, treatment, patient monitoring and data management in medicine. Therefore machine learning/neuronal networks and deep neuronal networks are very important methodical approaches in the future. The applied CNN is one type of deep neuronal networks which based on different hidden layers with billions of nodes and is a further development of neuronal networks. In this way CNN are used in recognizing of images. All in all, it is an interesting study about fracture classification based on artificial intelligence using a CNN. An overall area under the curve (AUC) has a good performance for fracture classification related to proximal and diaphyseal humerus fractures. Additionally the authors show good to excellent AUC for clavicule, and scapula fractures. Overall this study is a good example as the algorhythms of deep neuronal networks can work with unstructured data without processing to structured data. The algorhythms are extracting itself the essential characteristics to differentiate the data. Finally, this CNN model recognize patterns and interpret the variations. The demonstrated application of AI in fracture classification is a very interesting example in medicine. And the possible applications will probably expand to other medical fields. Response: Thank you for your thoughtful and thorough review of our study. We appreciate your recognition of the potential of AI and our work in the field of fracture classification using CNNs. We are encouraged by your positive feedback and will continue to explore the potential applications of AI in medical fields. 1) "The study conducted by the authors focuses on applying CNN to fracture-classification and not to degenerative bone changes. So I would omit the remarks about degenerative conditions of bone." Response: We appreciate your suggestion and agree that this might confuse the reader. To better represent our study focus, removed references to other labelled findings such as degenerative conditions. The removed sections were found on lines: 33, 97-98 in the first submission. We have removed reference number 13 on shoulder dislocations and updated the reference list, so it excludes this reference. 2) "The topic of shoulder dislocation injuries does not fit into the topic of fracture classifications generated using deep neuronal networks (DNN)." Response: We understand your concern. We aimed to demonstrate the versatility of our model, including its application to dislocation injuries. However, to maintain focus on fracture classification, we have removed all sections on anterior shoulder dislocations, and removed dislocations from the title. The removed sections were found on lines: 59-60, 70, 128-130, 225-228, and removed reference number 13 from the first submitted manuscript. 3) "The classification of dislocation injuries of acromioclavicular joints is missing from Table 1. But I would omit it altogether anyway as this entity does not contribute anything significant to the main topic." Response: We apologize for the oversight. However, following your valuable suggestion, we have now omitted dislocation injuries from our study to maintain focus on fracture classifications. 4) "This sentence is misleading. A diagnostic tool should generate a diagnosis that can be used a decision-making aid in order to make a possible indication for surgery." Response: We agree with your comment. We did not mean to suggest that AI would replace clinical decision-making. Rather, we wanted to highlight that AI could assist in classifying fractures more objectively, potentially leading to more uniform treatment strategies. We have revised the sentence to avoid any confusion. The revised text is found on line xxx Reviewer 2 Comments 1) "The upbringing of shoulder dislocations comes quite surprisingly at this point." Response: We agree with your feedback and have now revised the introduction to provide a clearer picture of our study focus on fracture classifications, and removed all sections on dislocations (please see response to reviewer 1). 2) "This sentence is not supported by the data provided." Response: We appreciate your critique and agrees with you that statement was not supported by the data. We have now revised the discussion to more accurately reflect the findings of our study. The revised text is found on lines 277-280. Journal Requirements 1) We have ensured that our manuscript now follows PLOS ONE's style requirements. 2) We have updated the Data Availability statement to specify where the minimal dataset can be found. We will also include URLs or DOIs for the data in the cover letter. 3) We have obtained written permission from the copyright holder to publish Figures 1 and 2 under the CC BY 4.0 license. This documentation will be uploaded as an "Other" file with our submission. 4) We have reviewed our reference list and confirmed that it is complete and correct. We sincerely thank you for considering our manuscript for publication in PLOS ONE. We believe the revised manuscript has addressed the concerns raised and hope that it is now acceptable for publication. Best Regards, Martin Magnéli, MD, PhD Attachments Attachment Submitted filename: Response to reviewers.docx https://doi.org/10.1371/journal.pone.0289808.r002
27 Jul 2023 Decision Letter - Hans-Peter Simmen, Editor Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle PONE-D-23-08539R1 Dear Dr. Magneli, 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, Hans-Peter Simmen, M.D., Professor of Surgery Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: https://doi.org/10.1371/journal.pone.0289808.r003
Formally Accepted
22 Aug 2023 Acceptance Letter - Hans-Peter Simmen, Editor PONE-D-23-08539R1 Deep learning classification of shoulder fractures on plain radiographs of the humerus, scapula and clavicle Dear Dr. Magneli: 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 Dr. Hans-Peter Simmen Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0289808.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 .