Evaluating Explainable Artificial Intelligence (XAI) techniques in chest radiology imaging through a human-centered Lens

Izegbua E. Ihongbe; Shereen Fouad; Taha F. Mahmoud; Arvind Rajasekaran; Bahadar Bhatia

doi:10.1371/journal.pone.0308758

Peer Review History

Original SubmissionJanuary 30, 2024
4 Jun 2024 Decision Letter - Cosimo Ieracitano, Editor PONE-D-24-03792Evaluating Explainable Artificial Intelligence (XAI) Techniques in Chest Radiology Imaging Through a human-centered LensPLOS ONE Dear Dr. Fouad, 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 Jul 19 2024 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, Cosimo Ieracitano Academic Editor PLOS ONE Journal Requirements: 1. When submitting your revision, we need you to address these additional requirements. 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. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse. 3. Your ethics statement should only appear in the Methods section of your manuscript. If your ethics statement is written in any section besides the Methods, please move it to the Methods section and delete it from any other section. Please ensure that your ethics statement is included in your manuscript, as the ethics statement entered into the online submission form will not be published alongside your manuscript. 4. We note that Figure(s) 3 and 4 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 Figure(s) 3 and 4 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. 5. Kindly upload a separate folder for figure(s) 1 to 26. Please amend the file type to 'Figures'. Additional Editor Comments: AE: This manuscript has some merit, however it is not in a fine shape for consideration of acceptance in its current shape. Beside addressing the reviewers comments, the authors are asked to further motivate the chose of the xAI method used. In addition, the importance of xAI in every application domain (such as space [1] and intrusion detection [1]) should be discussed. [1]https://doi.org/10.1016/j.engappai.2024.108517. [2]https://doi.org/10.1016/j.eswa.2023.121751 [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: N/A ****** 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: The authors proposed XAI model to predict the status of COVID-19.It is DL-enabled diagnostic systems in chest radiography. Two prominent XAI methods, Grad-CAM and LIME, are employed to generate visual explanations of the AI decision-making process. Two clinical scenarios for diagnosing pneumonia and COVID-19 using DL techniques are evaluated, achieving accuracy rates of 90% for pneumonia and 98% for COVID-19. The model seems interesting and may gain many interests, However, I have minor suggestions: -The authors msy highlight recent XAI-Covid models. I suggest to highlight PMID:36738712 and similar methods. -AUCROC plot must be drawn with mulitiple running points. -how the authors checked whether the model overfits or not. Reviewer #2: The paper analyzes the usefulness of xAI techniques (particularly Grad-CAM and LIME) in chest radiology (X-ray and CT) through the lens of the medical professionals who would leverage such advancements in a clinical context. Such an approach is critical in evaluating xAI techniques. The study suggests that Grad-CAM was preferred over LIME regarding coherency and trust, and medical professionals are not aware of the potential uses of xAI. Overall, the paper clearly identifies the gap that it aims to address (human-centered evaluation of Grad-CAM and LIME on a real use case of CAD), uses a grounded approach, and extracts reasonable conclusions from the results. However, the paper could benefit from a more detailed explanation of why Grad-CAM and LIME were the chosen xAI techniques when there are many others available (for example, SHAP is even mentioned in the literature review). It may also benefit from showing the performance of the discarded CNN architectures so one can better understand the weight of each evaluation metric in determining the model’s overall performance. As of now the influence of each metric seems arbitrarily defined. ****** 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: Yes: ABEDALRHMAN Reviewer #2: Yes: José Paulo Marques dos Santos ******** [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.0308758.r001
Revision 1
8 Jul 2024 Author Response Response to Reviewers Dear Reviewers, We sincerely appreciate the time and effort you and the reviewers have dedicated to evaluating our paper and offering valuable feedback. Your insightful comments have significantly contributed to the improvements in this revised version. We have carefully considered each suggestion and endeavoured to address them thoroughly. We hope the revised manuscript meets your high standards and we welcome any further constructive feedback. Below, we provide our point-by-point responses. As requested, all modifications in the marked-up manuscript have been highlighted in yellow. Reviewers’ comments (highlighted in black text below) have been addressed in the updated manuscript and our response is provided in the blue text below. Sincerely, Shereen Fouad, PhD, SFHEA s.fouad@aston.ac.uk ‪Senior Lecturer in Computer Science‬‬‬‬‬‬‬‬‬‬‬‬‬ Aston University (College of Engineering and Physical Sciences)‬ Response to Reviewer 1 General Comment - The authors proposed XAI model to predict the status of COVID-19.It is DL-enabled diagnostic systems in chest radiography. Two prominent XAI methods, Grad-CAM and LIME, are employed to generate visual explanations of the AI decision-making process. Two clinical scenarios for diagnosing pneumonia and COVID-19 using DL techniques are evaluated, achieving accuracy rates of 90% for pneumonia and 98% for COVID-19. The model seems interesting and may gain many interests, However, I have minor suggestions: Response – Thank you very much for your detailed review of our manuscript and your positive assessment. Your useful suggestions have been addressed below and included in our manuscript as advised. Suggestion 1 - The authors msy highlight recent XAI-Covid models. I suggest to highlight PMID:36738712 and similar methods. Response – Thank you for your suggestion, we highlighted recent XAI-Covid models by briefly discussing and citing the recommended article (reference 27) in section 2 (Literature review) paragraph 1, and the new text is highlighted in yellow in the updated manuscript. Suggestion 2 - AUCROC plot must be drawn with mulitiple running points. Response – Thank you for your suggestion, AUCROC plots have been provided for both datasets 1 and 2 (clinical case studies) in Figure 3 (3a and 3b), respectively. The figures are explained in section 3.2.2 paragraph 2, and the new text is highlighted in yellow in the updated manuscript. Suggestion 3 - how the authors checked whether the model overfits or not. Response – Thank you for your question. We implemented several techniques throughout our study to monitor and mitigate overfitting. In particular, our overfitting mitigation approach have been explained in the updated manuscript in section 3.2.1 (Experimental Settings) and the new text is highlighted in yellow in the updated manuscript. We mentioned the followings: “We implemented several techniques throughout our study to monitor and mitigate overfitting. This includes applying regularization techniques, specifically L2 regularization and dropout to penalize model complexity and minimizing the risk of overfitting. For instance, a dropout rate of $1^{-0.5}$ was used in the MobileNetV2 and DenseNet169 models (best performing) to classify chest X-ray images and CT scans into pneumonia and normal, and COVID-19 and Non-COVID-19 cases, respectively. We also utilised early stopping in the models to stop training the model after its optimal number of iterations has been reached. Furthermore, both the training and validation loss curves were continuously monitored to ensure that no significant divergence between these curves occurred, which is often a good indicator of overfitting.” Response to Reviewer 2 General Comment - The paper analyzes the usefulness of xAI techniques (particularly Grad-CAM and LIME) in chest radiology (X-ray and CT) through the lens of the medical professionals who would leverage such advancements in a clinical context. Such an approach is critical in evaluating xAI techniques. The study suggests that Grad-CAM was preferred over LIME regarding coherency and trust, and medical professionals are not aware of the potential uses of xAI. Overall, the paper clearly identifies the gap that it aims to address (human-centered evaluation of Grad-CAM and LIME on a real use case of CAD), uses a grounded approach, and extracts reasonable conclusions from the results. Response – Thank you very much for your thorough review of our manuscript and your thoughtful evaluation. Your useful suggestions have been addressed below and included in our manuscript as advised. Suggestion 1 - However, the paper could benefit from a more detailed explanation of why Grad-CAM and LIME were the chosen xAI techniques when there are many others available (for example, SHAP is even mentioned in the literature review). Response – we included a detailed discussion in section (3.3 Visual Explainability models) justifying why Grad-CAM and LIME were the chosen xAI techniques in our study. and the new text is highlighted in yellow in the updated manuscript. We explained that: “Based on our initial experimental findings, Grad-CAM [12] and LIME [13] provide more stable and accurate localized explanations compared to SHAP [14] in both image classification tasks. Therefore, in this paper, we selected LIME and Grad-CAM methods due to their superior performance in delivering accurate, relevant, and stable explainability results. Evidence from recent literature supports this choice. For instance, a study in remote sensing image classification [35] compared the performance of ten different XAI methods and found that Grad-CAM and LIME were the most interpretable and reliable. Similarly, a research in [16] comparing Grad-CAM, SHAP, and LIME in the context of medical imaging concluded that Grad-CAM and LIME were more reliable, whereas SHAP was not the best for local accuracy in this application. This is consistent with findings in [14], which highlights that while SHAP provides comprehensive feature importance in non-imaging datasets, it may produce less stable explanations in complex image classification tasks, leading to potential inconsistencies. These findings underscore the reliability and relevance of LIME and Grad-CAM in our study, facilitating better insights and trust in the model outputs. “ The above text was included in section 3.3 pages 6&7, and it is highlighted in yellow in the updated manuscript. Suggestion 2 - It may also benefit from showing the performance of the discarded CNN architectures so one can better understand the weight of each evaluation metric in determining the model’s overall performance. As of now the influence of each metric seems arbitrarily defined. Response – Thank you for your suggestion, we have included the experimental results obtained from all the studied deep learning models for dataset 1 and 2 in Tables 1 and 2, respectively. The test results are reported in section 3.2.2 (Results). The Performance Metrics (on testset) of Deep Learning Models on Dataset 1 and 2 are reported in terms of Accuracy, Precision, Recall, and F1 Score. We also report the training and validation loss and accuracy plots for the best performing models, in Dataset 1 and 2, in Figures 1 and 2, respectively. The updated text is highlighted in yellow in the updated manuscript. Attachments Attachment Submitted filename: Response to Reviewers.pdf https://doi.org/10.1371/journal.pone.0308758.r002
30 Jul 2024 Decision Letter - Cosimo Ieracitano, Editor Evaluating Explainable Artificial Intelligence (XAI) Techniques in Chest Radiology Imaging Through a human-centered Lens PONE-D-24-03792R1 Dear Dr. Fouad, 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 will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, 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, Cosimo Ieracitano 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: Yes Reviewer #2: N/A ****** 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: (No Response) 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: The authors have addressed the reviewers comments adequately. The manuscript is in a very good shape. Reviewer #2: The authors addressed all the previous comments/suggestions. Therefore, I recommend the article for publication. ****** 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: Yes: Abedalrhman Alkhateeb Reviewer #2: Yes: José Paulo Marques dos Santos ******** https://doi.org/10.1371/journal.pone.0308758.r003
Formally Accepted
14 Aug 2024 Acceptance Letter - Cosimo Ieracitano, Editor PONE-D-24-03792R1 PLOS ONE Dear Dr. Fouad, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset If revisions are needed, the production department will contact you directly to resolve them. If no revisions are needed, you will receive an email when the publication date has been set. At this time, we do not offer pre-publication proofs to authors during production of the accepted work. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few weeks to review your paper and let you know the next and final steps. Lastly, 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 customercare@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. Cosimo Ieracitano Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0308758.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 .