{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T20:25:16Z","timestamp":1791923116701,"version":"4.3.4"},"reference-count":46,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T00:00:00Z","timestamp":1770681600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Liaison Committee for Education, Research, and Innovation in Central Norway","award":["46055500"],"award-info":[{"award-number":["46055500"]}]},{"name":"Ministry of Health and Care Services of Norway"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Accurate localization of thoracic lymph nodes during endobronchial ultrasound (EBUS) is crucial for lung cancer staging, treatment planning, and prognostication. Artificial intelligence (AI) has the potential to support this process. Deep learning (DL) models often lack transparency but can benefit from explainable AI (XAI) tools like Gradient-weighted Class Activation Mapping (Grad-CAM). However, no prior study has quantitatively assessed whether model attention in EBUS imaging corresponds to relevant anatomy. This study developed a convolutional neural network (CNN) to classify thoracic lymph node stations and evaluated the anatomical relevance of Grad-CAM activations using a structured annotation framework. Applied on 35,527 labeled EBUS images, the CNN achieved 63.1% accuracy, with the highest F1-score in stations 4L, 4R, and 10R. Three expert bronchoscopists independently annotated Grad-CAM maps from 3131 test images. Activations predominantly aligned with lymph nodes and\/or blood vessels, yielding an accuracy of 65.9% and an F1-score of 58.4%, with moderate interobserver agreement. These findings indicate that DL can aid lymph node station classification and that XAI offers meaningful insight into model behavior. The proposed framework may enhance anatomical orientation and operator training during EBUS, although further optimization and multicenter validation are required.<\/jats:p>","DOI":"10.3390\/bioengineering13020198","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T11:16:38Z","timestamp":1770722198000},"page":"198","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Explainability of a Deep Learning Model for Mediastinal Lymph Node Station Classification in Endobronchial Ultrasound (EBUS)"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5857-3295","authenticated-orcid":false,"given":"\u00d8yvind","family":"Ervik","sequence":"first","affiliation":[{"name":"Clinic of Medicine, Nord-Tr\u00f8ndelag Hospital Trust, Levanger Hospital, 7601 Levanger, Norway"},{"name":"Department of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, 7030 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3141-3320","authenticated-orcid":false,"given":"Mia","family":"R\u00f8dde","sequence":"additional","affiliation":[{"name":"Department of Health Research, SINTEF Digital, Trondheim, 7034 Trondheim, Norway"},{"name":"HUNT Research Centre, Department of Public Health and Nursing, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, NTNU, 7600 Levanger, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5927-7468","authenticated-orcid":false,"given":"Erlend Fagertun","family":"Hofstad","sequence":"additional","affiliation":[{"name":"Department of Health Research, SINTEF Digital, Trondheim, 7034 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2824-6120","authenticated-orcid":false,"given":"Thomas","family":"Lang\u00f8","sequence":"additional","affiliation":[{"name":"Department of Health Research, SINTEF Digital, Trondheim, 7034 Trondheim, Norway"},{"name":"National Research Center for Minimally Invasive and Image-Guided Diagnostics and Therapy, St. Olavs Hospital, 7030 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0845-3891","authenticated-orcid":false,"given":"H\u00e5kon O.","family":"Leira","sequence":"additional","affiliation":[{"name":"Department of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, 7030 Trondheim, Norway"},{"name":"National Research Center for Minimally Invasive and Image-Guided Diagnostics and Therapy, St. Olavs Hospital, 7030 Trondheim, Norway"},{"name":"Department of Thoracic Medicine, St. Olavs Hospital, Trondheim University Hospital, 7030 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4714-1949","authenticated-orcid":false,"given":"Tore","family":"Amundsen","sequence":"additional","affiliation":[{"name":"Department of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, 7030 Trondheim, Norway"},{"name":"Department of Thoracic Medicine, St. Olavs Hospital, Trondheim University Hospital, 7030 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9968-3491","authenticated-orcid":false,"given":"Hanne","family":"Sorger","sequence":"additional","affiliation":[{"name":"Clinic of Medicine, Nord-Tr\u00f8ndelag Hospital Trust, Levanger Hospital, 7601 Levanger, Norway"},{"name":"Department of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, 7030 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"ref_1","first-page":"209","article-title":"Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","unstructured":"WHO (2023). Global Health Estimates: Leading Causes of Death and Disability, World Health Organization."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"iv1","DOI":"10.1093\/annonc\/mdx222","article-title":"Early and locally advanced non-small-cell lung cancer (NSCLC): ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up","volume":"28","author":"Postmus","year":"2017","journal-title":"Ann. Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1093\/ejcts\/ezu028","article-title":"Revised ESTS guidelines for preoperative mediastinal lymph node staging for non-small-cell lung cancer","volume":"45","author":"Dooms","year":"2014","journal-title":"Eur. J. Cardiothorac. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e211S","DOI":"10.1378\/chest.12-2355","article-title":"Methods for staging non-small cell lung cancer: Diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians evidence-based clinical practice guidelines","volume":"143","author":"Silvestri","year":"2013","journal-title":"Chest"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1055\/s-0034-1392040","article-title":"Combined endobronchial and esophageal endosonography for the diagnosis and staging of lung cancer: European Society of Gastrointestinal Endoscopy (ESGE) Guideline, in cooperation with the European Respiratory Society (ERS) and the European Society of Thoracic Surgeons (ESTS)","volume":"47","author":"Vilmann","year":"2015","journal-title":"Endoscopy"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1378\/chest.10-0955","article-title":"Endosonography for lung cancer staging: One scope fits all?","volume":"138","author":"Annema","year":"2010","journal-title":"Chest"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1016\/j.jtho.2024.02.011","article-title":"The International Association for the Study of Lung Cancer Lung Cancer Staging Project: Proposals for Revision of the TNM Stage Groups in the Forthcoming (Ninth) Edition of the TNM Classification for Lung Cancer","volume":"19","author":"Nishimura","year":"2024","journal-title":"J. Thorac. Oncol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1718","DOI":"10.1378\/chest.111.6.1718","article-title":"Regional lymph node classification for lung cancer staging","volume":"111","author":"Mountain","year":"1997","journal-title":"Chest"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1016\/j.jtho.2023.10.012","article-title":"The International Association for the Study of Lung Cancer Staging Project for Lung Cancer: Proposals for the Revision of the N Descriptors in the Forthcoming Ninth Edition of the TNM Classification for Lung Cancer","volume":"19","author":"Huang","year":"2024","journal-title":"J. Thorac. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"882","DOI":"10.1016\/j.chest.2024.05.026","article-title":"The Proposed Ninth Edition TNM Classification of Lung Cancer","volume":"166","author":"Detterbeck","year":"2024","journal-title":"Chest"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1164\/rccm.201111-1968OC","article-title":"Endobronchial ultrasound skills and tasks assessment tool: Assessing the validity evidence for a test of endobronchial ultrasound-guided transbronchial needle aspiration operator skill","volume":"186","author":"Davoudi","year":"2012","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1378\/chest.11-1986","article-title":"The endobronchial ultrasound-guided transbronchial needle biopsy learning curve for mediastinal and hilar lymph node diagnosis","volume":"141","year":"2012","journal-title":"Chest"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1378\/chest.12-2462","article-title":"Point: Are >50 supervised procedures required to develop competency in performing endobronchial ultrasound-guided transbronchial needle aspiration for mediastinal staging? Yes","volume":"143","author":"Folch","year":"2013","journal-title":"Chest"},{"key":"ref_15","first-page":"127","article-title":"Artificial intelligence in cancer imaging: Clinical challenges and applications","volume":"69","author":"Bi","year":"2019","journal-title":"CA Cancer J. Clin."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kufel, J., Bargie\u0142-\u0141\u0105czek, K., Kocot, S., Ko\u017alik, M., Bartnikowska, W., Janik, M., Czogalik, \u0141., Dudek, P., Magiera, M., and Lis, A. (2023). What Is Machine Learning, Artificial Neural Networks and Deep Learning?-Examples of Practical Applications in Medicine. Diagnostics, 13.","DOI":"10.3390\/diagnostics13152582"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1426","DOI":"10.1109\/TBME.2015.2494838","article-title":"Methods for 2-D and 3-D Endobronchial Ultrasound Image Segmentation","volume":"63","author":"Zang","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"14","DOI":"10.21037\/tlcr-21-870","article-title":"Malignant thoracic lymph node classification with deep convolutional neural networks on real-time endobronchial ultrasound (EBUS) images","volume":"11","author":"Yong","year":"2022","journal-title":"Transl. Lung Cancer Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.athoracsur.2021.06.082","article-title":"An Artificial Intelligence Algorithm to Predict Nodal Metastasis in Lung Cancer","volume":"114","author":"Churchill","year":"2022","journal-title":"Ann. Thorac. Surg."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2019","DOI":"10.1080\/03007995.2020.1837763","article-title":"Can artificial intelligence distinguish between malignant and benign mediastinal lymph nodes using sonographic features on EBUS images?","volume":"36","author":"Ozcelik","year":"2020","journal-title":"Curr. Med. Res. Opin."},{"key":"ref_21","first-page":"741","article-title":"Artificial Intelligence Algorithm Can Predict Lymph Node Malignancy from Endobronchial Ultrasound Transbronchial Needle Aspiration Images for Non-Small Cell Lung Cancer","volume":"103","author":"Patel","year":"2024","journal-title":"Respiration"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"9339","DOI":"10.1007\/s00464-023-10488-x","article-title":"Machine learning approaches in the interpretation of endobronchial ultrasound images: A comparative analysis","volume":"37","author":"Koseoglu","year":"2023","journal-title":"Surg. Endosc."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ervik, \u00d8., Tveten, I., Hofstad, E.F., Lang\u00f8, T., Leira, H.O., Amundsen, T., and Sorger, H. (2024). Automatic Segmentation of Mediastinal Lymph Nodes and Blood Vessels in Endobronchial Ultrasound (EBUS) Images Using Deep Learning. J. Imaging, 10.","DOI":"10.3390\/jimaging10080190"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Winiarski, S., Radziszewski, M., Wi\u015bniewski, M., Cisek, J., W\u0105sowski, D., Plewczynski, D., G\u00f3rska, K., and Korczynski, P. (2025). Integrating Artificial Intelligence in Bronchoscopy and Endobronchial Ultrasound (EBUS) for Lung Cancer Diagnosis and Staging: A Comprehensive Review. Cancers, 17.","DOI":"10.3390\/cancers17172835"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.xjtc.2024.09.008","article-title":"Deep learning-based prediction of nodal metastasis in lung cancer using endobronchial ultrasound","volume":"28","author":"Ishiwata","year":"2024","journal-title":"JTCVS Tech."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1097\/eus.0000000000000011","article-title":"A deep learning-based system for mediastinum station localization in linear EUS (with video)","volume":"12","author":"Yao","year":"2023","journal-title":"Endosc. Ultrasound"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ervik, \u00d8., R\u00f8dde, M., Hofstad, E.F., Tveten, I., Lang\u00f8, T., Leira, H.O., Amundsen, T., and Sorger, H. (2025). A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study. J. Imaging, 11.","DOI":"10.3390\/jimaging11010010"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1097\/LBR.0b013e31829cb2b5","article-title":"Bronchoscope-induced displacement of lung targets: First in vivo demonstration of effect from wedging maneuver in navigated bronchoscopy","volume":"20","author":"Leira","year":"2013","journal-title":"J. Bronchol. Interv. Pulmonol."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Sorger, H., Hofstad, E.F., Amundsen, T., Lang\u00f8, T., Bakeng, J.B., and Leira, H.O. (2017). A multimodal image guiding system for Navigated Ultrasound Bronchoscopy (EBUS): A human feasibility study. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0171841"},{"key":"ref_30","unstructured":"Igor, V.M., and Oleg, V.M. (2011). Techniques of Linear Endobronchial Ultrasound. Ultrasound Imaging, IntechOpen."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e1312","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","year":"2019","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.csbj.2024.08.005","article-title":"Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis","volume":"24","author":"Muhammad","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_34","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017, January 4\u20139). A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.jfma.2024.04.016","article-title":"TransEBUS: The interpretation of endobronchial ultrasound image using hybrid transformer for differentiating malignant and benign mediastinal lesions","volume":"124","author":"Lin","year":"2025","journal-title":"J. Formos. Med. Assoc."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1097\/LBR.0000000000000545","article-title":"Preoperative Staging by EBUS in cN0\/N1 Lung Cancer: Systematic Review and Meta-Analysis","volume":"26","author":"Leong","year":"2019","journal-title":"J. Bronchol. Interv. Pulmonol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"568","DOI":"10.1097\/JTO.0b013e3181a0d82e","article-title":"The IASLC Lung Cancer Staging Project: A Proposal for a New International Lymph Node Map in the Forthcoming Seventh Edition of the TNM Classification for Lung Cancer","volume":"4","author":"Rusch","year":"2009","journal-title":"J. Thorac. Oncol."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_40","unstructured":"TensorFlow (2025, December 06). tf.keras.optimizers.AdamW\u2014TensorFlow Documentation. Available online: https:\/\/www.tensorflow.org\/api_docs\/python\/tf\/keras\/optimizers\/AdamW."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"F\u0131rat, M., F\u0131rat, \u0130.T., \u00dcst\u00fcnda\u011f, Z.F., \u00d6zt\u00fcrk, E., and Tuncer, T. (2025). AI-Based Response Classification After Anti-VEGF Loading in Neovascular Age-Related Macular Degeneration. Diagnostics, 15.","DOI":"10.3390\/diagnostics15172253"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Obaid, W., Hussain, A., Rabie, T., and Mansoor, W. (2025). Noisy Ultrasound Kidney Image Classifications Using Deep Learning Ensembles and Grad-CAM Analysis. AI, 6.","DOI":"10.3390\/ai6080172"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Smistad, E., \u00d8stvik, A., and L\u00f8vstakken, L. (2021, January 11\u201316). Annotation Web\u2014An open-source web-based annotation tool for ultrasound images. Proceedings of the 2021 IEEE International Ultrasonics Symposium (IUS), Xi\u2019an, China.","DOI":"10.1109\/IUS52206.2021.9593336"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1136\/thoraxjnl-2011-200063","article-title":"Utility of endobronchial ultrasound-guided transbronchial needle aspiration in patients with tuberculous intrathoracic lymphadenopathy: A multicentre study","volume":"66","author":"Navani","year":"2011","journal-title":"Thorax"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1016\/j.lungcan.2005.07.013","article-title":"Endobronchial ultrasound guided transbronchial needle aspiration for staging of lung cancer","volume":"50","author":"Yasufuku","year":"2005","journal-title":"Lung Cancer"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P., and Balasubramanian, V.N. (2018, January 12\u201315). Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA.","DOI":"10.1109\/WACV.2018.00097"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/2\/198\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T11:54:11Z","timestamp":1770724451000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/2\/198"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,10]]},"references-count":46,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["bioengineering13020198"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13020198","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,10]]}}}