{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T23:58:44Z","timestamp":1793404724663,"version":"4.5.0"},"reference-count":25,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Respirology"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background and Objective<\/jats:title>\n                    <jats:p>Echo features of lymph nodes (LNs) influence target selection during endobronchial ultrasound\u2010guided transbronchial needle aspiration (EBUS\u2010TBNA). This study evaluates deep learning's diagnostic capabilities on EBUS images for detecting mediastinal LN metastasis in lung cancer, emphasising the added value of integrating a region of interest (ROI), LN size on CT, and PET\u2010CT findings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analysed 2901 EBUS images from 2055 mediastinal LN stations in 1454 lung cancer patients. ResNet18\u2010based deep learning models were developed to classify images of true positive malignant and true negative benign LNs diagnosed by EBUS\u2010TBNA using different inputs: original images, ROI images, and CT size and PET\u2010CT data. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC)\u00a0and other diagnostic metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The model using only original EBUS images showed the lowest AUROC (0.870) and accuracy (80.7%) in classifying LN images. Adding ROI information slightly increased the AUROC (0.896) without a significant difference (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.110). Further adding CT size resulted in a minimal change in AUROC (0.897), while adding PET\u2010CT (original + ROI + PET\u2010CT) showed a significant improvement (0.912,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.008 vs. original;\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.002 vs. original + ROI + CT size). The model combining original and ROI EBUS images with CT size and PET\u2010CT findings achieved the highest AUROC (0.914,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.005 vs. original;\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.018 vs. original + ROI + PET\u2010CT) and accuracy (82.3%).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Integrating an ROI, LN size on CT, and PET\u2010CT findings into the deep learning analysis of EBUS images significantly enhances the diagnostic capability of models for detecting mediastinal LN metastasis in lung cancer, with the integration of PET\u2010CT data having a substantial impact.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/resp.70010","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T16:55:09Z","timestamp":1741712109000},"page":"515-522","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Prediction of Lymph Node Metastasis in Lung Cancer Using\u00a0Deep Learning of Endobronchial Ultrasound Images\u00a0With Size on\n                    <scp>CT<\/scp>\n                    and\n                    <scp>PET<\/scp>\n                    \u2010\n                    <scp>CT<\/scp>\n                    Findings"],"prefix":"10.1111","volume":"30","author":[{"given":"Ji Eun","family":"Oh","sequence":"first","affiliation":[{"name":"Healthcare AI Team National Cancer Center  Goyang Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8834-7302","authenticated-orcid":false,"given":"Hyun Sung","family":"Chung","sequence":"additional","affiliation":[{"name":"Division of Pulmonology Center for Lung Cancer, National Cancer Center  Goyang Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hye Ran","family":"Gwon","sequence":"additional","affiliation":[{"name":"Division of Pulmonology Center for Lung Cancer, National Cancer Center  Goyang Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eun Young","family":"Park","sequence":"additional","affiliation":[{"name":"Biostatistics Collaboration Team, Research Core Center, National Cancer Center  Goyang Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyae Young","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Radiology National Cancer Center  Goyang Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geon Kook","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Pathology National Cancer Center  Goyang Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tae\u2010Sung","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine National Cancer Center  Goyang Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7979-7419","authenticated-orcid":false,"given":"Bin","family":"Hwangbo","sequence":"additional","affiliation":[{"name":"Division of Pulmonology Center for Lung Cancer, National Cancer Center  Goyang Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,3,3]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.12-2355"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezu028"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.00800-2018"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2023.03.041"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.athoracsur.2018.02.088"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtcvs.2023.11.020"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.09-2006"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtcvs.2019.10.205"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.4103\/EUS-D-20-00207"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14143334"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.21037\/tlcr-21-870"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.11648\/j.mma.20200502.14"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.08-2019"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.130.3.710"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1097\/LBR.0000000000000545"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1440-1843.2012.02223.x"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.11-0252"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/03007995.2020.1837763"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2024.1448294"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201607-1397OC"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00438-z"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102125"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104806"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2019.05.002"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13550-017-0260-9"}],"container-title":["Respirology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/resp.70010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T06:11:34Z","timestamp":1751004694000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/resp.70010"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,3]]},"references-count":25,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.1111\/resp.70010"],"URL":"https:\/\/doi.org\/10.1111\/resp.70010","archive":["Portico"],"relation":{},"ISSN":["1323-7799","1440-1843"],"issn-type":[{"value":"1323-7799","type":"print"},{"value":"1440-1843","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,3]]},"assertion":[{"value":"2024-09-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}