{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T16:44:07Z","timestamp":1793033047652,"version":"4.5.0"},"reference-count":60,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"vor","delay-in-days":20,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Markerless tumor tracking (MTT) using single\u2010energy (SE) kilovoltage (kV) imaging has been proposed as a technique for lung tumor motion management. However, bony structures can obscure the tumor and make tracking challenging. Dual\u2010energy (DE) subtraction imaging can suppress the bone and therefore enhance tumor visibility, potentially improving tracking accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop a machine learning model that predicts the reliability of MTT for SE and DE imaging using phantom and patient data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Images were collected at high and low energy (120\/60\u00a0kV) using fast\u2010kV switching on dynamic thorax phantom with 5\u201315 diameter targets and 20 lung cancer patients, including one patient with two tumor locations. DE images were then generated off\u2010line using weighted logarithmic subtraction. Separately, a template\u2010based tracking algorithm was used to track the tumor on both phantom and patient images. For phantom data, the ground truth (GT) was defined by the cos\n                      <jats:sup>4<\/jats:sup>\n                      waveform programmed into the motion controller. Since the GT was unknown for patient data, it was estimated using a Kalman filter and further refined using visual inspection. The tracking success rate (TSR) was subsequently calculated. Based on TSR, patients were stratified into three tracking groups: good, moderate, and poor. A logistic regression (LR) model was implemented with tracking features, including match score, peak to side\u2010peak ratio (PSR),\n                      <jats:italic>x<\/jats:italic>\n                      \u2010 and\n                      <jats:italic>y<\/jats:italic>\n                      \u2010velocity. To address the distribution differences between phantom and patient data, a domain indicator and interaction features were also incorporated. The model was trained on phantom and 17 patient data using leave\u2010one\u2010out cross\u2010validation, and its performance was evaluated on three held\u2010out patients, one from each tracking group. Separate LR models were developed for each imaging modality, resulting in SE\u2010LR and DE\u2010LR models. For each held\u2010out patient, the confusion matrix, sensitivity, and specificity were reported.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      For both SE\u2010LR and DE\u2010LR models, PSR has the largest coefficient value, indicating that it is the most influential factor when determining the reliability of tracking. At a specificity of 95%, the DE\u2010LR model achieved significantly higher sensitivity than the SE\u2010LR model (0.908 vs. 0.731,\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.01 for phantom data and 0.657 vs. 0.589,\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a00.01 for patient data). In the three held\u2010out patients, the DE\u2010LR model outperformed the SE\u2010LR model across all metrics. The largest gains were found in the patient with good tracking quality.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The proposed LR models successfully predicted the reliability of SE\u2010 and DE\u2010MTT. Across phantom and patient datasets, the DE\u2010LR model consistently demonstrated improved performance compared with the SE\u2010LR model, suggesting that DE imaging may be beneficial for MTT applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/acm2.70621","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T08:00:53Z","timestamp":1779350453000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of the reliability of markerless tumor tracking with single\u2010energy and dual\u2010energy imaging using machine learning"],"prefix":"10.1002","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5246-6236","authenticated-orcid":false,"given":"Ha","family":"Nguyen","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Stritch School of Medicine Cardinal Bernadin Cancer Center Loyola University Chicago  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Luce","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Stritch School of Medicine Cardinal Bernadin Cancer Center Loyola University Chicago  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangjia","family":"Zhu","sequence":"additional","affiliation":[{"name":"Varian Medical System  Palo Alto California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Lehmann","sequence":"additional","affiliation":[{"name":"Varian Medical System  Palo Alto California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4433-0939","authenticated-orcid":false,"given":"Hyejoo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Stritch School of Medicine Cardinal Bernadin Cancer Center Loyola University Chicago  Maywood Illinois USA"},{"name":"Department of Radiation Oncology Loyola University Medical School  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew M.","family":"Harkenrider","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Loyola University Medical School  Maywood Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John C.","family":"Roeske","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Mayo Clinic  Phoenix Arizona USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13573"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2020.01.008"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/aaf9dd"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2015.07.101"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.07.128"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15418"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2021.100705"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/aa6393"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17940"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.07.517"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12916\u2010019\u20101426\u20102"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100003"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14559"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2021.05.007"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17039"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16470"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12111197"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.06.438"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17949"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13821"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13993"},{"key":"e_1_2_11_23_1","doi-asserted-by":"crossref","unstructured":"MostafaviH SloutskyA JeungA.Detection and localization of radiotherapy targets by template matching. InProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. EMBS;2012:6023\u20106027. doi:10.1109\/EMBC.2012.6347367","DOI":"10.1109\/EMBC.2012.6347367"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ac06e3"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"e_1_2_11_26_1","unstructured":"JiangS ShiJ MouraS.A New Framework for Nonlinear Kalman Filters.2024:1\u201015.http:\/\/arxiv.org\/abs\/2407.05717"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2006.08.015"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1129380"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911\u2010019\u20101004\u20108"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.06.228"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2004.04.005"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034077"},{"key":"e_1_2_11_33_1","unstructured":"PinheiroJMH deOliveiraSVB SilvaTHS et\u00a0al.The Impact of Feature Scaling In Machine Learning: Effects on Regression and Classification Tasks.2025.http:\/\/arxiv.org\/abs\/2506.08274"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885\u2010018\u20104647\u20104"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16865"},{"key":"e_1_2_11_36_1","unstructured":"LiJL HsuCF ChangMC ChenWC.A Comprehensive Review of Machine Learning Advances on Data Change: A Cross\u2010Field Perspective.2024;XX(X):1\u201020.http:\/\/arxiv.org\/abs\/2402.12627"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3117407"},{"key":"e_1_2_11_38_1","unstructured":"GaoY BaoR JiY et\u00a0al.Transfer Learning with Clinical Concept Embeddings from Large Language Models.2024:167\u2010176.http:\/\/arxiv.org\/abs\/2409.13893"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2023.119863"},{"key":"e_1_2_11_40_1","volume-title":"Interaction Effects in Logistic Regression (Quantitative Applications in the Social Sciences)","author":"Jaccard J","year":"2001"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfma.2011.09.005"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118548387"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129527"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.3390\/math12223572"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010023\u201048177\u20103"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.21608\/mjeer.2021.70512.1034"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104431"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467\u20109868.2005.00503.x"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.4258\/HIR.2021.27.3.189"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220232"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1136\/ebnurs\u20102019\u2010103225"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3598435"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1177\/15330338221112280"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17743"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2019.02.004"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.3390\/informatics8040079"},{"key":"e_1_2_11_57_1","doi-asserted-by":"publisher","DOI":"10.21037\/jtd.2019.01.25"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.21037\/qims\u201022\u2010621"},{"key":"e_1_2_11_59_1","doi-asserted-by":"crossref","unstructured":"XueC DouQ ShiX ChenH HengPA.Robust learning at noisy labeled medical images: applied to skin lesion classification. InProceedings\u2014International Symposium on Biomedical Imaging.2019:1280\u20101283. doi:10.1109\/ISBI.2019.8759203","DOI":"10.1109\/ISBI.2019.8759203"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2024.110244"},{"key":"e_1_2_11_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11517\u2010025\u201003437\u20104"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70621","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acm2.70621","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T16:31:45Z","timestamp":1793032305000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.70621"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":60,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1002\/acm2.70621"],"URL":"https:\/\/doi.org\/10.1002\/acm2.70621","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"2026-01-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70621"}}