{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T18:13:57Z","timestamp":1779905637566,"version":"3.53.1"},"reference-count":56,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T00:00:00Z","timestamp":1746144000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F2023201069"],"award-info":[{"award-number":["F2023201069"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F2024201052"],"award-info":[{"award-number":["F2024201052"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Distinguishing small cell lung cancer brain metastases from non\u2010small cell lung cancer brain metastases in MRI sequence images is crucial for the accurate diagnosis and treatment of lung cancer brain metastases. Multi\u2010MRI modalities provide complementary and comprehensive information, but efficiently merging these sequences to achieve modality complementarity is challenging due to redundant information within radiomic features and heterogeneity across different modalities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To address these challenges, we propose a novel multimodal fusion network, termed MFN\u2010VAE, which utilizes a variational auto\u2010encoder (VAE) to compress and aggregate radiomic features derived from MRI images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Initially, we extract radiomic features from areas of interest in MRI images across T1WI, FLAIR, and DWI modalities. A VAE encoder is then constructed to project these multimodal features into a latent space, where they are decoded into reconstruction features using a decoder. The encoder\u2010decoder network is trained to extract the underlying feature representation of each modality, capturing both the consistency and specificity of each domain.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental results on our collected dataset of lung cancer brain metastases demonstrate the encouraging performance of our proposed MFN\u2010VAE. The method achieved a 0.888 accuracy and a 0.920 AUC (area under the curve), outperforming state\u2010of\u2010the\u2010art methods across different modal combinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>In this study, we introduce the MFN\u2010VAE, a new multimodal fusion network for differentiating small cell from non\u2010small cell lung cancer brain metastases. Tested on a private dataset, MFN\u2010VAE demonstrated high accuracy (ACC: 0.888; AUC: 0.920), effectively distinguishing between small cell lung cancer brain metastases (SCLC) and non\u2010small cell lung cancer (NSCLC). The SHapley Additive explanation (SHAP) method was used to enhance model interpretability, providing clinicians with a reliable diagnostic tool. Overall, MFN\u2010VAE shows great potential in improving the diagnosis and treatment of lung cancer brain metastases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.17816","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T08:47:01Z","timestamp":1746175621000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A multimodal fusion network based on variational autoencoder for distinguishing SCLC brain metastases from NSCLC brain metastases"],"prefix":"10.1002","volume":"52","author":[{"given":"Xue","family":"Linyan","sequence":"first","affiliation":[{"name":"College of Quality and Technical Supervision Hebei University  Baoding China"},{"name":"Hebei Technology Innovation Center for Lightweight of New Energy Vehicle Power System, and National &amp; Local Joint Engineering Research Center of Metrology Instrument and System Hebei University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cao","family":"Jie","sequence":"additional","affiliation":[{"name":"College of Quality and Technical Supervision Hebei University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Kexuan","sequence":"additional","affiliation":[{"name":"Talented Youth Class of Qian Xuesen College Xi'an Jiaotong University  Xi'an China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Houquan","sequence":"additional","affiliation":[{"name":"College of Quality and Technical Supervision Hebei University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Chaoyi","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineering Hebei University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yin","family":"Xiaosong","sequence":"additional","affiliation":[{"name":"College of Quality and Technical Supervision Hebei University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Jianing","sequence":"additional","affiliation":[{"name":"Department of Radiology Affiliated Hospital of Hebei University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Kun","sequence":"additional","affiliation":[{"name":"College of Quality and Technical Supervision Hebei University  Baoding China"},{"name":"Hebei Technology Innovation Center for Lightweight of New Energy Vehicle Power System, and National &amp; Local Joint Engineering Research Center of Metrology Instrument and System Hebei University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,5,2]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21492"},{"key":"e_1_2_8_3_1","first-page":"11","volume-title":"\u201cBRAIN METASTASIS.\u201d The Bedside Palliative Medicine Handbook","author":"Ying OW","year":"2022"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.12290\/xhyxzz.2022\u20100352"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41572\u2010020\u201000235\u20100"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(10)62101\u20100"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.soc.2016.02.003"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1200\/JOP.19.00357"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.19.01488"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.22.00428"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470\u20102045(19)30634\u20105"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2213\u20102600(21)00166\u20101"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1158\/2159\u20108290.CD\u201014\u20100326"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1097\/00004728\u2010199211000\u201000001"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.06.1403"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1097\/PPO.0000000000000146"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A2668"},{"key":"e_1_2_8_18_1","doi-asserted-by":"crossref","unstructured":"ZhangR LiuQ CuiH et\u00a0al.Thyroid classification via new multi\u2010channel feature association and learning from multi\u2010modality MRI images.2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018).IEEE;2018. doi:10.1109\/ISBI.2018.8363573","DOI":"10.1109\/ISBI.2018.8363573"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"ZhuZ NingZ CuiH et\u00a0al.MuMoSNet: 3D MRI\u2010based brain tumor segmentation via multi\u2010modal and multi\u2010scale feature fusion.2024 IEEE International Conference on Multimedia and Expo (ICME).IEEE;2024. doi:10.1109\/ICME57554.2024.10687443","DOI":"10.1109\/ICME57554.2024.10687443"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101831"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00804"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103758"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2020.3033538"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.105945"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"HatamiN MechtouffL RousseauD et\u00a0al.A novel autoencoders\u2010LSTM model for stroke outcome prediction using multimodal MRI data.2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI).IEEE;2023. doi:10.1109\/ISBI53787.2023.10230459","DOI":"10.1109\/ISBI53787.2023.10230459"},{"key":"e_1_2_8_26_1","unstructured":"RamakrishnanD JekelL ChadhaS et\u00a0al.A large open access dataset of brain metastasis 3D segmentations with clinical and imaging feature information. arXiv.2023. doi:10.1038\/s41597\u2010024\u201003021\u20109"},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"WangJ ZengJ YuX LiuJ.A model based on radiomics and machine learning in glioma grading.2022 2nd International Conference on Bioinformatics and Intelligent Computing;2022. doi:10.1145\/3523286.3524605","DOI":"10.1145\/3523286.3524605"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.18103\/mra.v11i5.3793"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.26524"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering9100532"},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"YeF PuJ WangJ LiY ZhaH.Glioma grading based on 3D multimodal convolutional neural network and privileged learning.2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM);2017:759\u2010763. doi:10.1109\/BIBM.2017.8217751","DOI":"10.1109\/BIBM.2017.8217751"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12073620"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2881110"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587\u2010022\u201001251\u2010z"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489\u2010022\u201003610\u20104"},{"key":"e_1_2_8_36_1","unstructured":"WangY ZhangY LiuY et\u00a0al.ACN: adversarial co\u2010training network for brain tumor segmentation with missing modalities.International Conference on Medical Image Computing and Computer\u2010Assisted Intervention;2021. doi:https:\/\/doi.org\/10.1007\/978\u20103\u2010030\u201087234\u20102_39"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278\u2010021\u201000486\u20107"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2023.3323432"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.796583"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1158\/0008\u20105472.CAN\u201017\u20100339"},{"key":"e_1_2_8_41_1","unstructured":"BaJL KirosJR HintonGE.Layer normalization. ArXiv.2016. abs\/1607.06450."},{"key":"e_1_2_8_42_1","unstructured":"HendrycksD GimpelK.Gaussian error linear units (GELUs). arXiv: Learning.2016."},{"key":"e_1_2_8_43_1","unstructured":"IoffeS SzegedyC.Batch normalization: accelerating deep network training by reducing internal covariate shift.International Conference on Machine Learning.PMLR;2015."},{"key":"e_1_2_8_44_1","unstructured":"AgarapAF.Deep Learning using Rectified Linear Units (ReLU). arXiv abs\/1803.08375.2018."},{"issue":"365","key":"e_1_2_8_45_1","first-page":"1","article-title":"Advanced normalization tools (ANTS)","volume":"2","author":"Avants BB","year":"2009","journal-title":"Insight J"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/38.219451"},{"key":"e_1_2_8_47_1","doi-asserted-by":"crossref","unstructured":"OjalaT PietikainenM HarwoodD.Performance evaluation of texture measures with classification based on Kullback discrimination of distributions.Proceedings of 12th International Conference on Pattern Recognition Vol.1.IEEE;1994. doi:10.1109\/ICPR.1994.576366","DOI":"10.1109\/ICPR.1994.576366"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/0031\u20103203(95)00067\u20104"},{"key":"e_1_2_8_49_1","unstructured":"BanerjeeJ MoelkerA NiessenWJ vanWalsum T.3D LBP\u2010based rotationally invariant region description.Computer Vision\u2010ACCV 2012 Workshops: ACCV 2012 International Workshops Daejeon Korea November 5\u20136 2012 Revised Selected Papers Part I 11.Springer Berlin Heidelberg;2013. doi:10.1007\/978\u20103\u2010642\u201037410\u20104_3"},{"key":"e_1_2_8_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2228639"},{"key":"e_1_2_8_51_1","doi-asserted-by":"crossref","unstructured":"HanH WangW\u2010Y MaoB\u2010H.Borderline\u2010SMOTE: a new over\u2010sampling method in imbalanced data sets learning.International Conference on Intelligent Computing;2005. doi:10.1007\/11538059_91","DOI":"10.1007\/11538059_91"},{"key":"e_1_2_8_52_1","unstructured":"LoshchilovI HutterF.Fixing weight decay regularization in Adam. arXiv abs\/1711.05101.2017"},{"key":"e_1_2_8_53_1","volume-title":"Algorithms for Hyper\u2010Parameter Optimization","author":"Bergstra JS","year":"2011"},{"key":"e_1_2_8_54_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_8_55_1","unstructured":"HosmerDW LemeshowS SturdivantRX.Applied Logistic Regression.Hoboken NJ:John Wiley & Sons;2013."},{"key":"e_1_2_8_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"e_1_2_8_57_1","unstructured":"LundbergSM LeeS\u2010I.A unified approach to interpreting model predictions. arXiv abs\/1705.07874.2017."}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T10:31:09Z","timestamp":1765189869000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17816"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,2]]},"references-count":56,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1002\/mp.17816"],"URL":"https:\/\/doi.org\/10.1002\/mp.17816","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,2]]},"assertion":[{"value":"2024-05-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e17816"}}