{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:26:22Z","timestamp":1787318782190,"version":"build-2736575974"},"reference-count":54,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2022,4,7]],"date-time":"2022-04-07T00:00:00Z","timestamp":1649289600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82071946"],"award-info":[{"award-number":["82071946"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2004"],"award-info":[{"award-number":["U21B2004"]}],"id":[{"id":"10.13039\/501100001809","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":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Automatic segmentation of medical lesions is a prerequisite for efficient clinic analysis. Segmentation algorithms for multimodal medical images have received much attention in recent years. Different strategies for multimodal combination (or fusion), such as probability theory, fuzzy models, belief functions, and deep neural networks, have also been developed. In this paper, we propose the modality weighted UNet (MW\u2010UNet) and attention\u2010based fusion method to combine multimodal images for medical lesion segmentation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>MW\u2010UNet is a multimodal fusion method which is based on UNet, but we use a shallower layer and fewer feature map channels to reduce the amount of network parameters, and our method uses the new multimodal fusion method called fusion attention. It uses weighted sum rule and fusion attention to combine feature maps in intermediate layers. During training, all the weight parameters are updated through backpropagation like other parameters in the network. We also incorporate residual blocks into MW\u2010UNet to further improve segmentation performance. The comparison between the automatic multimodal lesion segmentations and the manual contours was quantified by (1) five metrics including Dice, 95% Hausdorff Distance (HD95), volumetric overlap error (VOE), relative volume difference (RVD), and mean\u2010Intersection\u2010over\u2010Union (mIoU); (2) Number of parameters and flops to calculate the complexity of the\u00a0network.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed method is verified on ZJCHD, which is the data set of contrast\u2010enhanced computed tomography (CECT) for Liver Lesion Segmentation taken from Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Hangzhou, China. For accuracy evaluation, we use 120 patients with liver lesions from ZJCHD, of which 100 are used for fourfold cross\u2010validation (CV) and 20 are used for hold\u2010out (HO) test. The mean Dice was  and  for HO and CV tests, respectively. The corresponding HD95, VOE, RVD, and mIoU of the two tests are 1.95 \u00b1 1.83 and 2.67 \u00b1 3.35 mm, 13.11 \u00b1 15.83 and , 12.20 \u00b1 18.20 and , and 83.79 \u00b1 15.83 and . The parameters and flops of our method is 4.04 M and 18.36 G,\u00a0respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The results show that our method performs well on multimodal liver lesion segmentation. It can be easily extended to other multimodal data sets and other networks for multimodal fusion. Our method is the potential to provide doctors with multimodal annotations and assist them with clinical\u00a0diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.15610","type":"journal-article","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T06:15:02Z","timestamp":1647843302000},"page":"3692-3704","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Medical lesion segmentation by combining multimodal images with modality weighted UNet"],"prefix":"10.1002","volume":"49","author":[{"given":"Xiner","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering Zhejiang University Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichao","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering Zhejiang University Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoji","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering Zhejiang University Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianwei","family":"Zhuang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering Zhejiang University Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jincao","family":"Yao","sequence":"additional","affiliation":[{"name":"Cancer Hospital of the University of Chinese Academy of Sciences Zhejiang Cancer Hospital Hangzhou China"},{"name":"Institute of Basic Medicine and Cancer (IBMC) Chinese Academy of Sciences Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Ou","sequence":"additional","affiliation":[{"name":"Cancer Hospital of the University of Chinese Academy of Sciences Zhejiang Cancer Hospital Hangzhou China"},{"name":"Institute of Basic Medicine and Cancer (IBMC) Chinese Academy of Sciences Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Cancer Hospital of the University of Chinese Academy of Sciences Zhejiang Cancer Hospital Hangzhou China"},{"name":"Institute of Basic Medicine and Cancer (IBMC) Chinese Academy of Sciences Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Song","sequence":"additional","affiliation":[{"name":"Cancer Hospital of the University of Chinese Academy of Sciences Zhejiang Cancer Hospital Hangzhou China"},{"name":"Institute of Basic Medicine and Cancer (IBMC) Chinese Academy of Sciences Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Feng","sequence":"additional","affiliation":[{"name":"Cancer Hospital of the University of Chinese Academy of Sciences Zhejiang Cancer Hospital Hangzhou China"},{"name":"Institute of Basic Medicine and Cancer (IBMC) Chinese Academy of Sciences Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"Cancer Hospital of the University of Chinese Academy of Sciences Zhejiang Cancer Hospital Hangzhou China"},{"name":"Institute of Basic Medicine and Cancer (IBMC) Chinese Academy of Sciences Hangzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,4,7]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crad.2004.07.008"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2015.7341238"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2010.2056369"},{"key":"e_1_2_9_5_1","first-page":"198","volume-title":"Proceedings of ABD\u2010MICCAI","author":"Linguraru MG","year":"2011"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2017.03.008"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.273"},{"key":"e_1_2_9_10_1","first-page":"119","volume-title":"International MICCAI Brainlesion Workshop","author":"Mckinley R","year":"2016"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59050-9_28"},{"key":"e_1_2_9_13_1","first-page":"102","article-title":"An overview of deep learning in medical imaging focusing on MRI","volume":"29","author":"Lundervold AS","year":"2019","journal-title":"Med Phys"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2019.100004"},{"key":"e_1_2_9_15_1","unstructured":"KayalibayB JensenG van derSmagtP.CNN\u2010based segmentation of medical imaging data.arXiv preprint arXiv:1701.03056.2017:1\u201024."},{"key":"e_1_2_9_16_1","first-page":"1","article-title":"Attention U\u2010Net: learning where to look for the pancreas","author":"Oktay O","year":"2018","journal-title":"arXiv preprint arXiv:1804.03999"},{"key":"e_1_2_9_17_1","first-page":"255","volume-title":"Proceedings of ICIP","author":"Yichao W","year":"2019"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.10.004"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.11.001"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528821"},{"key":"e_1_2_9_21_1","first-page":"1","article-title":"Location sensitive deep convolutional neural networks for segmentation of white matter hyperintensities","author":"Ghafoorian M","year":"2017","journal-title":"Sci Rep"},{"key":"e_1_2_9_22_1","unstructured":"\u00c7i\u00e7ekO AbdulkadirA LienkampSS BroxT RonnebergerO.3D U\u2010Net: learning dense volumetric segmentation from sparse annotation.arXiv preprint arXiv:1606.06650.2018:1\u20108."},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/8356294"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46976-8_7"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2014.12.061"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2538465"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.01.024"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11726-9_28"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2016.7493515"},{"key":"e_1_2_9_30_1","unstructured":"BuiTD ShinJ MoonT.3D densely convolutional networks for volumetric segmentation.arXiv preprint arXiv:1709.03199.2018:1\u20107."},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2481436"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46726-9_43"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2948320"},{"key":"e_1_2_9_34_1","first-page":"478","article-title":"Deep learning for multi\u2010task medical image segmentation in multiple modalities","author":"Moeskops P","year":"2016","journal-title":"Springer, Cham"},{"key":"e_1_2_9_35_1","unstructured":"Cl\u00e8riguesA VaverdeS BernalJ FreixenetJ OliverA Llad\u00f3X.SUNet: a deep learning architecture for acute stroke lesion segmentation and outcome prediction in multimodal MRI.arXiv preprint arXiv:1810.13304.2018:1\u201013."},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.013"},{"key":"e_1_2_9_37_1","first-page":"448","volume-title":"Proceedings of ICML","author":"Ioffe S","year":"2015"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_9_39_1","first-page":"5998","volume-title":"Proceedings of NIPS","author":"Vaswani A","year":"2017"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2006.880587"},{"key":"e_1_2_9_41_1","unstructured":"AvantsBB TustisonN SongG.Advanced Normalization Tools (ANTS). Technical report ETH Z\u00fcrich Switzerland 2014."},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"e_1_2_9_43_1","unstructured":"KingmaDP BaJ.Adam: a method for stochastic optimization.arXiv preprint arXiv:1412.6980.2014."},{"key":"e_1_2_9_44_1","article-title":"SegFormer: simple and efficient design for semantic segmentation with transformers","author":"Xie E","year":"2021","journal-title":"arXiv preprint arXiv:2105.15203"},{"key":"e_1_2_9_45_1","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","author":"Chen J","year":"2021","journal-title":"arXiv preprint arXiv:2102.04306"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20170063"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2963882"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14569"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2975344"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-020-02015-1"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101795"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2019.100004"},{"key":"e_1_2_9_53_1","article-title":"Swin Transformer: hierarchical vision transformer using shifted windows","author":"Liu Z","year":"2021","journal-title":"arXiv preprint arXiv:2103.14030"},{"key":"e_1_2_9_54_1","article-title":"Swin\u2010Unet: Unet\u2010like pure transformer for medical image segmentation","author":"Cao H","year":"2021","journal-title":"arXiv preprint arXiv:2105.05537"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_6"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15610","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15610","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T03:50:52Z","timestamp":1692849052000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15610"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,7]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["10.1002\/mp.15610"],"URL":"https:\/\/doi.org\/10.1002\/mp.15610","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,7]]},"assertion":[{"value":"2021-10-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-04","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}