{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:06:06Z","timestamp":1792789566490,"version":"4.5.0"},"reference-count":36,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,12,28]],"date-time":"2025-12-28T00:00:00Z","timestamp":1766880000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,12,28]],"date-time":"2025-12-28T00:00:00Z","timestamp":1766880000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82502476"],"award-info":[{"award-number":["82502476"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate segmentation of liver tumors on contrast\u2010enhanced CT is essential for clinical decision\u2010making, but remains challenging due to irregular tumor boundaries and the difficulty of distinguishing lesions from blood vessels and bile ducts. Although 3D convolutional networks effectively capture inter\u2010slice contextual information, they are computationally intensive and memory\u2010demanding. In contrast, 2D networks are efficient but limited by their inability to model volumetric context, often resulting in discontinuous or inaccurate segmentations. 2.5D approaches that stack adjacent slices offer a compromise but suffer from early fusion of information that weakens spatial discrimination.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>We propose Mixed U\u2010Net, a hybrid segmentation architecture designed to extract fine\u2010grained z\u2010axis features while maintaining low computational cost.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We embed a small number of 3D convolutional layers into a 2D convolutional U\u2010Net using residual and skip connections. This allows the 3D convolutions to perform fine\u2010grained spatial feature extraction at multiple depths in the network, effectively simulating 3D segmentation within a lightweight framework. Mixed U\u2010Net was trained and evaluated on a dataset of 532 liver tumor cases from Hospital A, and externally validated on 45 cases from Hospital B.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Mixed U\u2010Net achieved a Dice score of 81.54% (95% CI: 81.45%\u201381.62%) on the internal test set, outperforming multiple 2D, 3D, and 2.5D baselines. On the external dataset, it maintained strong performance with a Dice of 78.92%, exceeding the baseline by 4.67%, demonstrating superior generalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>By integrating 3D feature extraction into a primarily 2D architecture, Mixed U\u2010Net balances contextual accuracy with computational efficiency, making it well\u2010suited for clinically applicable liver tumor segmentation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/acm2.70408","type":"journal-article","created":{"date-parts":[[2025,12,28]],"date-time":"2025-12-28T23:47:44Z","timestamp":1766965664000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Mixed U\u2010Net: Segmentation of focal liver lesions using a hybrid 2D and 3D model"],"prefix":"10.1002","volume":"27","author":[{"given":"Feifei","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Radiology West China Hospital Sichuan University  Chengdu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheming","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering University of Electronic Science and Technology of China  Chengdu Sichuan China"},{"name":"Yangtze Delta Region Institute (Quzhou) University of Electronic Science and Technology of China  Quzhou Zhejiang China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Xian","sequence":"additional","affiliation":[{"name":"Quzhou Affiliated Hospital of Wenzhou Medical University Quzhou People's Hospital  Quzhou Zhejiang China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Lu","sequence":"additional","affiliation":[{"name":"Quzhou Affiliated Hospital of Wenzhou Medical University Quzhou People's Hospital  Quzhou Zhejiang China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,12,28]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.21037\/tcr\u201020\u20103319"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102680"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2023.03.010"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1136\/gut.2004.046524"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201051260\u20106"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17237"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.212386"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2022.102088"},{"key":"e_1_2_11_11_1","doi-asserted-by":"crossref","unstructured":"LongJ ShelhamerE DarrellT.Fully convolutional networks for semantic segmentation. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Institute of Electrical and Electronics Engineers;2015:3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_11_12_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010Net: convolutional networks for biomedical image segmentation.In Medical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI 2015: 18th International Conference Munich Germany October 5\u20139 2015 Proceedings Part III 18.Springer International Publishing;2015:234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_11_13_1","doi-asserted-by":"crossref","unstructured":"ZhouZ Rahman SiddiqueeMM TajbakhshN LiangJU\u2010Net++: a nested U\u2010Net architecture for medical image segmentation. In:Deep Learning in Medical Image Analysis and Multimodal Larning for Clinical Decision Support: 4th International Workshop DLMIA 2018 and 8th International Workshop ML\u2010CDS 2018 Held in Conjunction with MICCAI 2018 Granada Spain September 20 2018 Proceedings 4.Springer International Publishing;2018:3\u201311.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"e_1_2_11_14_1","doi-asserted-by":"crossref","unstructured":"ChenLC ZhuY PapandreouG SchroffF AdamHEncoder\u2010decoder with atrous separable convolution for semantic image segmentation.In Proceedings of the European Conference on Computer Vision (ECCV).European Conference on Computer Vision;2018:801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_2_11_15_1","article-title":"An image is worth 16 \u00d7 16 words: transformers for image recognition at scale","author":"Dosovitskiy A","year":"2020","journal-title":"arXiv preprint"},{"key":"e_1_2_11_16_1","first-page":"12077","article-title":"SegFormer: simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie E","year":"2021","journal-title":"Adv Neural Inform Process Syst"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101954"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek\u00d6 AbdulkadirA LienkampSS BroxT RonnebergerO.3D U\u2010Net: learning dense volumetric segmentation from sparse annotation. InMedical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI 2016: 19th International Conference Athens Greece October 17\u201321 2016 Proceedings Part II 19.Springer International Publishing;2016:424\u2013432.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"e_1_2_11_19_1","article-title":"Thickened 2D networks for efficient 3D medical image segmentation","author":"Yu Q","year":"2019","journal-title":"arXiv preprint"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.180.5.1801217"},{"key":"e_1_2_11_21_1","unstructured":"GholamyA KreinovichV KoshelevaO.Why 70\/30 or 80\/20 relation between training and testing sets: a pedagogical explanation.2018."},{"key":"e_1_2_11_22_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Institute of Electrical and Electronics Engineers;2016:770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_11_23_1","doi-asserted-by":"crossref","unstructured":"LiuZ MaoH WuCY FeichtenhoferC DarrellT XieS.A convnet for the 2020s. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.Institute of Electrical and Electronics Engineers;2022:11976\u201311986.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67389-9_44"},{"key":"e_1_2_11_25_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiSA.V\u2010net: fully convolutional neural networks for volumetric medical image segmentation. In:2016 Fourth International Conference on 3D Vision (3DV).Institute of Electrical and Electronics Engineers;2016:565\u2013571. doi:10.1109\/3DV.2016.79","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001008\u2010z"},{"key":"e_1_2_11_27_1","doi-asserted-by":"crossref","unstructured":"IsenseeF WaldT UlrichC et\u00a0al.nnU\u2010Net revisited: a call for rigorous validation in 3D medical image segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer Nature Switzerland;2024:488\u2013498.","DOI":"10.1007\/978-3-031-72114-4_47"},{"key":"e_1_2_11_28_1","doi-asserted-by":"crossref","unstructured":"XiaoT LiuY ZhouB JiangY SunJ.Unified perceptual parsing for scene understanding. In:Proceedings of the European Conference on Computer Vision (ECCV).European Conference on Computer Vision;2018:418\u2013434.","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"e_1_2_11_29_1","doi-asserted-by":"crossref","unstructured":"CholletF.Xception: deep learning with depthwise separable convolutions. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Institute of Electrical and Electronics Engineers;2017:1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_11_30_1","first-page":"272","volume-title":"International MICCAI Brainlesion Workshop","author":"Hatamizadeh A","year":"2021"},{"key":"e_1_2_11_31_1","doi-asserted-by":"crossref","unstructured":"LiuS XuD ZhouSK et\u00a0al.3D anisotropic hybrid network: transferring convolutional features from 2D images to 3D anisotropic volumes. InMedical Image Computing and Computer Assisted Intervention\u2013MICCAI 2018: 21st International Conference Granada Spain September 16\u201320 2018 Proceedings Part II 11.Springer International Publishing;2018:851\u2013858.","DOI":"10.1007\/978-3-030-00934-2_94"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102802"},{"key":"e_1_2_11_33_1","doi-asserted-by":"crossref","unstructured":"LiuZ LinY CaoY et\u00a0al.Swin transformer: hierarchical vision transformer using shifted windows. In:Proceedings of the IEEE\/CVF International Conference on Computer Vision.Institute of Electrical and Electronics Engineers;2021:10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.4251\/wjgo.v5.i4.71"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/4756147"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(09)60737\u20106"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2018.10.004"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70408","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acm2.70408","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T13:08:51Z","timestamp":1771333731000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.70408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,28]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/acm2.70408"],"URL":"https:\/\/doi.org\/10.1002\/acm2.70408","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,28]]},"assertion":[{"value":"2025-06-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70408"}}