{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T14:56:47Z","timestamp":1768402607888,"version":"3.49.0"},"reference-count":58,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":13,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Transformers have achieved remarkable success in medical image segmentation due to their large receptive fields and global context extraction capabilities. However, convolutional neural networks (CNNs) face limitations with fixed\u2010size kernels, hindering their ability to capture multi\u2010scale features. To address these challenges, we propose two novel modules: the multi\u2010head channel mixed convolution (MHCMC) module, which enhances feature extraction by expanding the receptive field and utilizing channel attention, and the dynamic feature aggregation (DFA) module, which adaptively prioritizes crucial spatial features based on global information. Additionally, we introduce the evolutionary hybrid network (EHN) to simulate the transition from local to global dependency capture. The MHCMC and DFA modules are first fused to construct the multi\u2010head DFA (MHDFA) module. Subsequently, the MHDFA and EHN modules are sequentially stacked to form the encoder, which we denote as the multi\u2010head dynamic aggregation transformer (MDAT). By further integrating MDAT into the U\u2010Net architecture, we obtain the proposed MDAT\u2010Net. Experimental results show that MDAT\u2010Net outperforms other state\u2010of\u2010the\u2010art models in three medical image segmentation tasks: the liver tumor segmentation benchmark (LiTs2017), CVC LinicDB, and the automated cardiac diagnosis challenge (ACDC).<\/jats:p>","DOI":"10.1049\/ipr2.70274","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T08:59:45Z","timestamp":1768381185000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi\u2010Head Convolution Module With Dynamic Feature Fusion for Medical Image Segmentation"],"prefix":"10.1049","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1358-9982","authenticated-orcid":false,"given":"Zijian","family":"Chen","sequence":"first","affiliation":[{"name":"College of Medical Information Engineering Guangdong Pharmaceutical University Guangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangwei","family":"Qin","sequence":"additional","affiliation":[{"name":"College of Medical Information Engineering Guangdong Pharmaceutical University Guangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaohan","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Medical Information Engineering Guangdong Pharmaceutical University Guangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1888-7490","authenticated-orcid":false,"given":"Zhanpeng","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Medical Information Engineering Guangdong Pharmaceutical University Guangzhou China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"e_1_2_10_3_1","first-page":"234","volume-title":"U\u2010Net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger O.","year":"2015"},{"key":"e_1_2_10_4_1","unstructured":"J.Chen Y.Lu Q.Yu et\u00a0al. \u201cTransUNet: Transformers Make Strong Encoders for Medical Image Segmentation \u201d (2021). ArXiv abs\/2102.04306."},{"key":"e_1_2_10_5_1","first-page":"236","volume-title":"Reverse Attention for Salient Object Detection","author":"Chen S.","year":"2018"},{"key":"e_1_2_10_6_1","volume-title":"Attention U\u2010Net: Learning Where to Look for the Pancreas","author":"Oktay O.","year":"2018"},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","unstructured":"X.Wang R.Girshick A.Gupta andK.He \u201cNon\u2010Local Neural Networks \u201d2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018):7794\u20137803 https:\/\/doi.org\/10.1109\/CVPR.2018.00813.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_2_10_8_1","volume-title":"An Image Is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale, Cornell University Library","author":"Dosovitskiy A.","year":"2021"},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","unstructured":"W.Wang E.Xie andX.Li et al. \u201cPyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions \u201d2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(2021):548\u2013558 https:\/\/doi.org\/10.1109\/ICCV48922.2021.00061.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","unstructured":"Z.Liu Y.Lin Y.Cao et\u00a0al. \u201cSwin Transformer: Hierarchical Vision Transformer Using Shifted Windows \u201d2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(2021):9992\u201310002 https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"M.Liu Z.Meng andC.Zhao et al. \u201cAdaViT: Adaptive Vision Transformers for Efficient Image Recognition \u201d2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2022):12299\u201312308.","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"e_1_2_10_12_1","unstructured":"Y.Rao W.Zhao B.Liu J.Lu J.Zhou andC.Hsieh \u201cDynamicViT: Efficient Vision Transformers With Dynamic Token Sparsification \u201d (2021). ArXiv abs\/2106.02034."},{"key":"e_1_2_10_13_1","volume-title":"CoAtNet: Marrying Convolution and Attention for all Data Sizes","author":"Dai Z.","year":"2021"},{"key":"e_1_2_10_14_1","volume-title":"MobileViT: Light\u2010weight, General\u2010purpose, and Mobile\u2010friendly Vision Transformer","author":"Mehta S.","year":"2022"},{"key":"e_1_2_10_15_1","unstructured":"J.Li X.Xia W.Li et\u00a0al. \u201cNext\u2010ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios \u201d (2022). ArXiv abs\/2207.05501."},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095\u2010022\u20100274\u20108"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105053"},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","unstructured":"M. M.RahmanandR.Marculescu \u201cMedical Image Segmentation via Cascaded Attention Decoding \u201d2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)(2023):6211\u20136220 https:\/\/doi.org\/10.1109\/WACV56688.2023.00616.","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"e_1_2_10_19_1","first-page":"711","volume-title":"A Simple Single\u2010Scale Vision Transformer for Object Detection and Instance Segmentation","author":"Chen W.","year":"2022"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095\u2010023\u20100364\u20102"},{"key":"e_1_2_10_22_1","unstructured":"J.Yang C.Li X.Dai andJ.Gao \u201cFocal Modulation Networks \u201dProceedings of the 36th International Conference on Neural Information Processing Systems Curran Associates Inc. New Orleans LA USA (2024):304."},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","unstructured":"Y.Chen X.Dai M.Liu D.Chen L.Yuan andZ.Liu \u201cDynamic Convolution: Attention Over Convolution Kernels \u201d2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020):11027\u201311036 https:\/\/doi.org\/10.1109\/CVPR42600.2020.01104.","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"X.Li W.Wang X.Hu andJ.Yang \u201cSelective Kernel Networks \u201d2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2019):510\u2013519.","DOI":"10.1109\/CVPR.2019.00060"},{"key":"e_1_2_10_25_1","first-page":"84","volume-title":"ImageNet Classification With Deep Convolutional Neural Networks","author":"Krizhevsky A.","year":"2017"},{"key":"e_1_2_10_26_1","unstructured":"K.SimonyanandA.Zisserman \u201cVery Deep Convolutional Networks for Large\u2010Scale Image Recognition \u201d (2014). CoRR abs\/1409.1556."},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"Y.Chen X.Dai M.Liu D.Chen L.Yuan andZ.Liu \u201cDeep Residual Learning for Image Recognition \u201d2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2016):770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_28_1","doi-asserted-by":"crossref","unstructured":"S.Xie R. B.Girshick P.Doll\u00e1r Z.Tu andK.He \u201cAggregated Residual Transformations for Deep Neural Networks \u201d2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2017):5987\u20135995 https:\/\/doi.org\/10.1109\/CVPR.2017.634.","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"J.Hu L.Shen andG.Sun \u201cSqueeze\u2010and\u2010Excitation Networks \u201d2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2018):7132\u20137141 https:\/\/doi.org\/10.1109\/CVPR.2018.00745.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_10_31_1","first-page":"3","volume-title":"European Conference on Computer Vision\u20109","author":"Woo S.","year":"2018"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110553"},{"issue":"12","key":"e_1_2_10_33_1","doi-asserted-by":"crossref","first-page":"8274","DOI":"10.1109\/TPAMI.2024.3401450","article-title":"Conv2Former: A Simple Transformer\u2010Style ConvNet for Visual Recognition","volume":"46","author":"Hou Q.","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"e_1_2_10_34_1","first-page":"1","article-title":"Semi\u2010Supervised 3D Medical Image Segmentation Using Multi\u2010Consistency Learning with Fuzzy Perception\u2010Guided Target Selection","volume":"9","author":"Lei T.","year":"2024","journal-title":"IEEE Transactions on Radiation and Plasma Medical Science"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2024.3465561"},{"key":"e_1_2_10_36_1","doi-asserted-by":"crossref","unstructured":"W.Wang J.Dai andZ.Chen et al. \u201cInternImage: Exploring Large\u2010Scale Vision Foundation Models With Deformable Convolutions \u201d2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2023):14408\u201314419 https:\/\/doi.org\/10.1109\/CVPR52729.2023.01385.","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"e_1_2_10_37_1","doi-asserted-by":"crossref","unstructured":"C. F. R.Chen Q.Fan andR.Panda \u201cCrossViT: Cross\u2010Attention Multi\u2010Scale Vision Transformer for Image Classification \u201d2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(2021):347\u2013356 https:\/\/doi.org\/10.1109\/ICCV48922.2021.00041.","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"e_1_2_10_38_1","doi-asserted-by":"crossref","unstructured":"W.Xu Y.Xu T.Chang andZ.Tu \u201cCo\u2010Scale Conv\u2010Attentional Image Transformers \u201d2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(2021):9961\u20139970.","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"e_1_2_10_39_1","article-title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers, Neural Information Processing Systems","author":"Chu X.","year":"2021","journal-title":"Computer Vision and Pattern Recognition"},{"key":"e_1_2_10_40_1","volume-title":"Computer Vision and Pattern Recognition","author":"Yang J.","year":"2021"},{"key":"e_1_2_10_41_1","doi-asserted-by":"crossref","unstructured":"P.Zhang X.Dai andJ.Yang et al. \u201cMulti\u2010Scale Vision Longformer: A New Vision Transformer for High\u2010Resolution Image Encoding \u201d2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(2021):2978\u20132988 https:\/\/doi.org\/10.1109\/ICCV48922.2021.00299.","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"e_1_2_10_42_1","doi-asserted-by":"crossref","unstructured":"J.Zhang X.Li andJ.Li et al. \u201cRethinking Mobile Block for Efficient Attention\u2010Based Models \u201d2023 IEEE\/CVF International Conference on Computer Vision (ICCV)(2023):1389\u20131400 https:\/\/doi.org\/10.1109\/ICCV51070.2023.00134.","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"e_1_2_10_43_1","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1007\/978-3-031-20083-0_18","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Pan J.","year":"2022"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109204"},{"key":"e_1_2_10_45_1","first-page":"205","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Cao H.","year":"2023"},{"key":"e_1_2_10_46_1","first-page":"109","volume-title":"Computer Vision and Pattern Recognition","author":"Wang W.","year":"2021"},{"key":"e_1_2_10_47_1","first-page":"14","volume-title":"Computer Vision and Pattern Recognition","author":"Zhang Y.","year":"2021"},{"key":"e_1_2_10_48_1","doi-asserted-by":"crossref","unstructured":"H.Wu B.Xiao andN.Codella et al. \u201cCvT: Introducing Convolutions to Vision Transformers \u201d2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(2021):22\u201331 https:\/\/doi.org\/10.1109\/ICCV48922.2021.00009.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"e_1_2_10_49_1","doi-asserted-by":"crossref","unstructured":"J.Guo K.Han andH.Wu et al. \u201cCMT: Convolutional Neural Networks Meet Vision Transformers \u201d2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(2022):12165\u201312175 https:\/\/doi.org\/10.1109\/CVPR52688.2022.01186.","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"e_1_2_10_50_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.13222"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.13139"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108284"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.022"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102680"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837502"},{"key":"e_1_2_10_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_6"},{"key":"e_1_2_10_58_1","unstructured":"D.Jha N. K.Tomar V.Sharma andU.Bagci \u201cTransNetR: Transformer\u2010based Residual Network for Polyp Segmentation With Multi\u2010Center Out\u2010of\u2010Distribution Testing \u201d (2023). ArXiv abs\/2303.07428."},{"key":"e_1_2_10_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2025.105166"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70274","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70274","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T08:59:59Z","timestamp":1768381199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/ipr2.70274"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70274","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2024-10-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70274"}}