{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T08:29:13Z","timestamp":1771748953868,"version":"3.50.1"},"reference-count":35,"publisher":"World Scientific Pub Co Pte Ltd","issue":"01","funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100201"],"award-info":[{"award-number":["2018AAA0100201"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61906127"],"award-info":[{"award-number":["61906127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Neur. Syst."],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p> Three-dimensional (3D) medical image segmentation plays a crucial role in medical care applications. Although various two-dimensional (2D) and 3D neural network models have been applied to 3D medical image segmentation and achieved impressive results, a trade-off remains between efficiency and accuracy. To address this issue, a novel mixture convolutional network (MixConvNet) is proposed, in which traditional 2D\/3D convolutional blocks are replaced with novel MixConv blocks. In the MixConv block, 3D convolution is decomposed into a mixture of 2D convolutions from different views. Therefore, the MixConv block fully utilizes the advantages of 2D convolution and maintains the learning ability of 3D convolution. It acts as 3D convolutions and thus can process volumetric input directly and learn intra-slice features, which are absent in the traditional 2D convolutional block. By contrast, the proposed MixConv block only contains 2D convolutions; hence, it has significantly fewer trainable parameters and less computation budget than a block containing 3D convolutions. Furthermore, the proposed MixConvNet is pre-trained with small input patches and fine-tuned with large input patches to improve segmentation performance further. In experiments on the Decathlon Heart dataset and Sliver07 dataset, the proposed MixConvNet outperformed the state-of-the-art methods such as UNet3D, VNet, and nnUnet. <\/jats:p>","DOI":"10.1142\/s0129065722500599","type":"journal-article","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T12:18:07Z","timestamp":1663330687000},"source":"Crossref","is-referenced-by-count":31,"title":["Mixture 2D Convolutions for 3D Medical Image Segmentation"],"prefix":"10.1142","volume":"33","author":[{"given":"Jianyong","family":"Wang","sequence":"first","affiliation":[{"name":"Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu, Sichuan, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu, Sichuan, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu, Sichuan, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"issue":"2","key":"S0129065722500599BIB001","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"Isensee F.","year":"2021","journal-title":"Nat. Methods"},{"key":"S0129065722500599BIB002","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.05.001"},{"issue":"04","key":"S0129065722500599BIB003","doi-asserted-by":"crossref","first-page":"2250016","DOI":"10.1142\/S0129065722500162","volume":"32","author":"Hua Y.","year":"2022","journal-title":"Int. J. Neural Syst."},{"key":"S0129065722500599BIB004","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2015","author":"Ronneberger O.","year":"2015"},{"key":"S0129065722500599BIB005","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1109\/3DV.2016.79","volume-title":"2016 4th Int. Conf. on 3D Vision (3DV)","author":"Milletari F.","year":"2016"},{"key":"S0129065722500599BIB007","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/978-3-030-87193-2_25","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2014 MICCAI 2021","author":"Li L.","year":"2021"},{"issue":"2","key":"S0129065722500599BIB008","doi-asserted-by":"crossref","first-page":"782","DOI":"10.3390\/app11020782","volume":"11","author":"Comelli A.","year":"2021","journal-title":"Appl. Sci."},{"issue":"12","key":"S0129065722500599BIB010","doi-asserted-by":"crossref","first-page":"6377","DOI":"10.1002\/mp.12602","volume":"44","author":"Men K.","year":"2017","journal-title":"Med. Phys."},{"key":"S0129065722500599BIB011","doi-asserted-by":"crossref","first-page":"101666","DOI":"10.1016\/j.media.2020.101666","volume":"61","author":"He T.","year":"2020","journal-title":"Med. Image Anal."},{"key":"S0129065722500599BIB012","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.neucom.2020.11.028","volume":"427","author":"Hu J.","year":"2021","journal-title":"Neurocomputing"},{"key":"S0129065722500599BIB013","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1007\/978-3-319-46723-8_49","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2016","author":"\u00c7i\u00e7ek \u00d6.","year":"2016"},{"key":"S0129065722500599BIB014","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.04.041"},{"key":"S0129065722500599BIB015","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1007\/978-3-319-24553-9_68","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2014 MICCAI 2015","volume":"9349","author":"Roth H. R.","year":"2015"},{"key":"S0129065722500599BIB016","first-page":"3044","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Chen J.","year":"2016"},{"key":"S0129065722500599BIB017","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1007\/978-3-030-00937-3_51","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2014 MICCAI 2018","author":"Xia Y.","year":"2018"},{"key":"S0129065722500599BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2845918"},{"key":"S0129065722500599BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2013851"},{"key":"S0129065722500599BIB021","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"S0129065722500599BIB022","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12494"},{"key":"S0129065722500599BIB023","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12647"},{"key":"S0129065722500599BIB024","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.ebiom.2018.08.033","volume":"35","author":"Wang J.","year":"2018","journal-title":"EBioMedicine"},{"issue":"05","key":"S0129065722500599BIB025","doi-asserted-by":"crossref","first-page":"1850060","DOI":"10.1142\/S0129065718500600","volume":"30","author":"Lin L.-C.","year":"2020","journal-title":"Int. J. Neural Syst."},{"key":"S0129065722500599BIB026","doi-asserted-by":"publisher","DOI":"10.1515\/revneuro-2020-0043"},{"key":"S0129065722500599BIB027","doi-asserted-by":"publisher","DOI":"10.1159\/000512985"},{"key":"S0129065722500599BIB028","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065719500242"},{"issue":"09","key":"S0129065722500599BIB029","doi-asserted-by":"crossref","first-page":"2050045","DOI":"10.1142\/S0129065720500458","volume":"30","author":"Lozano A.","year":"2020","journal-title":"Int. J. Neural Syst."},{"key":"S0129065722500599BIB030","doi-asserted-by":"publisher","DOI":"10.1515\/revneuro-2018-0050"},{"key":"S0129065722500599BIB031","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"S0129065722500599BIB032","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"S0129065722500599BIB033","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"S0129065722500599BIB034","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"S0129065722500599BIB036","first-page":"S09252312210173","volume":"488","author":"Wang J.","year":"2021","journal-title":"Neurocomputing"},{"key":"S0129065722500599BIB037","first-page":"1","volume-title":"3rd Int. Conf. Learning Representations","author":"Simonyan K.","year":"2015"},{"key":"S0129065722500599BIB038","doi-asserted-by":"crossref","first-page":"1451","DOI":"10.1109\/TMI.2006.880587","volume":"25","author":"Crum W. R.","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"3","key":"S0129065722500599BIB039","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1148\/radiol.2019182012","volume":"291","author":"Lin L.","year":"2019","journal-title":"Radiology"}],"container-title":["International Journal of Neural Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0129065722500599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T05:52:11Z","timestamp":1673848331000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0129065722500599"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,4]]},"references-count":35,"journal-issue":{"issue":"01","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1142\/S0129065722500599"],"URL":"https:\/\/doi.org\/10.1142\/s0129065722500599","relation":{},"ISSN":["0129-0657","1793-6462"],"issn-type":[{"value":"0129-0657","type":"print"},{"value":"1793-6462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,4]]},"article-number":"2250059"}}