{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T03:01:03Z","timestamp":1772766063192,"version":"3.50.1"},"reference-count":49,"publisher":"Vilnius University Press","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"abstract":"<jats:p>Focusing on the problems of failing to make full use of spatial context information and limited local receptive field when U-Net is utilized to solve MRI brain tumour segmentation, a novel 3D multi-scale attention U-Net method, i.e. MAU-Net, is proposed in this paper. Firstly, a Mixed Depth-wise Convolution (MDConv) module is introduced in the encoder and decoder, which leverages various convolution kernels to extract the multi-scale features of brain tumour images, and effectively strengthens the feature expression of the brain tumour lesion region in the up and down sampling. Secondly, a Context Pyramid Module (CPM) combining multi-scale and attention is embedded in the skip connection position to achieve the combination of local feature enhancement at multi-scale with global feature correlation. Finally, MAU-Net adopts Self-ensemble in the decoding process to achieve complementary detailed features of sampled brain tumour images at different scales, thereby further improving segmentation performance. Ablation and comparison experiment results on the publicly available BraTS 2019\/2020 datasets well validate its effectiveness. It respectively achieves the Dice Similarity Coefficients (DSC) of 90.6%\/90.2%, 82.7%\/82.8%, and 77.9%\/78.5% on the whole tumour (WT), tumour core (TC) and enhanced tumour (ET) segmentation. Additionally, on the BraTS 2021 training set, the DSC for WT, TC, and ET reached 93.7%, 93.2%, and 88.9%, respectively.<\/jats:p>","DOI":"10.15388\/24-infor574","type":"journal-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T09:32:31Z","timestamp":1730280751000},"page":"751-774","source":"Crossref","is-referenced-by-count":4,"title":["MRI Brain Tumour Segmentation Using Multiscale Attention U-Net"],"prefix":"10.15388","author":[{"given":"Bonian","family":"Chen","sequence":"first","affiliation":[]},{"given":"Tao","family":"He","sequence":"additional","affiliation":[]},{"given":"Weizhuo","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yutong","family":"Han","sequence":"additional","affiliation":[]},{"given":"Jianxin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Samo","family":"Bobek","sequence":"additional","affiliation":[]},{"given":"Simona Sternad","family":"Zabukovsek","sequence":"additional","affiliation":[]}],"member":"6097","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"issue":"6","key":"2024120408521779684_j_infor574_ref_001","doi-asserted-by":"crossref","first-page":"3247","DOI":"10.1016\/j.jksuci.2022.03.022","article-title":"Single level UNet3D with multipath residual attention block for brain tumor segmentation","volume":"34","year":"2022","journal-title":"Journal of King Saud University-Computer and Information Sciences"},{"key":"2024120408521779684_j_infor574_ref_002"},{"key":"2024120408521779684_j_infor574_ref_003","article-title":"Advancing the Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features","volume":"4","year":"2017","journal-title":"Scientific Data"},{"issue":"1","key":"2024120408521779684_j_infor574_ref_004","first-page":"113","article-title":"Multi-scale structured CNN with label consistency for brain MR image segmentation","volume":"6","year":"2018","journal-title":"Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization"},{"key":"2024120408521779684_j_infor574_ref_005","article-title":"DPAFNet: a residual dual-path attention-fusion convolutional neural network for multimodal brain tumor segmentation","volume":"79","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"key":"2024120408521779684_j_infor574_ref_006","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.neuroimage.2017.04.041","article-title":"VoxResNet: deep voxelwise residual networks for brain segmentation from 3D MR images","volume":"170","year":"2018","journal-title":"NeuroImage"},{"key":"2024120408521779684_j_infor574_ref_007","first-page":"424","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016","volume":"9901","year":"2016"},{"key":"2024120408521779684_j_infor574_ref_008","first-page":"274","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","volume":"12658","year":"2021"},{"key":"2024120408521779684_j_infor574_ref_009","volume-title":"International Conference on Learning Representations","year":"2020"},{"key":"2024120408521779684_j_infor574_ref_010","first-page":"241","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","volume":"12659","year":"2021"},{"key":"2024120408521779684_j_infor574_ref_011","first-page":"315","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","volume":"11992","year":"2020"},{"key":"2024120408521779684_j_infor574_ref_012","first-page":"574","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","year":"2022"},{"issue":"1","key":"2024120408521779684_j_infor574_ref_013","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1053\/j.semnuclmed.2016.09.004","article-title":"Brain tumors: an update on clinical PET research in gliomas","volume":"47","year":"2017","journal-title":"Seminars in Nuclear Medicine"},{"key":"2024120408521779684_j_infor574_ref_014","first-page":"7132","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","year":"2018"},{"key":"2024120408521779684_j_infor574_ref_015","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.neucom.2017.12.032","article-title":"Segmentation of glioma tumors in brain using deep convolutional neural network","volume":"282","year":"2018","journal-title":"Neurocomputing"},{"key":"2024120408521779684_j_infor574_ref_016","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.procs.2016.09.407","article-title":"Review of MRI-based brain tumor image segmentation using deep learning methods","volume":"102","year":"2016","journal-title":"Procedia Computer Science"},{"key":"2024120408521779684_j_infor574_ref_017","article-title":"Two-branch network for brain tumor segmentation using attention mechanism and super-resolution reconstruction","volume":"157","year":"2023","journal-title":"Computers in Biology and Medicine"},{"issue":"6","key":"2024120408521779684_j_infor574_ref_018","doi-asserted-by":"crossref","first-page":"797","DOI":"10.3390\/brainsci12060797","article-title":"SwinBTS: a method for 3D multimodal brain tumor segmentation using swin transformer","volume":"12","year":"2022","journal-title":"Brain Sciences"},{"key":"2024120408521779684_j_infor574_ref_019","first-page":"183","volume":"12658","year":"2021"},{"key":"2024120408521779684_j_infor574_ref_020","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation","volume":"36","year":"2017","journal-title":"Medical Image Analysis"},{"key":"2024120408521779684_j_infor574_ref_021","first-page":"6399","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","year":"2019"},{"issue":"3","key":"2024120408521779684_j_infor574_ref_022","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1007\/s11517-023-02965-1","article-title":"mResU-Net: multi-scale residual U-Net-based brain tumor segmentation from multimodal MRI","volume":"62","year":"2024","journal-title":"Medical & Biological Engineering & Computing"},{"key":"2024120408521779684_j_infor574_ref_023","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1109\/YAC63405.2024.10598552","volume-title":"2024 39th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","year":"2024"},{"issue":"7","key":"2024120408521779684_j_infor574_ref_024","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.1109\/TMI.2021.3065918","article-title":"CANet: context aware network for brain glioma segmentation","volume":"40","year":"2021","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"2024120408521779684_j_infor574_ref_025","first-page":"10012","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","year":"2021"},{"key":"2024120408521779684_j_infor574_ref_026","doi-asserted-by":"crossref","first-page":"3431","DOI":"10.1109\/CVPR.2015.7298965","volume-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2015"},{"issue":"10","key":"2024120408521779684_j_infor574_ref_027","first-page":"1993","article-title":"The multimodal brain tumor image segmentation benchmark (BRATS)","volume":"34","year":"2014","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"2024120408521779684_j_infor574_ref_028","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1109\/3DV.2016.79","volume-title":"2016 Fourth International Conference on 3D Vision (3DV)","year":"2016"},{"key":"2024120408521779684_j_infor574_ref_029","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1007\/978-3-031-16443-9_16","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022","volume":"13435","year":"2022"},{"key":"2024120408521779684_j_infor574_ref_030","first-page":"56","volume-title":"MICCAI Multimodal Brain Tumor Segmentation Challenge (BraTS)","year":"2015"},{"key":"2024120408521779684_j_infor574_ref_031","first-page":"234","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015","volume":"9351","year":"2015"},{"key":"2024120408521779684_j_infor574_ref_032","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"2024120408521779684_j_infor574_ref_033","first-page":"4510","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2018"},{"key":"2024120408521779684_j_infor574_ref_034"},{"key":"2024120408521779684_j_infor574_ref_035","first-page":"2820","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2019"},{"key":"2024120408521779684_j_infor574_ref_036","first-page":"31","volume-title":"MICCAI BraTS (Brain Tumor Segmentation) Challenge. Proceedings, Winning Contribution","year":"2014"},{"issue":"10","key":"2024120408521779684_j_infor574_ref_037","doi-asserted-by":"crossref","first-page":"4129","DOI":"10.1007\/s00330-017-4789-9","article-title":"Diagnostic accuracy of magnetic resonance imaging techniques for treatment response evaluation in patients with high-grade glioma, a systematic review and meta-analysis","volume":"27","year":"2017","journal-title":"European Radiology"},{"key":"2024120408521779684_j_infor574_ref_038","article-title":"MRI brain tumor segmentation using residual Spatial Pyramid Pooling-powered 3D U-Net","volume":"11","year":"2023","journal-title":"Frontiers in Public Health"},{"key":"2024120408521779684_j_infor574_ref_039","first-page":"412","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","volume":"12658","year":"2021"},{"key":"2024120408521779684_j_infor574_ref_040","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.neucom.2019.01.103","article-title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","volume":"338","year":"2019","journal-title":"Neurocomputing"},{"key":"2024120408521779684_j_infor574_ref_041","first-page":"109","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24","year":"2021"},{"key":"2024120408521779684_j_infor574_ref_042","doi-asserted-by":"crossref","first-page":"7794","DOI":"10.1109\/CVPR.2018.00813","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","year":"2018"},{"issue":"4","key":"2024120408521779684_j_infor574_ref_043","doi-asserted-by":"crossref","first-page":"6315","DOI":"10.1609\/aaai.v34i04.6100","article-title":"Non-local U-Nets for biomedical image segmentation","volume":"34","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2024120408521779684_j_infor574_ref_044","first-page":"3","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","year":"2018"},{"key":"2024120408521779684_j_infor574_ref_045"},{"key":"2024120408521779684_j_infor574_ref_046","first-page":"6848","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","year":"2018"},{"key":"2024120408521779684_j_infor574_ref_047","first-page":"210","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","volume":"11992","year":"2020"},{"issue":"6","key":"2024120408521779684_j_infor574_ref_048","first-page":"1856","article-title":"UNet++: redesigning skip connections to exploit multiscale features in image segmentation","volume":"39","year":"2019","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"2014","key":"2024120408521779684_j_infor574_ref_049","first-page":"36","article-title":"Segmentation of brain tumor tissues with convolutional neural networks","volume":"36","year":"2014","journal-title":"Proceedings MICCAI-BRATS"}],"container-title":["Informatica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/informatica.vu.lt\/journal\/INFORMATICA\/article\/1353\/text","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/informatica.vu.lt\/journal\/INFORMATICA\/article\/1353\/text","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T07:04:49Z","timestamp":1733295889000},"score":1,"resource":{"primary":{"URL":"https:\/\/informatica.vu.lt\/doi\/10.15388\/24-INFOR574"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":49,"alternative-id":["10.15388\/24-INFOR574"],"URL":"https:\/\/doi.org\/10.15388\/24-infor574","relation":{},"ISSN":["0868-4952","1822-8844"],"issn-type":[{"value":"0868-4952","type":"print"},{"value":"1822-8844","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}