{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T06:00:30Z","timestamp":1787032830743,"version":"build-2736575974"},"reference-count":45,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of the Xinjiang Uygur Autonomous Region","award":["2022D01C184 and 2022D01C436"],"award-info":[{"award-number":["2022D01C184 and 2022D01C436"]}]},{"name":"Project of Top-notch Talents of Technological Youth of Xinjiang","award":["2023TSYCCX0067"],"award-info":[{"award-number":["2023TSYCCX0067"]}]},{"name":"Natural Science Foundation of the Xinjiang Uygur Autonomous Region, China","award":["2022D01A311"],"award-info":[{"award-number":["2022D01A311"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Pancreatic cancer, as a highly lethal malignant tumor, presents significant challenges for early diagnosis and treatment. Accurate segmentation of the pancreas and tumors is crucial for surgical planning and treatment strategy development. However, due to the variable morphology, blurred boundaries, and low contrast with surrounding tissues in CT images, traditional manual segmentation methods are inefficient and heavily reliant on expert experience. To address this challenge, this study proposes a lightweight automated 3D segmentation algorithm\u2014Multi-Dimensional Decoupled Multi-Scale U-Net (MDMU-Net). First, depthwise separable convolution is employed to reduce model complexity. Second, a multi-dimensional decoupled multi-scale module is designed as the primary encoder module, which independently extracts features along depth, height, and width dimensions through parallel multi-scale convolutional kernels, achieving fine-grained modeling of complex anatomical structures. Finally, cross-dimensional channel and spatial attention mechanisms are introduced to enhance recognition capability for small tumors and blurred boundaries. Experimental results on the MSDPT and NIHP datasets demonstrate that MDMU-Net exhibits competitive advantages in both pancreatic segmentation DSC (0.7108\/0.7709) and tumor segmentation DSC (showing an 11.8% improvement over AttentionUNet), while achieving a 15.3% enhancement in HD95 boundary accuracy compared to 3DUX-Net. While maintaining clinically viable precision, the model significantly improves computational efficiency, with parameter count (26.97M) and FLOPs (84.837G) reduced by 65.5% and 71%, respectively, compared to UNETR, providing reliable algorithmic support for precise diagnosis and treatment of pancreatic cancer.<\/jats:p>","DOI":"10.7717\/peerj-cs.3059","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T08:26:06Z","timestamp":1754555166000},"page":"e3059","source":"Crossref","is-referenced-by-count":2,"title":["MDMU-Net: 3D multi-dimensional decoupled multi-scale U-Net for pancreatic cancer segmentation"],"prefix":"10.7717","volume":"11","author":[{"given":"Lian","family":"Lu","sequence":"first","affiliation":[{"name":"College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"},{"name":"Institute of Medical Engineering Interdisciplinary Research, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"},{"name":"Institute of Medical Engineering Interdisciplinary Research, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gan","family":"Sen","sequence":"additional","affiliation":[{"name":"College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"},{"name":"Institute of Medical Engineering Interdisciplinary Research, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"},{"name":"Institute of Medical Engineering Interdisciplinary Research, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"},{"name":"Institute of Medical Engineering Interdisciplinary Research, Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2025,8,7]]},"reference":[{"key":"10.7717\/peerj-cs.3059\/ref-1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.06955","article-title":"Recurrent residual convolutional neural network based on U-Net (R2U-Net) for medical image segmentation","author":"Alom","year":"2018"},{"key":"10.7717\/peerj-cs.3059\/ref-2","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1016\/j.surg.2014.02.001","article-title":"Borderline resectable pancreatic cancer: a consensus statement by the International Study Group of Pancreatic Surgery (ISGPS)","volume":"155","author":"Bockhorn","year":"2014","journal-title":"Surgery"},{"key":"10.7717\/peerj-cs.3059\/ref-3","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/978-3-031-25066-8_9","article-title":"Swin-Unet: unet-like pure transformer for medical image segmentation","volume-title":"Computer Vision\u2014ECCV, 2022 Workshops","author":"Cao","year":"2023"},{"key":"10.7717\/peerj-cs.3059\/ref-4","doi-asserted-by":"publisher","first-page":"5019","DOI":"10.1002\/mp.13159","article-title":"CT radiomics to predict high-risk intraductal papillary mucinous neoplasms of the pancreas","volume":"45","author":"Chakraborty","year":"2018","journal-title":"Medical Physics"},{"key":"10.7717\/peerj-cs.3059\/ref-5","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1007\/s11831-023-10032-z","article-title":"Review of lightweight deep convolutional neural networks","volume":"31","author":"Chen","year":"2024a","journal-title":"Archives of Computational Methods in Engineering"},{"key":"10.7717\/peerj-cs.3059\/ref-6","first-page":"184","article-title":"3D dilated multi-fiber network for real-time brain tumor segmentation in MRI","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2019","author":"Chen","year":"2019"},{"key":"10.7717\/peerj-cs.3059\/ref-7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306","article-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"10.7717\/peerj-cs.3059\/ref-8","doi-asserted-by":"publisher","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","year":"2024b","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.3059\/ref-9","doi-asserted-by":"publisher","first-page":"107208","DOI":"10.1016\/j.compbiomed.2023.107208","article-title":"MS-FANet: multi-scale feature attention network for liver tumor segmentation","volume":"163","author":"Chen","year":"2023","journal-title":"Computers in Biology and Medicine"},{"key":"10.7717\/peerj-cs.3059\/ref-10","first-page":"424","article-title":"3D U-Net: learning dense volumetric segmentation from sparse annotation","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2016","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"10.7717\/peerj-cs.3059\/ref-11","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.ejca.2015.12.026","article-title":"Current standards and new innovative approaches for treatment of pancreatic cancer","volume":"57","author":"Conroy","year":"2016","journal-title":"European Journal of Cancer"},{"key":"10.7717\/peerj-cs.3059\/ref-12","doi-asserted-by":"publisher","first-page":"e0210758","DOI":"10.1371\/journal.pone.0210758","article-title":"Computed tomography based radiomic signature as predictive of survival and local control after stereotactic body radiation therapy in pancreatic carcinoma","volume":"14","author":"Cozzi","year":"2019","journal-title":"PLOS ONE"},{"key":"10.7717\/peerj-cs.3059\/ref-13","doi-asserted-by":"publisher","first-page":"v56","DOI":"10.1093\/annonc\/mdv295","article-title":"Cancer of the pancreas: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up\u2020","volume":"26","author":"Ducreux","year":"2015","journal-title":"Annals of Oncology"},{"key":"10.7717\/peerj-cs.3059\/ref-14","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/978-3-031-09002-8_2","article-title":"Optimized U-Net for brain tumor segmentation","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","author":"Futrega","year":"2022"},{"key":"10.7717\/peerj-cs.3059\/ref-15","first-page":"1230","article-title":"Deep LOGISMOS: deep learning graph-based 3D segmentation of pancreatic tumors on CT scans","author":"Guo","year":"2018"},{"key":"10.7717\/peerj-cs.3059\/ref-16","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/978-3-031-08999-2_22","article-title":"Swin UNETR: swin transformers for semantic segmentation of brain tumors in MRI images","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","author":"Hatamizadeh","year":"2022a"},{"key":"10.7717\/peerj-cs.3059\/ref-17","first-page":"1748","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022b"},{"key":"10.7717\/peerj-cs.3059\/ref-18","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.7717\/peerj-cs.3059\/ref-19","doi-asserted-by":"publisher","first-page":"106838","DOI":"10.1016\/j.compbiomed.2023.106838","article-title":"RMAU-Net: residual multi-scale attention U-Net for liver and tumor segmentation in CT images","volume":"158","author":"Jiang","year":"2023","journal-title":"Computers in Biology and Medicine"},{"key":"10.7717\/peerj-cs.3059\/ref-20","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1016\/j.bbe.2020.07.007","article-title":"A deep residual U-Net convolutional neural network for automated lung segmentation in computed tomography images","volume":"40","author":"Khanna","year":"2020","journal-title":"Biocybernetics and Biomedical Engineering"},{"key":"10.7717\/peerj-cs.3059\/ref-21","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.7717\/peerj-cs.3059\/ref-22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.15076","article-title":"3D UX-Net: a large kernel volumetric convnet modernizing hierarchical transformer for medical image segmentation","author":"Lee","year":"2022"},{"key":"10.7717\/peerj-cs.3059\/ref-23","first-page":"9992","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.7717\/peerj-cs.3059\/ref-24","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1109\/JBHI.2020.2998146","article-title":"HDC-Net: hierarchical decoupled convolution network for brain tumor segmentation","volume":"25","author":"Luo","year":"2021","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.7717\/peerj-cs.3059\/ref-25","first-page":"5694","article-title":"Rewrite the stars","author":"Ma","year":"2024"},{"key":"10.7717\/peerj-cs.3059\/ref-26","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1007\/978-3-030-11726-9_28","article-title":"3D MRI brain tumor segmentation using autoencoder regularization","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","author":"Myronenko","year":"2019"},{"key":"10.7717\/peerj-cs.3059\/ref-27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.03999","article-title":"Attention U-Net: learning where to look for the pancreas","author":"Oktay","year":"2018"},{"key":"10.7717\/peerj-cs.3059\/ref-28","doi-asserted-by":"publisher","first-page":"343","DOI":"10.3978\/j.issn.2078-6891.2015.024","article-title":"Imaging preoperatively for pancreatic adenocarcinoma","volume":"6","author":"Pietryga","year":"2015","journal-title":"Journal of Gastrointestinal Oncology"},{"key":"10.7717\/peerj-cs.3059\/ref-29","doi-asserted-by":"publisher","first-page":"2913","DOI":"10.1158\/0008-5472.Can-14-0155","article-title":"Projecting cancer incidence and deaths to 2030: the unexpected burden of thyroid, liver, and pancreas cancers in the United States","volume":"74","author":"Rahib","year":"2014","journal-title":"Cancer Research"},{"key":"10.7717\/peerj-cs.3059\/ref-30","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"10.7717\/peerj-cs.3059\/ref-31","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3322\/caac.21442","article-title":"Cancer statistics, 2018","volume":"68","author":"Siegel","year":"2018","journal-title":"CA: A Cancer Journal for Clinicians"},{"key":"10.7717\/peerj-cs.3059\/ref-32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.7717\/peerj-cs.3059\/ref-33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.09063","article-title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","author":"Simpson","year":"2019"},{"key":"10.7717\/peerj-cs.3059\/ref-34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"Szegedy","year":"2017"},{"key":"10.7717\/peerj-cs.3059\/ref-35","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.7717\/peerj-cs.3059\/ref-36","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","article-title":"CBAM: convolutional block attention module","volume-title":"Computer Vision\u2014ECCV 2018","author":"Woo","year":"2018"},{"key":"10.7717\/peerj-cs.3059\/ref-37","doi-asserted-by":"publisher","first-page":"107733","DOI":"10.1016\/j.asoc.2021.107733","article-title":"MSMANet: a multi-scale mesh aggregation network for brain tumor segmentation","volume":"110","author":"Zhang","year":"2021b","journal-title":"Applied Soft Computing"},{"key":"10.7717\/peerj-cs.3059\/ref-38","doi-asserted-by":"publisher","first-page":"105395","DOI":"10.1016\/j.cmpb.2020.105395","article-title":"DENSE-INception U-net for medical image segmentation","volume":"192","author":"Zhang","year":"2020","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"10.7717\/peerj-cs.3059\/ref-39","doi-asserted-by":"publisher","first-page":"101884","DOI":"10.1016\/j.media.2020.101884","article-title":"A deep learning framework for pancreas segmentation with multi-atlas registration and 3D level-set","volume":"68","author":"Zhang","year":"2021c","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.3059\/ref-40","doi-asserted-by":"publisher","first-page":"107762","DOI":"10.1016\/j.patcog.2020.107762","article-title":"Automatic pancreas segmentation based on lightweight DCNN modules and spatial prior propagation","volume":"114","author":"Zhang","year":"2021a","journal-title":"Pattern Recognition"},{"key":"10.7717\/peerj-cs.3059\/ref-41","doi-asserted-by":"publisher","first-page":"4036","DOI":"10.1109\/TIP.2023.3293771","article-title":"nnFormer: volumetric medical image segmentation via a 3D transformer","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.7717\/peerj-cs.3059\/ref-42","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","article-title":"UNet++: a nested U-Net architecture for medical image segmentation","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"Zhou","year":"2018"},{"key":"10.7717\/peerj-cs.3059\/ref-43","first-page":"693","article-title":"A fixed-point model for pancreas segmentation in abdominal CT scans","volume-title":"Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2017","author":"Zhou","year":"2017"},{"key":"10.7717\/peerj-cs.3059\/ref-44","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1186\/s12916-018-1215-3","article-title":"Pancreatic cancer: challenges and opportunities","volume":"16","author":"Zhu","year":"2018a","journal-title":"BMC Medicine"},{"key":"10.7717\/peerj-cs.3059\/ref-45","first-page":"682","article-title":"A 3D coarse-to-fine framework for volumetric medical image segmentation","author":"Zhu","year":"2018b"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3059.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3059.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3059.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3059.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T08:26:13Z","timestamp":1754555173000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"references-count":45,"alternative-id":["10.7717\/peerj-cs.3059"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3059","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,7]]},"article-number":"e3059"}}