{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T00:39:11Z","timestamp":1792802351783,"version":"4.5.0"},"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Leading Talents of Science and Technology Innovation in Zhejiang Province","award":["2020R52042"],"award-info":[{"award-number":["2020R52042"]}]},{"name":"Zhejiang-Netherlands Joint Laboratory for Digital Diagnosis and Treatment of oral diseases","award":["2021C01189"],"award-info":[{"award-number":["2021C01189"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82011530399"],"award-info":[{"award-number":["82011530399"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LGG20F020015"],"award-info":[{"award-number":["LGG20F020015"]}],"id":[{"id":"https:\/\/ror.org\/04aqat463","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>\n                    In modern medical imaging-assisted therapies, manual annotation is commonly employed for liver and tumor segmentation in abdominal CT images. However, this approach suffers from low efficiency and poor accuracy. With the development of deep learning, automatic liver tumor segmentation algorithms based on neural networks have emerged, for the improvement of the work efficiency. However, existing liver tumor segmentation algorithms still have several limitations: (1) they often encounter the common issue of class imbalance in liver tumor segmentation tasks, where the tumor region is significantly smaller than the normal tissue region, causing models to predict more negative samples and neglect the tumor region; (2) they fail to adequately consider feature fusion between global contexts, leading to the loss of crucial information; (3) they exhibit weak perception of local details such as fuzzy boundaries, irregular shapes, and small lesions, thereby failing to capture important features. To address these issues, we propose a Multi-Axis Attention Conditional Generative Adversarial Network, referred to as MA-cGAN. Firstly, we propose the Multi-Axis attention mechanism (MA) that projects three-dimensional CT images along different axes to extract two-dimensional features. The features from different axes are then fused by using learnable factors to capture key information from different directions. Secondly, the MA is incorporated into a U-shaped segmentation network as the generator to enhance its ability to extract detailed features. Thirdly, a conditional generative adversarial network is built by combining a discriminator and a generator to enhance the stability and accuracy of the generator\u2019s segmentation results. The MA-cGAN was trained and tested on the LiTS public dataset for the liver and tumor segmentation challenge. Experimental results show that MA-cGAN improves the Dice coefficient, Hausdorff distance, average surface distance, and other metrics compared to the state-of-the-art segmentation models. The segmented liver and tumor models have clear edges, fewer false positive regions, and are closer to the true labels, which plays an active role in medical adjuvant therapy. The source code with our proposed model are available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/jhliao0525\/MA-cGAN.git\" xlink:type=\"simple\">\n                      <jats:italic>https<\/jats:italic>\n                      :\n                      <jats:italic>\/\/github<\/jats:italic>\n                      .\n                      <jats:italic>com\/jhliao0525\/MA-cGAN<\/jats:italic>\n                      .\n                      <jats:italic>git<\/jats:italic>\n                    <\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0312105","type":"journal-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T13:35:21Z","timestamp":1733232921000},"page":"e0312105","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["Liver tumor segmentation method combining multi-axis attention and conditional generative adversarial networks"],"prefix":"10.1371","volume":"19","author":[{"given":"Jiahao","family":"Liao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1340-398X","authenticated-orcid":true,"given":"Hanjie","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghui","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"issue":"6","key":"pone.0312105.ref001","first-page":"394","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J].","volume":"201868","author":"F Bray","journal-title":"CA: a cancer journal for clinicians"},{"issue":"05","key":"pone.0312105.ref002","first-page":"584","article-title":"Cancer statistics in China and United States, 2022: profiles, trends, and determinants[J].","volume":"2022135","author":"C Xia","journal-title":"Chinese medical journal"},{"issue":"3","key":"pone.0312105.ref003","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1148\/radiol.2403050850","article-title":"Automated hepatic volumetry for living related liver transplantation at multisection CT [J].","volume":"240","author":"Y Nakayama","year":"2006","journal-title":"Radiology"},{"issue":"2","key":"pone.0312105.ref004","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1504\/IJCAT.2018.091642","article-title":"Research on the image segmentation of icing line based on NSCT and 2D OSTU [J]","volume":"57","author":"L Qi","year":"2018","journal-title":"International Journal of Computer Applications in Technology"},{"issue":"3","key":"pone.0312105.ref005","doi-asserted-by":"crossref","first-page":"1355","DOI":"10.1109\/TIP.2016.2621670","article-title":"Fast threshold image segmentation based on 2D fuzzy fisher and random local optimized QPSO [J]","volume":"26","author":"C Zhang","year":"2016","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"pone.0312105.ref006","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1109\/TLA.2015.7069113","article-title":"Improving parameters selection of a seeded region growing method for multiband image segmentation [J].","volume":"13","author":"S Hernandez J","year":"2015","journal-title":"IEEE Latin America Transactions"},{"issue":"24","key":"pone.0312105.ref007","doi-asserted-by":"crossref","first-page":"5427","DOI":"10.1080\/01431160600944010","article-title":"Improving edge detection and watershed segmentation with anisotropic diffusion and morphological levellings [J]","volume":"27","author":"K Karantzalos","year":"2006","journal-title":"International Journal of Remote Sensing"},{"key":"pone.0312105.ref008","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis [J]","volume":"42","author":"G Litjens","year":"2017","journal-title":"Medical image analysis"},{"key":"pone.0312105.ref009","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep learning in medical image analysis[J]","volume":"19","author":"D Shen","year":"2017","journal-title":"Annual review of biomedical engineering"},{"key":"pone.0312105.ref010","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]\/\/Medical Image Computing and Computer-Assisted 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":"pone.0312105.ref011","unstructured":"Oktay O, Schlemper J, Folgoc L L, et al. Attention u-net: Learning where to look for the pancreas [J]. arXiv preprint arXiv:180403999, 2018. Available from: https:\/\/arxiv.org\/abs\/1804.03999"},{"key":"pone.0312105.ref012","unstructured":"Li, C., Wang, X., Eberl, S., et al. (2017). \"Residual U-Net for Biomedical Image Segmentation.\" In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), pages 372\u2013380. Springer, 2017."},{"key":"pone.0312105.ref013","first-page":"30","article-title":"Attention is all you need [J]","author":"A Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pone.0312105.ref014","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding.","author":"Jacob Devlin","year":"1810"},{"key":"pone.0312105.ref015","article-title":"Antoine Vial-Aussavy, and Anshumali Shri-vastava. Raw nav-merge seismic data to subsurface properties with mlp based multi-modal information unscrambler","author":"Aditya Desai","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"pone.0312105.ref016","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale [J].","author":"A Dosovitskiy","journal-title":"arXiv"},{"key":"pone.0312105.ref017","unstructured":"Jieneng Chen, Y ongyi Lu, Qihang Y u, Xiangde Luo, Ehsan Adeli, Yan Wang, et al. Transunet: Transformers make strong encoders for medical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI),2021."},{"key":"pone.0312105.ref018","doi-asserted-by":"crossref","unstructured":"Gao Y, Zhou M, Metaxas D N. UTNet: a hybrid transformer architecture for medical image segmentation[C]\/\/Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part III 24. Springer International Publishing, 2021: 61\u201371.","DOI":"10.1007\/978-3-030-87199-4_6"},{"key":"pone.0312105.ref019","doi-asserted-by":"crossref","unstructured":"Wang W, Chen C, Ding M, et al. Transbts: Multimodal brain tumor segmentation using transformer[C]\/\/Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part I 24. Springer International Publishing, 2021: 109\u2013119.","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"pone.0312105.ref020","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Tang Y, Nath V, et al. Unetr: Transformers for 3d medical image segmentation[C]\/\/Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 2022: 574\u2013584.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"pone.0312105.ref021","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]\/\/Proceedings of the IEEE\/CVF international conference on computer vision. 2021: 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0312105.ref022","doi-asserted-by":"crossref","unstructured":"Tang Y, Yang D, Li W, et al. Self-supervised pre-training of swin transformers for 3d medical image analysis[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022: 20730\u201320740.","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"pone.0312105.ref023","article-title":"U-Netmer: U-Net meets Transformer for medical image segmentation[J].","author":"S He","journal-title":"arXiv preprint"},{"issue":"3","key":"pone.0312105.ref024","doi-asserted-by":"crossref","first-page":"3381","DOI":"10.1007\/s10489-022-03682-2","article-title":"An innovative medical image synthesis based on dual GAN deep neural networks for improved segmentation quality [J].","volume":"53","author":"A Beji","year":"2023","journal-title":"Applied Intelligence"},{"key":"pone.0312105.ref025","doi-asserted-by":"crossref","first-page":"107119","DOI":"10.1016\/j.compbiomed.2023.107119","article-title":"MedGAN: An adaptive GAN approach for medical image generation [J]","volume":"163","author":"K Guo","year":"2023","journal-title":"Computers in Biology and Medicine"},{"key":"pone.0312105.ref026","doi-asserted-by":"crossref","first-page":"107457","DOI":"10.1016\/j.engappai.2023.107457","article-title":"Dual attention and channel transformer based generative adversarial network for restoration of the damaged artwork[J]","volume":"128","author":"P Kumar","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"pone.0312105.ref027","doi-asserted-by":"crossref","first-page":"104791","DOI":"10.1016\/j.bspc.2023.104791","article-title":"Transformers in medical image segmentation: A review[J].","volume":"84","author":"H Xiao","year":"2023","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0312105.ref028","article-title":"nnformer: Volumetric medical image segmentation via a 3d transformer[J]","author":"Y Zhou H","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"issue":"6","key":"pone.0312105.ref029","doi-asserted-by":"crossref","first-page":"6030","DOI":"10.1609\/aaai.v38i6.28418","article-title":"Medsegdiff-v2: Diffusion-based medical image segmentation with transformer[C]\/\/","volume":"38","author":"J Wu","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"11","key":"pone.0312105.ref030","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks [J]","volume":"63","author":"I Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"key":"pone.0312105.ref031","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J Y. Zhou T, et al. Image-to-image translation with conditional adversarial networks[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"pone.0312105.ref032","doi-asserted-by":"crossref","unstructured":"Yang D, Xu D, Zhou S K, et al. Automatic liver segmentation using an adversarial image-to-image network[C]\/\/Medical Image Computing and Computer Assisted Intervention\u2212 MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11\u201313, 2017, Proceedings, Part III 20. Springer International Publishing, 2017: 507\u2013515.","DOI":"10.1007\/978-3-319-66179-7_58"},{"key":"pone.0312105.ref033","article-title":"Improved techniques for training gans","author":"Tim Salimans","year":"2016","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"pone.0312105.ref034","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek \u00d6, Abdulkadir A, Lienkamp S S, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation[C]\/\/Medical Image Computing and Computer-Assisted 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":"pone.0312105.ref035","article-title":"Boundary loss-based 2.5 d fully convolutional neural networks approach for segmentation: A case study of the liver and tumor on computed tomography","author":"Xiaolong Li Y uexing Han","year":"2021","journal-title":"Algorithms"},{"key":"pone.0312105.ref036","article-title":"Conditional generative adversarial nets [J].","author":"M Mirza","journal-title":"arXiv preprint"},{"key":"pone.0312105.ref037","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J Y, Zhou T, et al. Image-to-image translation with conditional adversarial networks[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"pone.0312105.ref038","first-page":"14745","article-title":"Transgan: Two pure transformers can make one strong gan, and that can scale up[J]","volume":"34","author":"Y Jiang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0312105.ref039","doi-asserted-by":"crossref","unstructured":"Zeng Y, Lin Z, Patel V M. Sketchedit: Mask-free local image manipulation with partial sketches[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2022: 5951\u20135961.","DOI":"10.1109\/CVPR52688.2022.00586"},{"key":"pone.0312105.ref040","article-title":"Vishal M Patel. Cr-fill: Generative image inpainting with auxiliary contextual reconstruction","author":"Zhe Lin Y u Zeng","year":"2021","journal-title":"IEEE International Conference on Computer Vision"},{"key":"pone.0312105.ref041","article-title":"Compositional transformers for scene generation.","author":"Dor Arad Hudson","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"pone.0312105.ref042","first-page":"18367","article-title":"Improved transformer for high-resolution gans[J]","volume":"34","author":"L Zhao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0312105.ref043","article-title":"Improving visual quality of image synthesis by a token-based generator with transformers","author":"Yanhong Zeng","year":"2021","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"issue":"10","key":"pone.0312105.ref044","doi-asserted-by":"crossref","first-page":"519","DOI":"10.3390\/sym10100519","article-title":"Synthetic medical images using F&BGAN for improved lung nodules classification by multi-scale VGG16 [J].","volume":"10","author":"D Zhao","year":"2018","journal-title":"Symmetry"},{"key":"pone.0312105.ref045","unstructured":"Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]\/\/International conference on machine learning. pmlr, 2015: 448\u2013456."},{"key":"pone.0312105.ref046","unstructured":"Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks[C]\/\/International conference on machine learning. PMLR, 2017: 214\u2013223."},{"key":"pone.0312105.ref047","doi-asserted-by":"crossref","unstructured":"Salehi S S M, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks[C]\/\/Machine Learning in Medical Imaging: 8th International Workshop, MLMI 2017, Held in Conjunction with MICCAI 2017, Quebec City, QC, Canada, September 10, 2017, Proceedings 8. Springer International Publishing, 2017: 379\u2013387.","DOI":"10.1007\/978-3-319-67389-9_44"},{"key":"pone.0312105.ref048","doi-asserted-by":"crossref","first-page":"102680","DOI":"10.1016\/j.media.2022.102680","article-title":"The liver tumor segmentation benchmark (LiTS),\u201d","volume":"84","author":"P. Bilic","year":"2023","journal-title":"Medical Image Analysis"},{"issue":"3","key":"pone.0312105.ref049","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species[J]","volume":"26","author":"R. Dice L","year":"1945","journal-title":"Ecology"},{"issue":"11","key":"pone.0312105.ref050","doi-asserted-by":"crossref","first-page":"1451","DOI":"10.1109\/TMI.2006.880587","article-title":"Generalized overlap measures for evaluation and validation in medical image analysis[J]","volume":"25","author":"R Crum W","year":"2006","journal-title":"IEEE transactions on medical imaging"},{"issue":"1","key":"pone.0312105.ref051","first-page":"1","article-title":"Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool[J].","volume":"15","author":"A A Taha","year":"2015","journal-title":"BMC medical imaging"},{"issue":"2","key":"pone.0312105.ref052","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1111\/j.1469-8137.1912.tb05611.x","article-title":"The distribution of the flora in the alpine zone. 1[J]","volume":"11","author":"P. Jaccard","year":"1912","journal-title":"New phytologist"},{"key":"pone.0312105.ref053","unstructured":"Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. In International Conference on Learning Representations (ICLR), 2019."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0312105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T13:35:43Z","timestamp":1733232943000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0312105"}},"subtitle":[],"editor":[{"given":"Jin","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":53,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12,3]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0312105","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]}}}