{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T13:01:31Z","timestamp":1784120491811,"version":"3.55.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T00:00:00Z","timestamp":1755043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T00:00:00Z","timestamp":1755043200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>Deep learning has significantly advanced medical image analysis, particularly in semantic segmentation, which is essential for clinical decisions. However, existing 3D segmentation models, like the traditional 3D UNet, face challenges in balancing computational efficiency and accuracy when processing volumetric medical data. This study aims to develop an improved architecture for 3D medical image segmentation with enhanced learning strategies to improve accuracy and address challenges related to limited training data.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>We propose ES-UNet, a 3D segmentation architecture that achieves superior segmentation performance while offering competitive efficiency across multiple computational metrics, including memory usage, inference time, and parameter count. The model builds upon the full-scale skip connection design of UNet3+ by integrating channel attention modules into each encoder-to-decoder path and incorporating full-scale deep supervision to enhance multi-resolution feature learning. We further introduce Region Specific Scaling (RSS), a data augmentation method that adaptively applies geometric transformations to annotated regions, and a Dynamically Weighted Dice (DWD) loss to improve the balance between precision and recall. The model was evaluated on the MICCAI HECKTOR dataset, and additional validation was conducted on selected tasks from the Medical Segmentation Decathlon (MSD).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>On the HECKTOR dataset, ES-UNet achieved a Dice Similarity Coefficient (DSC) of 76.87%, outperforming baseline models including 3D UNet, 3D UNet 3+, nnUNet, and Swin UNETR. Ablation studies showed that RSS and DWD contributed up to 1.22% and 1.06% improvement in DSC, respectively. A sensitivity analysis demonstrated that the chosen scaling range in RSS offered a favorable trade-off between deformation and anatomical plausibility. Cross-dataset evaluation on MSD Heart and Spleen tasks also indicated strong generalization. Computational analysis revealed that ES-UNet achieves superior segmentation performance with moderate computational demands. Specifically, the enhanced skip connection design with lightweight channel attention modules integrated throughout the network architecture enables this favorable balance between high segmentation accuracy and computational efficiency.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>ES-UNet integrates architectural and algorithmic improvements to achieve robust 3D medical image segmentation. While the framework incorporates established components, its core contributions lie in the optimized skip connection strategy and supporting techniques like RSS and DWD. Future work will explore adaptive scaling strategies and broader validation across diverse imaging modalities.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/s12880-025-01857-0","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T12:45:33Z","timestamp":1755089133000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["ES-UNet: efficient 3D medical image segmentation with enhanced skip connections in 3D UNet"],"prefix":"10.1186","volume":"25","author":[{"given":"Minyoung","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungtaek","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyoung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taikyeong","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungwook","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,13]]},"reference":[{"key":"1857_CR1","doi-asserted-by":"crossref","unstructured":"Cire\u015fan DC, Giusti A, Gambardella LM, Schmidhuber J. Mitosis detection in breast cancer histology images with deep neural networks. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2013: 16th International Conference, Nagoya, Japan, September 22-26, 2013, Proceedings, Part II 16. 2013. pp. 411\u201318.","DOI":"10.1007\/978-3-642-40763-5_51"},{"key":"1857_CR2","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Medical image computing and Computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. 2015. pp. 234-41.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"5","key":"1857_CR3","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"HC Shin","year":"2016","unstructured":"Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imag. 2016;35(5):1285\u201398.","journal-title":"IEEE Trans Med Imag"},{"issue":"3","key":"1857_CR4","doi-asserted-by":"publisher","first-page":"413","DOI":"10.3390\/jpm13030413","volume":"13","author":"G Marullo","year":"2023","unstructured":"Marullo G, Tanzi L, Ulrich L, Porpiglia F, Vezzetti E. A multi-task convolutional neural network for semantic segmentation and event detection in laparoscopic surgery. J Personalized Med. 2023;13(3):413.","journal-title":"J Personalized Med"},{"issue":"3","key":"1857_CR5","doi-asserted-by":"publisher","first-page":"036501","DOI":"10.1117\/1.JMI.5.3.036501","volume":"5","author":"K Yan","year":"2018","unstructured":"Yan K, Wang X, Lu L, Summers RM. DeepLesion: Automated mining of large-scale lesion annotations and universal lesion detection with deep learning. J Med Imaging. 2018;5(3):036501\u2013036501.","journal-title":"J Med Imaging"},{"issue":"4","key":"1857_CR6","doi-asserted-by":"publisher","first-page":"597","DOI":"10.24425\/ijet.2019.129818","volume":"65","author":"F Sherif","year":"2019","unstructured":"Sherif F, Mohamed WA, Mohra A. Skin lesion analysis toward melanoma detection using deep learning techniques. Int J Electron Telecommun. 2019;65(4):597\u2013602.","journal-title":"Int J Electron And Telecommunications"},{"key":"1857_CR7","doi-asserted-by":"crossref","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115\u201318.","DOI":"10.1038\/nature21056"},{"issue":"4","key":"1857_CR8","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1109\/TMI.2019.2945514","volume":"39","author":"N Wu","year":"2019","unstructured":"Wu N, Phang J, Park J, Shen Y, Huang Z, Zorin M, et al. Deep neural networks improve radiologists\u2019 performance in breast cancer screening. IEEE Trans Med Imag. 2019;39(4):1184\u201394.","journal-title":"IEEE Trans Med Imag"},{"issue":"4","key":"1857_CR9","doi-asserted-by":"publisher","first-page":"1227","DOI":"10.1002\/jmri.27129","volume":"52","author":"M Zhang","year":"2020","unstructured":"Zhang M, Young GS, Chen H, Li J, Qin L, McFaline-Figueroa JR, et al. Deep-learning detection of cancer metastases to the brain on MRI. J Magnetic Reson Imag. 2020;52(4):1227\u201336.","journal-title":"J Magnetic Reson Imag"},{"issue":"1","key":"1857_CR10","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda AP, Shehata S, Mutter D, Marescaux J, De Mathelin M, Padoy N. Endonet: A deep architecture for recognition tasks on laparoscopic videos. IEEE Trans Med Imag. 2016;36(1):86\u201397.","journal-title":"IEEE Trans Med Imag"},{"key":"1857_CR11","doi-asserted-by":"crossref","unstructured":"Czempiel T, Paschali M, Keicher M, Simson W, Feussner H, Kim ST, et al. TeCNO: Surgical phase recognition with multi-stage temporal convolutional networks. Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23. 2020. p. 343\u201352.","DOI":"10.1007\/978-3-030-59716-0_33"},{"issue":"1","key":"1857_CR12","doi-asserted-by":"publisher","first-page":"107","DOI":"10.3390\/diagnostics13010107","volume":"13","author":"M Park","year":"2022","unstructured":"Park M, Oh S, Jeong T, Yu S. Multi-stage temporal convolutional network with moment loss and positional encoding for surgical phase recognition. Diagnostics. 2022;13(1):107.","journal-title":"Diagnostics"},{"issue":"1","key":"1857_CR13","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1186\/s13018-024-05128-6","volume":"19","author":"KB Park","year":"2024","unstructured":"Park K-B, Kim MS, Yoon DK, Jeon YD. Clinical validation of a deep learning-based approach for preoperative decision-making in implant size for total knee arthroplasty. J Orthop Surg Res. 2024;19(1):637.","journal-title":"J Appl Psychol Orthopaedic Surgery And Research"},{"key":"1857_CR14","doi-asserted-by":"publisher","first-page":"113196","DOI":"10.1016\/j.knosys.2025.113196","volume":"315","author":"EB Loussaief","year":"2025","unstructured":"Loussaief EB, Rashwan HA, Ayad M, Khalid A, Puig D. Adaptive weighted multi-teacher distillation for efficient medical imaging segmentation with limited data. Knowl-Based Syst. 2025;315:113196.","journal-title":"Knowl-Based Syst"},{"key":"1857_CR15","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi SA. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D vision (3DV). 2016. p. 565\u201371.","DOI":"10.1109\/3DV.2016.79"},{"key":"1857_CR16","doi-asserted-by":"crossref","unstructured":"Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, Liang J. Unet++: A nested U-Net architecture for medical image segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support. 4th international workshop, DLMIA 2018, and 8th international workshop, ML-CDS 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4. 2018. p. 3\u201311.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"1857_CR17","doi-asserted-by":"crossref","unstructured":"Huang H, Lin L, Tong R, Hu H, Zhang Q, Iwamoto Y, et al. Unet 3+: A full-scale connected unet for medical image segmentation. ICASSP 2020\u20132020 IEEE international conference on acoustics, speech and signal processing (ICASSP). 2020. p. 1055\u201359.","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"1857_CR18","doi-asserted-by":"crossref","unstructured":"Wu R, Liu Y, Liang P, Chang Q. H-vmunet: High-order vision mamba unet for medical image segmentation. Neurocomputing. 2025;129447.","DOI":"10.1016\/j.neucom.2025.129447"},{"key":"1857_CR19","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Nath V, Tang Y, Yang D, Roth HR, Xu D. Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. International MICCAI brainlesion workshop. 2021. p. 272\u201384.","DOI":"10.1007\/978-3-031-08999-2_22"},{"issue":"2","key":"1857_CR20","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein KH. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203\u201311.","journal-title":"Nat Methods"},{"key":"1857_CR21","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Tang Y, Nath V, Yang D, Myronenko A, Landman B, et al. Unetr: Transformers for 3d medical image segmentation. Proceedings of the IEEE\/CVF winter conference on applications of computer vision. 2022. p. 574\u201384.","DOI":"10.1109\/WACV51458.2022.00181"},{"issue":"1","key":"1857_CR22","doi-asserted-by":"publisher","first-page":"11747","DOI":"10.1038\/s41598-025-96053-z","volume":"15","author":"J Yoo","year":"2025","unstructured":"Yoo J, Joo I, Jeon SK, Park J, Cho EJ. Three-dimensional organ segmentation-derived CT attenuation parameters for assessing hepatic steatosis in chronic hepatitis B patients. Sci Rep. 2025;15(1):11747.","journal-title":"Sci Rep"},{"key":"1857_CR23","doi-asserted-by":"crossref","unstructured":"\u04aai\u00e7ek \u00d6, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19. 2016. p. 424\u201332.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"1857_CR24","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. p. 7132\u201341.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1857_CR25","doi-asserted-by":"crossref","unstructured":"Andrearczyk V, Oreiller V, Boughdad S, Rest CCL, Elhalawani H, Jreige M, et al. Overview of the HECKTOR challenge at MICCAI 2021: Automatic head and neck tumor segmentation and outcome prediction in PET\/CT images. In: 3D head and neck tumor segmentation in PET\/CT Chall. 2021. p. 1\u201337.","DOI":"10.1007\/978-3-030-98253-9_1"},{"key":"1857_CR26","first-page":"562","volume-title":"Artificial intelligence and statistics","author":"CY Lee","year":"2015","unstructured":"Lee CY, Xie S, Gallagher P, Zhang Z, Tu Z. Deeply-supervised nets. In: Artificial intelligence and statistics. 2015. p. 562\u201370."},{"key":"1857_CR27","unstructured":"Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. International conference on machine learning. 2015. p. 448\u201356."},{"key":"1857_CR28","unstructured":"Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th international conference on machine learning (ICML-10). 2010. p. 807\u201314."},{"key":"1857_CR29","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P. Focal loss for dense object detection. Proceedings of the IEEE international conference on computer vision. 2017. p. 2980\u201388.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1857_CR30","unstructured":"Kingma DP. Adam: a method for stochastic optimization. 2014; https:\/\/doi.org\/arXiv:1412.6980"},{"key":"1857_CR31","unstructured":"Loshchilov I, Hutter F. Sgdr: Stochastic gradient descent with warm restarts. 2016. https:\/\/doi.org\/arXiv:1608.03983"},{"key":"1857_CR32","doi-asserted-by":"crossref","unstructured":"Li Z, Huang C, Xie S. Multi-modality assisted semi-supervised brain tumor segmentation in non-dominant modality based on consistency learning. IEEE Transactions on Instrumentation and Measurement. 2024.","DOI":"10.1109\/TIM.2024.3400343"},{"key":"1857_CR33","doi-asserted-by":"crossref","unstructured":"Jin Q, Zou C, Cui H, Sun C, Huang SW, Kuo YJ, et al. Multi-modality contrastive learning for sarcopenia screening from hip x-rays and clinical information. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2023. p. 85\u201394.","DOI":"10.1007\/978-3-031-43987-2_9"},{"issue":"11","key":"1857_CR34","doi-asserted-by":"publisher","first-page":"8260","DOI":"10.1002\/mp.17323","volume":"51","author":"Z Li","year":"2024","unstructured":"Li Z, Xie S. EBC-Net: 3D semi-supervised segmentation of pancreas based on edge-biased consistency regularization in dual perturbation space. Med Phys. 2024;51(11):8260\u201371.","journal-title":"Med Phys"},{"key":"1857_CR35","doi-asserted-by":"crossref","unstructured":"Jin Q, Cui H, Sun C, Zheng J, Wei L, Fang Z, et al. Semi-supervised histological image segmentation via hierarchical consistency enforcement. International conference on medical image computing and computer-assisted intervention. 2022. p. 3\u201313.","DOI":"10.1007\/978-3-031-16434-7_1"},{"key":"1857_CR36","doi-asserted-by":"publisher","first-page":"122093","DOI":"10.1016\/j.eswa.2023.122093","volume":"238","author":"Q Jin","year":"2024","unstructured":"Jin Q, Cui H, Sun C, Song Y, Zheng J, Cao L, et al. Inter-and intra-uncertainty based feature aggregation model for semi-supervised histopathology image segmentation. Expert Syst Appl. 2024;238:122093.","journal-title":"Expert Syst With Applications"}],"updated-by":[{"DOI":"10.1186\/s12880-025-01891-y","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000}}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01857-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-025-01857-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01857-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T12:49:30Z","timestamp":1757422170000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-025-01857-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,13]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1857"],"URL":"https:\/\/doi.org\/10.1186\/s12880-025-01857-0","relation":{"correction":[{"id-type":"doi","id":"10.1186\/s12880-025-01891-y","asserted-by":"object"}]},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,13]]},"assertion":[{"value":"14 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original version of this article was revised: wrong symbols in Table 9 have been removed; the layout of Table 2 has been revised to improve clarity.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2025","order":7,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":8,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1186\/s12880-025-01891-y","URL":"https:\/\/doi.org\/10.1186\/s12880-025-01891-y","order":10,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study utilized publicly available anonymized datasets that were previously collected with appropriate ethical approvals and patient consent. No additional ethics approval was required for our analysis, as it involved secondary use of de-identified public data in accordance with the original data usage agreements and licenses.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable. This study used publicly available anonymized datasets where consent for publication was obtained during the original data collection process by the original data providers.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"327"}}