{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T10:46:00Z","timestamp":1777113960626,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"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":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate segmentation of the fetal cerebellum in ultrasound images is crucial for assessing fetal development and detecting prenatal abnormalities. However, this task remains challenging due to factors such as image noise, complex anatomical structures, and limited availability of annotated data, which is further compounded by the high cost and effort required for manual labeling. To address these challenges, we propose SS_CASE_UNet, a novel semi-supervised segmentation framework that enhances U-Net with attention mechanisms to better manage image noise and anatomical complexity. Additionally, a multi-stage semi-supervised training strategy effectively mitigates the scarcity of annotated data. The architecture integrates Squeeze-and-Excitation blocks for dynamic channel-wise feature recalibration and a Coordinate Attention block at the bottleneck to capture precise spatial and long-range dependencies. Our multi-stage training pipeline leverages both labeled and unlabeled data through iterative pseudo-label and re-training, improving generalization in low-annotation scenarios. Experimental results demonstrate that SS_CASE_UNet outperforms existing methods, achieving a Dice Similarity Coefficient (DSC) of 87.65%, along with high accuracy (99.08%), precision (93.49%), recall (82.34%), and Jaccard Similarity (81.78%). Despite incorporating advanced attention mechanisms, our model maintains a balanced complexity-performance trade-off. These results highlight SS_CASE_UNet as a robust and clinically practical solution for automated segmentation of the fetal cerebellum in ultrasound images.<\/jats:p>","DOI":"10.1038\/s41598-025-28201-4","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T13:20:00Z","timestamp":1766582400000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SS_CASE_UNet: an attention-enhanced semi-supervised framework for fetal cerebellum segmentation in ultrasound images"],"prefix":"10.1038","volume":"15","author":[{"given":"Amene","family":"Vatanparast","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mansoor","family":"Fateh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hoda","family":"Mashayekhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saideh","family":"Ferdowsi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"28201_CR1","doi-asserted-by":"crossref","unstructured":"Rubesova, E. & Barth, R. Advances in fetal imaging. Am. J. Perinatol. 31, 7 (2014).","DOI":"10.1055\/s-0034-1371712"},{"key":"28201_CR2","doi-asserted-by":"crossref","unstructured":"Lentz, B., Fong, T., Rhyne, R. & Risko, N. A systematic review of the cost-effectiveness of ultrasound in emergency care settings. Ultrasound J 13, 1 (2021).","DOI":"10.1186\/s13089-021-00216-8"},{"key":"28201_CR3","doi-asserted-by":"crossref","unstructured":"A. I. o. U. i. Medicine, AIUM practice guideline for the performance of obstetric ultrasound examinations. J. Ultrasound Med. 32(6),  1083\u2009\u2013\u2009101 (2013).","DOI":"10.7863\/jum.2013.32.6.1083"},{"key":"28201_CR4","first-page":"198586","volume":"112","author":"A Vatanparast","year":"2025","unstructured":"Vatanparast, A., Fateh, M. & Mashayekhi, H. AC_Branch_MobileNet: an effective hybrid branch network for plane classification in fetus brain ultrasound image. Biomed. Signal Process. Control. 112, 198586 (2025).","journal-title":"Biomed. Signal Process. Control"},{"key":"28201_CR5","doi-asserted-by":"crossref","unstructured":"Qu, R., Xu, G., Ding, C., Jia, W. & Sun, M. Standard plane identification in fetal brain ultrasound scans using a differential convolutional neural network. IEEE Access 1\u20131 (2020).","DOI":"10.1109\/ACCESS.2020.2991845"},{"key":"28201_CR6","doi-asserted-by":"publisher","first-page":"25665","DOI":"10.1038\/s41598-025-06526-4","volume":"15","author":"I Umar","year":"2025","unstructured":"Umar, I., Yasser, A., Al-Razgan, M. Fetal-Net: enhancing maternal-fetal ultrasound interpretation through multi-scale convolutional neural networks and transformers. Sci. Rep. 15, 25665 (2025).","journal-title":"Sci. Rep."},{"key":"28201_CR7","doi-asserted-by":"publisher","first-page":"25076","DOI":"10.1038\/s41598-024-77313-w","volume":"14","author":"J Mlodawski","year":"2024","unstructured":"Mlodawski, J., Zmelonek-Znamirowska, A. & Mlodawska, M. Repeatability and reproducibility of artificial intelligence-acquired fetal brain measurements (SonoCNS) in the second and third trimesters of pregnancy. Sci. Rep. 14, 25076 (2024).","journal-title":"Sci. Rep."},{"key":"28201_CR8","doi-asserted-by":"crossref","unstructured":"Westerhuis, J., Dudink, J., Wijnands, B. D., Zeeuw, C. & Canto, C. Impact of intrauterine insults on fetal and postnatal cerebellar development in humans and rodents. Cells 13(22),  11\u201319  (2024).","DOI":"10.3390\/cells13221911"},{"key":"28201_CR9","doi-asserted-by":"crossref","unstructured":"Singh, V. et al. Semantic segmentation of cerebellum in 2D fetal ultrasound brain images using convolutional neural networks. IEEE Access 1\u20131 (2021).","DOI":"10.1109\/ACCESS.2021.3088946"},{"key":"28201_CR10","doi-asserted-by":"publisher","first-page":"102639","DOI":"10.1016\/j.media.2022.102639","volume":"83","author":"A Veronika","year":"2023","unstructured":"Veronika, A. et al. Placenta segmentation in ultrasound imaging: addressing sources of uncertainty and limited field-of-view. Med. Image. Anal. 83, 102639 (2023).","journal-title":"Med. Image. Anal."},{"issue":"4","key":"28201_CR11","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1002\/jcu.23924","volume":"53","author":"D Vetriselvi","year":"2025","unstructured":"Vetriselvi, D. & Thenmozhi, R. Prenatal diagnostics using deep learning: A dual approach to plane localization and cerebellum segmentation in ultrasound images. J. Clin. Ultrasound. 53 (4), 721\u2013735 (2025).","journal-title":"J. Clin. Ultrasound"},{"key":"28201_CR12","doi-asserted-by":"publisher","first-page":"19612","DOI":"10.1038\/s41598-025-04631-y","volume":"15","author":"R Singh","year":"2025","unstructured":"Singh, R., Gupta, S., Mohamed, H. & Advancing prenatal healthcare by explainable AI enhanced fetal ultrasound image segmentation using U-Net\u2009+\u2009+\u2009with attention mechanisms. Sci. Rep. 15, 19612 (2025).","journal-title":"Sci. Rep."},{"issue":"17","key":"28201_CR13","doi-asserted-by":"publisher","first-page":"2760","DOI":"10.3390\/diagnostics13172760","volume":"13","author":"NR Redefining Radiology","year":"2023","unstructured":"Redefining Radiology, N. R. A review of artificial intelligence integration in medical imaging. Diagnostics (Basel). 13 (17), 2760 (2023).","journal-title":"Diagnostics (Basel)"},{"key":"28201_CR14","doi-asserted-by":"crossref","unstructured":"Khajeha, H. R., Fateh, M. & Abolghase, V. Diagnosis of glaucoma using multi-scale attention block in convolution neural network and data augmentation techniques. Eng. Rep. 6, 10 (2024).","DOI":"10.1002\/eng2.12866"},{"issue":"9","key":"28201_CR15","doi-asserted-by":"publisher","first-page":"e13625","DOI":"10.1111\/exsy.13625","volume":"41","author":"S Rezvani","year":"2024","unstructured":"Rezvani, S., Fateh, M. & Khosravi, H. ABANet: attention boundary-aware network for image segmentation. Expert Syst. 41 (9), e13625 (2024).","journal-title":"Expert Syst."},{"key":"28201_CR16","doi-asserted-by":"publisher","first-page":"104623","DOI":"10.1016\/j.compbiomed.2021.104623","volume":"135","author":"MFA N","year":"2021","unstructured":"N, M. F. A., Meiburger, K. & D. J and Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease. Comput. Biol. Med. 135, 104623 (2021).","journal-title":"Comput. Biol. Med."},{"key":"28201_CR17","doi-asserted-by":"crossref","unstructured":"Fatima, M. et al.  An adaptive deep learning approach based on InBNFus and CNNDen-GRU networks for breast cancer and maternal fetal classification using ultrasound images. Sci. Rep. 15,  22027 (2025).","DOI":"10.1038\/s41598-025-03402-z"},{"key":"28201_CR18","doi-asserted-by":"publisher","first-page":"103528","DOI":"10.1016\/j.bspc.2022.103528","volume":"75","author":"S Xin","year":"2022","unstructured":"Xin, S., Feng, C., Xin, Z., Changbin, S. & Xibei, Y. ECAU-Net: efficient channel attention U-Net for fetal ultrasound cerebellum segmentation. Biomed. Signal Process. Control. 75, 103528 (2022).","journal-title":"Biomed. Signal Process. Control"},{"key":"28201_CR19","doi-asserted-by":"crossref","unstructured":"Vel\u00e1squez-Rodr\u00edguez, G., Fanti-Guti\u00e9rrez, Z. & Torres 3D statistical shape models for automatic segmentation of the fetal cerebellum in ultrasound images, SIViP, vol. 81, p. 19, (2025).","DOI":"10.1007\/s11760-024-03615-1"},{"key":"28201_CR20","doi-asserted-by":"crossref","unstructured":"Vel\u00e1squez Rodr\u00edguez, G., A. et al. Automatic segmentation of the cerebellum in ultrasound volumes of the fetal brain. Rev. Mex.  Ingenieria Biomed. 36 (2), 121\u2013129 (2015).","DOI":"10.17488\/RMIB.36.2.4"},{"issue":"7","key":"28201_CR21","doi-asserted-by":"publisher","first-page":"6575","DOI":"10.1016\/j.eswa.2011.12.044","volume":"39","author":"HC Chen","year":"2012","unstructured":"Chen, H. C. & Gu, F. C. Pattern recognition with cerebellar model articulation controller and fractal features on partial discharges. Expert Syst. Appl. 39 (7), 6575\u20136584 (2012).","journal-title":"Expert Syst. Appl."},{"key":"28201_CR22","doi-asserted-by":"crossref","unstructured":"Kan, H. C. et al. Automated kidney tumor segmentation in CT images using deep learning: A multi-stage approach. Acad. Radiol. (2025).","DOI":"10.1016\/j.acra.2025.08.020"},{"key":"28201_CR23","doi-asserted-by":"crossref","unstructured":"Xin, S., Yingyan, G., Xin, Z., Chunlong, H. & Ke, C. FCRB U-Net: A novel fully connected residual block U-Net for fetal cerebellum ultrasound image segmentation. Comput. Biol. Med. 148,  105693 (2022).","DOI":"10.1016\/j.compbiomed.2022.105693"},{"key":"28201_CR24","doi-asserted-by":"crossref","unstructured":"Venturini, L., Papageorghiou, A., Noble, J. & Namburete, A. Multi-task CNN for structural semantic segmentation in 3D fetal brain ultrasound. In Medical Image Understanding and Analysis (2020).","DOI":"10.1007\/978-3-030-39343-4_14"},{"issue":"4","key":"28201_CR25","first-page":"1","volume":"21","author":"RS Aljuraifani","year":"2025","unstructured":"Aljuraifani, R. S., Aljohani, A. & Alharbi, A. Fetal cerebellar area: Ultrasound reference ranges at 13\u201339 weeks of gestation. Curr. Med. Imaging. 21 (4), 1\u20138 (2025).","journal-title":"Curr. Med. Imaging"},{"issue":"12","key":"28201_CR26","doi-asserted-by":"publisher","first-page":"4080","DOI":"10.3390\/jcm12124080","volume":"12","author":"L Manzo","year":"2023","unstructured":"Manzo, L. et al. Fetal cerebellar area: ultrasound reference ranges at 13\u201339 weeks of gestation. J. Clin. Med. 12 (12), 4080 (2023).","journal-title":"J. Clin. Med."},{"issue":"9","key":"28201_CR27","doi-asserted-by":"publisher","first-page":"6059","DOI":"10.21037\/qims-22-1242","volume":"13","author":"Q Wang","year":"2023","unstructured":"Wang, Q. et al. A method framework of automatic localization and quantitative segmentation for the cavum septum pellucidum complex and the cerebellar vermis in fetal brain ultrasound images. Quant. Imaging Med. Surg. 13 (9), 6059\u20136088 (2023).","journal-title":"Quant. Imaging Med. Surg."},{"key":"28201_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Z., Gong, H., Wan, X. & Li, H. ASC: Appearance and structure consistency for unsupervised domain adaptation in fetal brain MRI segmentation. In Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023: 26th International Conference, Vancouver, BC, Canada (2023).","DOI":"10.1007\/978-3-031-43990-2_31"},{"key":"28201_CR29","doi-asserted-by":"publisher","first-page":"109027","DOI":"10.1016\/j.cmpb.2025.109027","volume":"271","author":"S Huang","year":"2025","unstructured":"Huang, S., Wang, S., Qiao, S. & Li, Y. SEMI-PLC: A framework for semi-supervised medical images segmentation with pseudo label correction. Comput. Methods Programs Biomed. 271, 109027 (2025).","journal-title":"Comput. Methods Programs Biomed."},{"key":"28201_CR30","doi-asserted-by":"crossref","unstructured":"Fischer, P., Brox, T. & Ronneberger, O. U-Net: Convolutional networks for biomedical image segmentation. In International Conference on Medical Image, Munich, Germany (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"28201_CR31","doi-asserted-by":"crossref","unstructured":"Hu J. et al. Squeeze-and-excitation network. In CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA (2018).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"28201_CR32","doi-asserted-by":"publisher","first-page":"76691","DOI":"10.1109\/ACCESS.2023.3297206","volume":"11","author":"JH Bang","year":"2023","unstructured":"Bang, J. H. Coordinate attention for optimizing CMT networks. IEEE Access. 11, 76691\u201376702 (2023).","journal-title":"IEEE Access."},{"issue":"9","key":"28201_CR33","doi-asserted-by":"publisher","first-page":"4997","DOI":"10.1016\/j.acra.2025.05.007","volume":"32","author":"S Asif","year":"2025","unstructured":"Asif, S. et al. Improving breast cancer diagnosis in ultrasound images using deep learning with feature fusion and attention mechanism. Acad. Radiol. 32 (9), 4997\u20135009 (2025).","journal-title":"Acad. Radiol."},{"key":"28201_CR34","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","volume":"109","author":"JE van Engelen","year":"2020","unstructured":"van Engelen, J. E. & Hoos, H. H. A survey on semi-supervised learning. Mach. Learn. 109, 373\u2013440 (2020).","journal-title":"Mach. Learn."},{"key":"28201_CR35","doi-asserted-by":"publisher","first-page":"101693","DOI":"10.1016\/j.media.2020.101693","volume":"63","author":"N Tajbakhsh","year":"2020","unstructured":"Tajbakhsh, N. et al. Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation. Med. Image. Anal. 63, 101693 (2020).","journal-title":"Med. Image. Anal."},{"key":"28201_CR36","doi-asserted-by":"publisher","first-page":"107208","DOI":"10.1016\/j.cmpb.2022.107208","volume":"227","author":"CG Chadoulos","year":"2022","unstructured":"Chadoulos, C. G., Tsaopoulos, D. E., Moustakidis, S., Tsakiridis, N. L. & Theocharis, J. B. A novel multi-atlas segmentation approach under the semi-supervised learning framework: application to knee cartilage segmentation. Comput. Methods Programs Biomed. 227, 107208 (2022).","journal-title":"Comput. Methods Programs Biomed."},{"key":"28201_CR37","doi-asserted-by":"crossref","unstructured":"Huang, S., Wang, S., Qiao, S. & Liu, Y. SEMI-PLC: A framework for semi-supervised medical images segmentation with Pseudo label correction. In Computer Methods Programs Biomedicine. 109027  (2025).","DOI":"10.1016\/j.cmpb.2025.109027"},{"issue":"1","key":"28201_CR38","doi-asserted-by":"publisher","first-page":"10200","DOI":"10.1038\/s41598-020-67076-5","volume":"10","author":"X Burgos-Artizzu","year":"2020","unstructured":"Burgos-Artizzu, X., Coronado-Guti\u00e9rrez, D., Valenzuela-Alcaraz, B., Bonet-Carne, E. & Eixarch, E. Evaluation of deep convolutional neural networks for automatic classification of common maternal fetal ultrasound planes. Sci. Rep. 10 (1), 10200 (2020).","journal-title":"Sci. Rep."},{"key":"28201_CR39","doi-asserted-by":"crossref","unstructured":"Azimi Abriz, S., Fateh, M., Jafarin, F. & Abolghasemi, V. Multi-disease detection in retinal imaging using VNet with image processing methods for data generation. Adv. Intell. Syst. 10, 2401039 (2025).","DOI":"10.1002\/aisy.202401039"},{"key":"28201_CR40","doi-asserted-by":"crossref","unstructured":"Shorten, C. & Khoshgoftaar, T. A survey on image data augmentation for deep learning. J. Big Data, 60  (2019).","DOI":"10.1186\/s40537-019-0197-0"},{"key":"28201_CR41","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A. & Vedantam, R. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In IEEE International Conference on Computer Vision (ICCV), Venice, Italy (2017).","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-28201-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-28201-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-28201-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T10:31:08Z","timestamp":1777113068000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-28201-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["28201"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-28201-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,24]]},"assertion":[{"value":"7 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"44536"}}