{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T20:54:13Z","timestamp":1790801653122,"version":"4.1.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":52,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Swiss Federal Institute of Technology Zurich"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate delineation of kidney tumours in Computed Tomography (CT) is essential for downstream quantitative analysis and precision oncology that could enable personalised treatments, but manual segmentation is a specialised task, time-consuming and difficult to scale in routine practice. Automated 3D segmentation remains challenging in medical imaging, where images are large and dense volumes of data, making high-resolution processing with conventional dense convolutional neural networks computationally expensive, and often reliant on downsampling or patch-based inference. To overcome this problem, we propose a two-stage 3D segmentation methodology based on voxel sparsification and submanifold sparse convolutional networks (SSCNs). In Stage\u00a01, a low-resolution sparse network identifies a region of interest (ROI); in Stage\u00a02, a high-resolution sparse network performs refined segmentation within the cropped ROI. This design enables native 3D processing at high resolution while reducing CPU\/GPU memory usage and inference time. We evaluate the method on the KiTS23 dataset of renal cancer CT scans using 5-fold cross-validation. Our method achieved Dice similarity coefficients of 95.8% for kidneys + masses, 85.7% for tumours + cysts, and 80.3% for tumours alone, with performance competitive with top KiTS23 approaches. In direct comparisons on the same cross-validation folds, the proposed sparse method achieves tumour + cyst and tumour-only Dice scores comparable to, and slightly higher than, a patch-based nnU-Net baseline, while consistently requiring less VRAM and shorter inference time across the tested hardware. Across the tested GPUs, our sparse model is markedly faster than both nnU-Net and the zero-shot zoom-out\/zoom-in foundation model SegVol, which localises kidneys well but underperforms on small heterogeneous lesions. Compared to an equivalent dense implementation of the same architecture, the proposed sparse approach achieves up to a 60% reduction in inference time and up to a 75% reduction in VRAM usage across both CPU and the GPU configurations tested.<\/jats:p>","DOI":"10.1038\/s41598-026-51801-7","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T10:04:47Z","timestamp":1780308287000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Submanifold sparse convolutional networks for automated 3D segmentation of kidneys and kidney tumours in computed tomography"],"prefix":"10.1038","volume":"16","author":[{"given":"Sa\u00fal","family":"Alonso-Monsalve","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leigh H.","family":"Whitehead","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Aurisano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorena","family":"Escudero Sanchez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"51801_CR1","doi-asserted-by":"publisher","DOI":"10.3332\/ecancer.2023.1529","author":"A Bansal","year":"2023","unstructured":"Bansal, A., Dhamija, E., Chandrashekhara, S. & Sahoo, R. Role of CT in the detection and management of cancer related complications: a study of 599 patients. Ecancermedicalscience https:\/\/doi.org\/10.3332\/ecancer.2023.1529 (2023).","journal-title":"Ecancermedicalscience"},{"key":"51801_CR2","doi-asserted-by":"publisher","unstructured":"Siegel, R., Giaquinto, A. & A., J. Cancer statistics, 2024. CA Cancer J Clin.74, https:\/\/doi.org\/10.3322\/caac.21830 (2024).","DOI":"10.3322\/caac.21830"},{"key":"51801_CR3","unstructured":"West Midlands Cancer Alliance. Guidelines for the management of renal cancer. Online (Accessed April 2025)."},{"key":"51801_CR4","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1016\/S0140-6736(22)01059-5","volume":"400","author":"G Stewart","year":"2022","unstructured":"Stewart, G. et al. The multispeciality approach to the management of localised kidney cancer. Lancet 400, 523\u2013534. https:\/\/doi.org\/10.1016\/S0140-6736(22)01059-5 (2022).","journal-title":"Lancet"},{"key":"51801_CR5","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2015151169","author":"RJ Gillies","year":"2016","unstructured":"Gillies, R. J., Kinahan, P. & Hricak, H. Radiomics: Images are more than pictures, they are data. Radiology https:\/\/doi.org\/10.1148\/radiol.2015151169 (2016).","journal-title":"Radiology"},{"key":"51801_CR6","doi-asserted-by":"publisher","first-page":"6254","DOI":"10.1007\/s00330-024-10731-6","volume":"34","author":"A Uhlig","year":"2024","unstructured":"Uhlig, A. et al. Radiomics and machine learning for renal tumor subtype assessment using multiphase computed tomography in a multicenter setting. Eur. Radiol. 34, 6254\u20136263. https:\/\/doi.org\/10.1007\/s00330-024-10731-6 (2024).","journal-title":"Eur. Radiol."},{"key":"51801_CR7","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.868265","author":"L Rundo","year":"2022","unstructured":"Rundo, L. et al. Clinically interpretable radiomics-based prediction of histopathologic response to neoadjuvant chemotherapy in high-grade serous ovarian carcinoma. Front. Oncol. https:\/\/doi.org\/10.3389\/fonc.2022.868265 (2022).","journal-title":"Front. Oncol."},{"key":"51801_CR8","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8030055","author":"A Abdelrahman","year":"2022","unstructured":"Abdelrahman, A. & Viriri, S. Kidney tumor semantic segmentation using deep learning: A survey of state-of-the-art. J. Imaging https:\/\/doi.org\/10.3390\/jimaging8030055 (2022).","journal-title":"J. Imaging"},{"key":"51801_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101821","volume":"67","author":"N Heller","year":"2021","unstructured":"Heller, N. et al. The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge. Med. Image Anal. 67, 101821. https:\/\/doi.org\/10.1016\/j.media.2020.101821 (2021).","journal-title":"Med. Image Anal."},{"key":"51801_CR10","doi-asserted-by":"publisher","DOI":"10.1186\/s41747-023-00388-z","author":"T Buddenkotte","year":"2023","unstructured":"Buddenkotte, T. et al. Deep learning-based segmentation of multisite disease in ovarian cancer. Eur. Radiol. Exp. https:\/\/doi.org\/10.1186\/s41747-023-00388-z (2023).","journal-title":"Eur. Radiol. Exp."},{"key":"51801_CR11","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024","author":"J Wasserthal","year":"2023","unstructured":"Wasserthal, J. et al. Totalsegmentator: Robust segmentation of 104 anatomic structures in CT images. Radiol. Artif. Intell. https:\/\/doi.org\/10.1148\/ryai.230024 (2023).","journal-title":"Radiol. Artif. Intell."},{"key":"51801_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106405","volume":"152","author":"R Ranjbarzadeh","year":"2023","unstructured":"Ranjbarzadeh, R., Caputo, A., Tirkolaee, E. B., Jafarzadeh Ghoushchi, S. & Bendechache, M. Brain tumor segmentation of mri images: A comprehensive review on the application of artificial intelligence tools. Comput. Biol. Med. 152, 106405. https:\/\/doi.org\/10.1016\/j.compbiomed.2022.106405 (2023).","journal-title":"Comput. Biol. Med."},{"key":"51801_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. Int. Conf. Med. Image Comput. Comput.-Assist. Interv. (MICCAI) https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28 (2015).","journal-title":"Int. Conf. Med. Image Comput. Comput.-Assist. Interv. (MICCAI)"},{"key":"51801_CR14","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, P. F., Kohl, S. A. A., Petersen, J. & Maier-Hein, K. H. nnu-net: A self-configuring method for deep learning-based biomedical image segmentation.. Nat. Methods 18, 203\u2013211. https:\/\/doi.org\/10.1038\/s41592-020-01008-z (2021).","journal-title":"Nat. Methods"},{"key":"51801_CR15","doi-asserted-by":"publisher","first-page":"2793","DOI":"10.1007\/s11831-023-09898-w","volume":"30","author":"SS Kshatri","year":"2023","unstructured":"Kshatri, S. S. & Singh, D. Convolutional neural network in medical image analysis: A review.. Arch. Comput. Methods Eng. 30, 2793\u20132810 (2023).","journal-title":"Arch. Comput. Methods Eng."},{"key":"51801_CR16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.01307","author":"B Graham","year":"2017","unstructured":"Graham, B. & van der Maaten, L. Submanifold sparse convolutional networks. arXiv https:\/\/doi.org\/10.48550\/arXiv.1706.01307 (2017).","journal-title":"arXiv"},{"key":"51801_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961","author":"B Graham","year":"2018","unstructured":"Graham, B., Engelcke, M. & van der Maaten, L. 3D semantic segmentation with submanifold sparse convolutional networks. IEEE\/CVF Conf. Comput. Vision Pattern Recogn. https:\/\/doi.org\/10.1109\/CVPR.2018.00961 (2018).","journal-title":"IEEE\/CVF Conf. Comput. Vision Pattern Recogn."},{"key":"51801_CR18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.102.012005","volume":"102","author":"L Domin\u00e9","year":"2020","unstructured":"Domin\u00e9, L. & Terao, K. Scalable deep convolutional neural networks for sparse, locally dense liquid argon time projection chamber data. Phys. Rev. D 102, 012005. https:\/\/doi.org\/10.1103\/PhysRevD.102.012005 (2020).","journal-title":"Phys. Rev. D"},{"key":"51801_CR19","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/15\/04\/P04009","volume":"15","author":"C Adams","year":"2020","unstructured":"Adams, C. et al. Enhancing neutrino event reconstruction with pixel-based 3D readout for liquid argon time projection chambers. JINST 15, P04009. https:\/\/doi.org\/10.1088\/1748-0221\/15\/04\/P04009 (2020).","journal-title":"JINST"},{"key":"51801_CR20","doi-asserted-by":"publisher","unstructured":"Kekic, M. & et al. Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment. JHEP01, 189, https:\/\/doi.org\/10.1007\/JHEP01(2021)189 (2021). arXiv:2009.10783.","DOI":"10.1007\/JHEP01(2021)189"},{"key":"51801_CR21","unstructured":"Jianning, L. et al. Sparse Convolutional Neural Networks for Medical Image Analysis (2022)."},{"key":"51801_CR22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-47437-6","volume":"13","author":"J Li","year":"2023","unstructured":"Li, J. et al. Sparse convolutional neural network for high-resolution skull shape completion and shape super-resolution.. Sci. Rep. 13, 20229 (2023).","journal-title":"Sci. Rep."},{"key":"51801_CR23","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1097\/00004728-198010000-00017","volume":"4","author":"GN Hounsfield","year":"1980","unstructured":"Hounsfield, G. N. Computed medical imaging: Nobel lecture December 8 1979.. J. Comput. Assist. Tomogr. 4, 665\u2013674 (1980).","journal-title":"J. Comput. Assist. Tomogr."},{"key":"51801_CR24","doi-asserted-by":"crossref","unstructured":"Du, Y., BAI, F., Huang, T. & Zhao, B. Segvol: Universal and interactive volumetric medical image segmentation. In The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024).","DOI":"10.52202\/079017-3516"},{"key":"51801_CR25","unstructured":"The 2023 kidney and kidney tumor segmentation challenge (Online; Accessed June 2025). Https:\/\/kits-challenge.org\/kits23\/."},{"key":"51801_CR26","doi-asserted-by":"crossref","unstructured":"Hu, X. & Peng, Y. Gsca-net: A global spatial channel attention network for kidney, tumor and cyst segmentation. In Kidney and Kidney Tumor Segmentation (ed. Heller, N.) 67\u201376 (Springer Nature Switzerland, 2024).","DOI":"10.1007\/978-3-031-54806-2_10"},{"key":"51801_CR27","doi-asserted-by":"crossref","unstructured":"Uhm, K.-H. et al. Exploring 3d u-net training configurations and post-processing strategies for the miccai 2023 kidney and tumor segmentation challenge (2023). arXiv:2312.05528.","DOI":"10.1007\/978-3-031-54806-2_2"},{"key":"51801_CR28","doi-asserted-by":"publisher","unstructured":"Myronenko, A., Yang, D., He, Y. & Xu, D. Automated 3d segmentation of kidneys and tumors in MICCAI KiTS 2023 challenge. Lecture Notes in Computer Science14540, https:\/\/doi.org\/10.1007\/978-3-031-54806-2_1 (2024).","DOI":"10.1007\/978-3-031-54806-2_1"},{"key":"51801_CR29","doi-asserted-by":"crossref","unstructured":"Liu, S. & Han, B. Dynamic resolution network for kidney tumor segmentation In (ed. Heller, N.) (2024).","DOI":"10.1007\/978-3-031-54806-2_3"},{"key":"51801_CR30","unstructured":"Cardoso, M.\u00a0J. & et al. MONAI: An open-source framework for deep learning in healthcare (2022). arXiv:2211.02701."},{"key":"51801_CR31","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J.\u00a0Y. & Savarese, S. 4D spatio-temporal ConvNets: Minkowski convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3075\u20133084 (2019).","DOI":"10.1109\/CVPR.2019.00319"},{"key":"51801_CR32","doi-asserted-by":"publisher","unstructured":"Woo, S. et al. ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 16133\u201316142, https:\/\/doi.org\/10.1109\/CVPR52729.2023.01548 (2023).","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"51801_CR33","doi-asserted-by":"publisher","unstructured":"Milletari, F., Navab, N. & Ahmadi, S.-A. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 Fourth International Conference on 3D Vision (3DV), 565\u2013571, https:\/\/doi.org\/10.1109\/3DV.2016.79 (2016).","DOI":"10.1109\/3DV.2016.79"},{"key":"51801_CR34","doi-asserted-by":"crossref","unstructured":"Sudre, C.\u00a0H., Li, W., Vercauteren, T., Ourselin, S. & Jorge Cardoso, M. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In Cardoso, M.\u00a0J. et al. (eds.) Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 240\u2013248 (Springer International Publishing, Cham, 2017).","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"51801_CR35","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2019).","DOI":"10.1145\/3292500.3330701"},{"key":"51801_CR36","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In Proceedings of the 7th International Conference on Learning Representations (ICLR) (2019)."},{"key":"51801_CR37","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale (2021). arXiv:2010.11929."},{"key":"51801_CR38","unstructured":"Heller, N. et al. The KiTS21 challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT (2023). arXiv:2307.01984."},{"key":"51801_CR39","doi-asserted-by":"publisher","unstructured":"Uhm, K. et al. kidney and tumor segmentation challenge. Lecture Notes in Computer Science14540, 2024. https:\/\/doi.org\/10.1007\/978-3-031-54806-2_2 (2023).","DOI":"10.1007\/978-3-031-54806-2_2"},{"key":"51801_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106861","volume":"221","author":"C-H Hsiao","year":"2022","unstructured":"Hsiao, C.-H. et al. A deep learning-based precision volume calculation approach for kidney and tumor segmentation on computed tomography images. Comput. Methods Programs Biomed. 221, 106861. https:\/\/doi.org\/10.1016\/j.cmpb.2022.106861 (2022).","journal-title":"Comput. Methods Programs Biomed."},{"key":"51801_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.diii.2024.06.002","author":"D Ueda","year":"2024","unstructured":"Ueda, D. et al. Climate change and artificial intelligence in healthcare: Review and recommendations towards a sustainable future. Diagn. Interv. Imaging https:\/\/doi.org\/10.1016\/j.diii.2024.06.002 (2024).","journal-title":"Diagn. Interv. Imaging"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-51801-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-51801-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-51801-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T13:12:06Z","timestamp":1784812326000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-51801-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["51801"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-51801-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]},"assertion":[{"value":"6 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"23089"}}