{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T10:32:01Z","timestamp":1785407521570,"version":"3.56.0"},"reference-count":33,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T00:00:00Z","timestamp":1779494400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Spanish Ministry of Science, Innovation and Universities","award":["PID2024-155219OB-C33"],"award-info":[{"award-number":["PID2024-155219OB-C33"]}]},{"award":["PID2024-155219OB-C33"],"award-info":[{"award-number":["PID2024-155219OB-C33"]}],"id":[{"id":"https:\/\/ror.org\/05r0vyz12","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Ischemic stroke remains a leading cause of global mortality and long-term neurological disability, where the \u201cTime is Brain\u201d paradigm dictates that rapid and accurate lesion assessment is fundamental for effective clinical intervention. While the nnU-Net v2 framework has established a new state of the art in medical image segmentation, its high computational demands and reliance on data-center-grade GPUs hinder its translation into real-time, point-of-care clinical workflows. This study presents a technical feasibility analysis of a Cloud-to-Edge optimization pipeline designed to transfer a 3D nnU-Net v2 model from a high-performance cloud environment to a resource-constrained embedded device. Experimental results showed that edge deployment was associated with a reduction in overlap-based segmentation metrics compared with the cloud reference, with Dice decreasing from approximately 0.78 to 0.67. However, TensorRT FP32 and FP16 inference produced nearly identical mean segmentation metrics, suggesting that reduced-precision inference did not introduce additional measurable degradation under the evaluated conditions. The optimized FP16 configuration achieved a processing time of 10.2 s per 3D volume, representing a 33% reduction compared with embedded FP32 inference, while operating within a low-power envelope of approximately 10\u201313 W. These findings support the preliminary technical feasibility of executing advanced 3D volumetric segmentation models on low-power edge hardware. Nevertheless, the evaluation was limited to an internal 25-case test subset and did not include external validation, prospective clinical assessment, or reader studies. Therefore, the proposed system should be interpreted as a preliminary deployment framework rather than a clinically validated tool for autonomous stroke imaging.<\/jats:p>","DOI":"10.3390\/s26113322","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T01:45:08Z","timestamp":1779673508000},"page":"3322","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cloud-to-Edge Deployment of Optimized nnU-Net for Ischemic Stroke Lesion Segmentation on Resource-Constrained Embedded Devices"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2332-531X","authenticated-orcid":false,"given":"Daniel","family":"Alcaraz-Ortiz","sequence":"first","affiliation":[{"name":"Escuela T\u00e9cnica Superior de Ingenier\u00eda Industrial, Campus Muralla del Mar, Universidad Polit\u00e9cnica de Cartagena, European University of Technology EUT+, C\/Doctor Fleming, s\/n, 30202 Cartagena, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7798-3928","authenticated-orcid":false,"given":"Juan Francisco","family":"Zapata-P\u00e9rez","sequence":"additional","affiliation":[{"name":"Escuela T\u00e9cnica Superior de Ingenier\u00eda Industrial, Campus Muralla del Mar, Universidad Polit\u00e9cnica de Cartagena, European University of Technology EUT+, C\/Doctor Fleming, s\/n, 30202 Cartagena, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5193-7800","authenticated-orcid":false,"given":"Juan","family":"Martinez-Alajarin","sequence":"additional","affiliation":[{"name":"Escuela T\u00e9cnica Superior de Ingenier\u00eda Industrial, Campus Muralla del Mar, Universidad Polit\u00e9cnica de Cartagena, European University of Technology EUT+, C\/Doctor Fleming, s\/n, 30202 Cartagena, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1016\/S1474-4422(21)00252-0","article-title":"Global, regional, and national burden of stroke and its risk factors, 1990\u20132019","volume":"20","author":"Feigin","year":"2021","journal-title":"Lancet Neurol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/S1474-4422(19)30034-1","article-title":"Global, regional, and national burden of stroke, 1990\u20132016: A systematic analysis","volume":"18","author":"Johnson","year":"2019","journal-title":"Lancet Neurol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1161\/01.STR.0000196957.55928.ab","article-title":"Time Is Brain\u2014Quantified","volume":"37","author":"Saver","year":"2006","journal-title":"Stroke"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1056\/NEJMoa1414905","article-title":"Randomized Assessment of Rapid Endovascular Treatment of Ischemic Stroke","volume":"372","author":"Goyal","year":"2015","journal-title":"N. Engl. J. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e46","DOI":"10.1161\/STR.0000000000000158","article-title":"2018 Guidelines for the Early Management of Patients With Acute Ischemic Stroke","volume":"49","author":"Powers","year":"2018","journal-title":"Stroke"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of MICCAI 2015, Munich, Germany, 5\u20139 October 2015, Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S.S., Brox, T., and Ronneberger, O. (2016). 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. Proceedings of MICCAI 2016, Athens, Greece, 17\u201321 October 2016, Springer.","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net v2: A Self-Configuring Method for Deep Learning-Based Biomedical Image Segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","article-title":"The Medical Segmentation Decathlon","volume":"13","author":"Antonelli","year":"2022","journal-title":"Nat. Commun."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"82031","DOI":"10.1109\/ACCESS.2021.3086020","article-title":"U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications","volume":"9","author":"Siddique","year":"2021","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Alam, M.S., Yakopcic, C., Wu, Q., Barnell, M., Khan, S., and Taha, T.M. (2024). Survey of Deep Learning Accelerators for Edge and Emerging Computing. Electronics, 13.","DOI":"10.20944\/preprints202407.0025.v1"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"100988","DOI":"10.1016\/j.patter.2024.100988","article-title":"AI deception: A survey of examples, risks, and potential solutions","volume":"5","author":"Park","year":"2024","journal-title":"Patterns"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101079","DOI":"10.1109\/ACCESS.2020.2997831","article-title":"Edge-Cloud Computing and Artificial Intelligence in Internet of Medical Things: Architecture, Technology and Application","volume":"8","author":"Sun","year":"2020","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Busnatu, \u0218., Niculescu, A.G., Bolocan, A., Petrescu, G.E.D., P\u0103duraru, D.N., N\u0103stas\u0103, I., Lupu\u0219oru, M., Geant\u0103, M., Andronic, O., and Grumezescu, A.M. (2022). Clinical Applications of Artificial Intelligence-An Updated Overview. J. Clin. Med., 11.","DOI":"10.3390\/jcm11082265"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.media.2016.07.009","article-title":"ISLES 2015\u2014A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI","volume":"35","author":"Maier","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Winzeck, S., Hakim, A., McKinley, R., Pinto, J.A., Alves, V., Silva, C., Pisov, M., Krivov, E., Belyaev, M., and Monteiro, M. (2018). ISLES 2016 and 2017\u2014Benchmarking ischemic stroke lesion outcome prediction based on multispectral MRI. Front. Neurol., 9.","DOI":"10.3389\/fneur.2018.00679"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1038\/s41597-022-01875-5","article-title":"ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset","volume":"9","author":"Hanning","year":"2022","journal-title":"Sci. Data"},{"key":"ref_18","unstructured":"de la Rosa, E., Reyes, M., Liew, S.L., Hutton, A., Wiest, R., Kaesmacher, J., Hanning, U., Hakim, A., Zubal, R., and Valenzuela, W. (2024). A Robust Ensemble Algorithm for Ischemic Stroke Lesion Segmentation: Generalizability and Clinical Utility Beyond the ISLES Challenge. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation","volume":"36","author":"Kamnitsas","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 12). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Isensee, F., Kickingereder, P., Wick, W., Bendszus, M., and Maier-Hein, K.H. (2018). No New-Net. BrainLes Workshop, Springer.","DOI":"10.1007\/978-3-030-11726-9_21"},{"key":"ref_23","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., and Zhou, Y. (2021). TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. arXiv."},{"key":"ref_24","unstructured":"Zhou, H., Guo, J., Zhang, Y., Yu, L., Wang, L., and Yu, Y. (2021). nnFormer: Interleaved Transformer for Volumetric Segmentation. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","article-title":"Edge Computing: Vision and Challenges","volume":"3","author":"Shi","year":"2016","journal-title":"IEEE Internet Things J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MC.2017.9","article-title":"The Emergence of Edge Computing","volume":"50","author":"Satyanarayanan","year":"2017","journal-title":"Computer"},{"key":"ref_27","unstructured":"Micikevicius, P., Narang, S., Alben, J., Diamos, G., Elsen, E., Garcia, D., Ginsburg, B., Houston, M., Kuchaiev, O., and Venkatesh, G. (2018). Mixed Precision Training. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., and Kalenichenko, D. (2018, January 18\u201323). Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref_29","unstructured":"Han, S., Pool, J., Tran, J., and Dally, W. (2015). Learning both Weights and Connections for Efficient Neural Networks. arXiv."},{"key":"ref_30","unstructured":"Blalock, D., Ortiz, J.G., Frankle, J., and Guttag, J. (2020). What is the State of Neural Network Pruning?. arXiv."},{"key":"ref_31","unstructured":"Chen, T., Moreau, T., Jiang, Z., Zheng, L., Yan, E., Shen, H., Cowan, M., Wang, L., Hu, Y., and Ceze, L. (2018, January 8\u201310). TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2018), Carlsbad, CA, USA. Available online: https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"10103","DOI":"10.1007\/s00500-021-05891-2","article-title":"Deploying a Smart Queuing System on Edge with Intel OpenVINO Toolkit","volume":"25","author":"Dagli","year":"2021","journal-title":"Soft Comput."},{"key":"ref_33","unstructured":"Jin, T., Bercea, G.T., Le, T.D., Chen, T., Su, G., Imai, H., Negishi, Y., Leu, A., O\u2019Brien, K., and Kawachiya, K. (2020). Compiling ONNX Neural Network Models Using MLIR. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/11\/3322\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T17:36:34Z","timestamp":1780076194000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/11\/3322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,23]]},"references-count":33,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26113322"],"URL":"https:\/\/doi.org\/10.3390\/s26113322","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,23]]}}}