{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:52:40Z","timestamp":1781643160768,"version":"3.54.5"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":74,"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>White matter hyperintensities (WMHs) are common radiological findings in brain magnetic resonance imaging (MRI) and are strongly associated with neurological disorders such as stroke, dementia, and multiple sclerosis. Accurate detection and segmentation of WMHs are crucial for early diagnosis, disease progression analysis, and treatment planning. However, manual delineation of WMHs is labour-intensive, time-consuming, and prone to inter-observer variability, which limits its practicality in large-scale clinical and research settings. Deep learning has shown promise in automating WMH analysis; however, challenges remain due to heterogeneous lesion sizes, low contrast boundaries, and imaging noise. We propose a Deep Optimization-Guided Hybrid Neural Network (DOGHNN) that combines Inception-v3, ResNet-50, and Practical Swarm Optimization (PSO) for enhanced WMH segmentation. Inception-v3 is employed to capture multi-scale lesion features, enabling the detection of both small punctate and large confluent WMHs. ResNet-50 is integrated to extract deep contextual representations, leveraging residual learning to distinguish true lesions from surrounding tissue and artifacts. Finally, PSO is incorporated as an optimization strategy to iteratively refine fusion weights, segmentation thresholds, and key parameters, minimizing segmentation loss and improving boundary delineation. This hybrid approach ensures both fine-grained lesion sensitivity and robust global feature learning. The DOGHNN framework was evaluated on benchmark WMH MRI datasets with diverse lesion loads and anatomical complexities. Comparative experiments showed superior performance over baseline deep learning models. Quantitative evaluation yielded a maximum precision of 93.2%, recall of 91.5%, dice score 91.1%, and f1-score of 90.5% were achieved by the suggested DOGHNN, and Hausdorff distance of 6.5, confirming its robustness and reliability. By combining multi-scale learning, residual contextual modelling, and optimization-driven refinement, the DOGHNN framework delivers accurate and efficient WMH segmentation. This approach holds strong potential for clinical integration, supporting automated neuroimaging workflows and improving diagnostic decision-making in neurological care.<\/jats:p>","DOI":"10.1038\/s41598-026-41137-7","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T13:33:29Z","timestamp":1773408809000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep optimization-guided hybrid neural network for accurate detection and segmentation of white matter hyperintensities in clinical MRI images"],"prefix":"10.1038","volume":"16","author":[{"given":"Bharathi","family":"Panduri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"O. Srinivasa","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"key":"41137_CR1","unstructured":"Cheng, Y. et al. Federated Spatial Prior-Based Source-Free Domain Adaptation for White Matter Hyperintensities Segmentation. IEEE J. biomedical health informatics, pp. 1\u201314. (2025)."},{"key":"41137_CR2","unstructured":"Bawil, M. B., Shamsi, M. & Bavil, A. S. Simultaneous Segmentation of Ventricles and Normal\/Abnormal White Matter Hyperintensities in Clinical MRI using Deep Learning. (2025). arXiv preprint arXiv:2506.07123."},{"key":"41137_CR3","doi-asserted-by":"crossref","unstructured":"Agarwal, R., Ghosal, P., Sadhu, A. K., Murmu, N. & Nandi, D. Multi-scale dual-channel feature embedding decoder for biomedical image segmentation Vol. 257, 108464 (Computer Methods and Programs in Biomedicine, 2024).","DOI":"10.1016\/j.cmpb.2024.108464"},{"key":"41137_CR4","doi-asserted-by":"crossref","unstructured":"Alamoudi, N., Hern\u00e1ndez, M. V., Seth, S., Wardlaw, J. M. & Bernabeu, M. O. Robust Windowing Harmonisation for Improved Cross-Scanner Generalisation of White Matter Hypoattenuation Segmentation in Brain CT Clinical Scans. In International Conference on AI in Healthcare (pp. 382\u2013395). Cham: Springer Nature Switzerland. (2025), August.","DOI":"10.1007\/978-3-032-00656-1_28"},{"key":"41137_CR5","doi-asserted-by":"crossref","unstructured":"Puranam, R., Kumar, B. & Shilpa, R. K. Jha BrainTract: segmentation of white matter fiber tractography and analysis of structural connectivity using hybrid convolutional neural network, Neuroscience, 580, pp. 218\u2013230, (2025).","DOI":"10.1016\/j.neuroscience.2025.06.043"},{"issue":"6","key":"41137_CR6","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/s42979-025-04101-2","volume":"6","author":"MRA Banu","year":"2025","unstructured":"Banu, M. R. A., Rao, K. P. & Gupta, A. Accurate Human Brain Tissue Segmentation in MRI Scans Using Optimized Deep Neural Network. SN Comput. Sci. 6 (6), 614 (2025).","journal-title":"SN Comput. Sci."},{"key":"41137_CR7","doi-asserted-by":"crossref","unstructured":"U\u00e7ar, G. & Dandil, E. Enhanced detection of white matter hyperintensities via deep learning-enabled MR imaging segmentation. Traitement du Signal., 41(1). (2024).","DOI":"10.18280\/ts.410101"},{"key":"41137_CR8","doi-asserted-by":"publisher","first-page":"107904","DOI":"10.1016\/j.cmpb.2023.107904","volume":"243","author":"S Mu","year":"2024","unstructured":"Mu, S., Lu, W., Yu, G., Zheng, L. & Qiu, J. Deep learning-based grading of white matter hyperintensities enables identification of potential markers in multi-sequence MRI data. Comput. Methods Programs Biomed. 243, 107904 (2024).","journal-title":"Comput. Methods Programs Biomed."},{"key":"41137_CR9","doi-asserted-by":"publisher","first-page":"1416174","DOI":"10.3389\/fnins.2024.1416174","volume":"18","author":"MB Bawil","year":"2024","unstructured":"Bawil, M. B., Shamsi, M., Bavil, A. S. & Danishvar, S. Specialized gray matter segmentation via a generative adversarial network: application on brain white matter hyperintensities classification. Front. NeuroSci. 18, 1416174 (2024).","journal-title":"Front. NeuroSci."},{"key":"41137_CR10","doi-asserted-by":"crossref","unstructured":"Gibson, E. et al. segcsvdWMH: A Convolutional Neural Network-Based Tool for Quantifying White Matter Hyperintensities in Heterogeneous Patient Cohorts Vol. 45 (Clinical, 2024). 18e70104.","DOI":"10.1002\/hbm.70104"},{"key":"41137_CR11","doi-asserted-by":"crossref","unstructured":"Philps, B. et al. M. O. Stochastic uncertainty quantification techniques fail to account for inter-analyst variability in white matter hyperintensity segmentation. In Annual Conference on Medical Image Understanding and Analysis (pp. 34\u201353). Cham: Springer Nature Switzerland. (2024), July.","DOI":"10.1007\/978-3-031-66955-2_3"},{"issue":"4","key":"41137_CR12","doi-asserted-by":"publisher","first-page":"1344","DOI":"10.1002\/hbm.26109","volume":"44","author":"F Huang","year":"2023","unstructured":"Huang, F. et al. Semisupervised white matter hyperintensities segmentation on MRI. Hum. Brain. Mapp. 44 (4), 1344\u20131358 (2023).","journal-title":"Hum. Brain. Mapp."},{"key":"41137_CR13","doi-asserted-by":"publisher","first-page":"103547","DOI":"10.1016\/j.nicl.2023.103547","volume":"40","author":"M Coenen","year":"2023","unstructured":"Coenen, M. et al. Spatial distributions of white matter hyperintensities on brain MRI: A pooled analysis of individual participant data from 11 memory clinic cohorts. NeuroImage: Clin. 40, 103547 (2023).","journal-title":"NeuroImage: Clin."},{"key":"41137_CR14","doi-asserted-by":"publisher","first-page":"66910","DOI":"10.1109\/ACCESS.2023.3281201","volume":"11","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Zhu, C., Lian, X. & Hua, F. A Nested attention guided UNet\u2009+\u2009+\u2009architecture for white matter hyperintensity segmentation. IEEE Access. 11, 66910\u201366920 (2023).","journal-title":"IEEE Access."},{"key":"41137_CR15","doi-asserted-by":"publisher","first-page":"106596","DOI":"10.1016\/j.engappai.2023.106596","volume":"125","author":"R Pilli","year":"2023","unstructured":"Pilli, R., Goel, T., Murugan, R. & Tanveer, M. Association of white matter volume with brain age classification using deep learning network and region wise analysis. Eng. Appl. Artif. Intell. 125, 106596 (2023).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"41137_CR16","doi-asserted-by":"crossref","unstructured":"Eldianto, M. N. D., Rachmadi, M. F. & Jatmiko, W. White Matter Hyperintensities Segmentation Using Probabilistic TransUNet. In 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE) (pp. 134\u2013139). IEEE. (2023), February.","DOI":"10.1109\/ICCoSITE57641.2023.10127707"},{"issue":"4","key":"41137_CR17","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/s00234-021-02820-w","volume":"64","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y. et al. A deep learning algorithm for white matter hyperintensity lesion detection and segmentation. Neuroradiology 64 (4), 727\u2013734 (2022).","journal-title":"Neuroradiology"},{"key":"41137_CR18","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.patrec.2023.07.014","volume":"175","author":"KT Duarte","year":"2023","unstructured":"Duarte, K. T. et al. Segmenting white matter hyperintensities in brain magnetic resonance images using convolution neural networks. Pattern Recognit. Lett. 175, 90\u201394 (2023).","journal-title":"Pattern Recognit. Lett."},{"key":"41137_CR19","doi-asserted-by":"crossref","unstructured":"Ghosal, P. et al. MhURI:A Supervised Segmentation Approach to Leverage Salient Brain Tissues in Magnetic Resonance Images Vol. 200, 105841 (Computer Methods and Programs in Biomedicine, 2021).","DOI":"10.1016\/j.cmpb.2020.105841"},{"key":"41137_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10792-024-03279-3","volume":"44","author":"PR Kumar","year":"2024","unstructured":"Kumar, P. R. & Shilpa, B. Jha, and Veni Sree Chellibouina Spatial Attention U-Net Model with Harris Hawks Optimization for Retinal Blood Vessel and Optic Disc Segmentation in Fundus Images. Int. Ophthalmol. 44, 1\u201313 (2024).","journal-title":"Int. Ophthalmol."},{"issue":"3","key":"41137_CR21","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.imed.2023.10.001","volume":"4","author":"PR Kumar","year":"2024","unstructured":"Kumar, P. R., Jha, R. K., Akhendra Kumar, P. & Deevena Raju, B. Improved neurological diagnoses and treatment strategies via automated human brain tissue segmentation from clinical magnetic resonance imaging. Intell. Med. 4 (3), 161\u2013169 (2024).","journal-title":"Intell. Med."},{"issue":"6","key":"41137_CR22","doi-asserted-by":"publisher","first-page":"720","DOI":"10.3390\/brainsci11060720","volume":"11","author":"Z Rieu","year":"2021","unstructured":"Rieu, Z. et al. Semi-supervised learning in medical MRI segmentation: brain tissue with white matter hyperintensity segmentation using FLAIR MRI. Brain Sci. 11 (6), 720 (2021).","journal-title":"Brain Sci."},{"key":"41137_CR23","doi-asserted-by":"publisher","first-page":"15545","DOI":"10.1007\/s11227-024-06080-2","volume":"80","author":"PR Kumar","year":"2024","unstructured":"Kumar, P. R., Jha, R. K. & Akhendra Kumar, P. BrainHyperintensities: Automatic Segmentation of White Matter Hyperintensities in Clinical Brain MRI Images using Improved Deep Neural Network. J. Supercomputing. 80, 15545\u201315581 (2024).","journal-title":"J. Supercomputing"},{"key":"41137_CR24","doi-asserted-by":"publisher","first-page":"681183","DOI":"10.3389\/fmed.2021.681183","volume":"8","author":"W Shan","year":"2021","unstructured":"Shan, W. et al. Segmentation of cerebral small vessel diseases-white matter hyperintensities based on a deep learning system. Front. Med. 8, 681183 (2021).","journal-title":"Front. Med."},{"key":"41137_CR25","doi-asserted-by":"crossref","unstructured":"Umapathy, L. et al. A stacked generalization of 3D orthogonal deep learning convolutional neural networks for improved detection of white matter hyperintensities in 3D FLAIR images. Am. J. Neuroradiol. 42 (4), 639\u2013647 (2021). \u2026 Alzheimer\u2019s Disease Neuroimaging Initiative.","DOI":"10.3174\/ajnr.A6970"},{"key":"41137_CR26","doi-asserted-by":"crossref","unstructured":"Vanderbecq, Q. et al. \u2026 Alzheimer\u2019s Disease Neuroimaging Initiative. Comparison and validation of seven white matter hyperintensities segmentation software in elderly patients. NeuroImage: Clinical, 27, 102357. (2020).","DOI":"10.1016\/j.nicl.2020.102357"},{"key":"41137_CR27","doi-asserted-by":"crossref","unstructured":"Ding, T. et al. An improved algorithm of white matter hyperintensity detection in elderly adults Vol. 25, 102151 (Clinical, 2020).","DOI":"10.1016\/j.nicl.2019.102151"},{"key":"41137_CR28","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.neucom.2019.12.050","volume":"384","author":"L Liu","year":"2020","unstructured":"Liu, L. et al. Deep convolutional neural network for accurate segmentation and quantification of white matter hyperintensities. Neurocomputing 384, 231\u2013242 (2020).","journal-title":"Neurocomputing"},{"issue":"10","key":"41137_CR29","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1007\/s00234-020-02410-2","volume":"62","author":"J Pitk\u00e4nen","year":"2020","unstructured":"Pitk\u00e4nen, J. et al. Evaluating severity of white matter lesions from computed tomography images with convolutional neural network. Neuroradiology 62 (10), 1257\u20131263 (2020).","journal-title":"Neuroradiology"},{"key":"41137_CR30","doi-asserted-by":"publisher","first-page":"612928","DOI":"10.3389\/fphys.2020.612928","volume":"11","author":"Z Wang","year":"2020","unstructured":"Wang, Z. et al. 3D compressed convolutional neural network differentiates neuromyelitis optical spectrum disorders from multiple sclerosis using automated white matter hyperintensities segmentations. Front. Physiol. 11, 612928 (2020).","journal-title":"Front. Physiol."},{"key":"41137_CR31","doi-asserted-by":"crossref","unstructured":"Hong, J. et al. Two-step deep neural network for segmentation of deep white matter hyperintensities in migraineurs Vol. 183, 105065 (Computer Methods and Programs in Biomedicine, 2020).","DOI":"10.1016\/j.cmpb.2019.105065"},{"key":"41137_CR32","doi-asserted-by":"publisher","first-page":"150","DOI":"10.3389\/fnagi.2019.00150","volume":"11","author":"Y Jeong","year":"2019","unstructured":"Jeong, Y., Rachmadi, M. F., Vald\u00e9s-Hern\u00e1ndez, M. D. C. & Komura, T. Dilated saliency u-net for white matter hyperintensities segmentation using irregularity age map. Front. Aging Neurosci. 11, 150 (2019).","journal-title":"Front. Aging Neurosci."},{"key":"41137_CR33","doi-asserted-by":"crossref","unstructured":"Wei, K. et al. White matter hypointensities and hyperintensities have equivalent correlations with age and CSF \u03b2-amyloid in the nondemented elderly. Brain Behav., 9(12), e01457. (2019).","DOI":"10.1002\/brb3.1457"},{"key":"41137_CR34","doi-asserted-by":"crossref","unstructured":"Kumar, P. R., Shilpa, B., Jha, R. K., Deevena Raju, B. & Mohammed, T. K. Inpainting Non-Anatomical Objects in Brain Imaging using Enhanced Deep Convolutional Autoencoder Network, Sadhana, vol. 49, article number 181, pp. 1\u201313, (2024).","DOI":"10.1007\/s12046-024-02536-6"},{"key":"41137_CR35","unstructured":"Baur, C., Wiestler, B., Albarqouni, S. & Navab, N. Fusing unsupervised and supervised deep learning for white matter lesion segmentation. In International Conference on Medical Imaging with Deep Learning (pp. 63\u201372). PMLR. (2019), May."},{"key":"41137_CR36","doi-asserted-by":"crossref","unstructured":"Puranam, R., Kumar, B., Shilpa & Kumar, R. Jha Brain disorders: Impact of mild SARS-CoV-2 may shrink several parts of the brain. Neurosci. Biobehavioral Reviews, 149, p.105150, (2023).","DOI":"10.1016\/j.neubiorev.2023.105150"},{"key":"41137_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13760-023-02170-9","volume":"124","author":"PR Kumar","year":"2023","unstructured":"Kumar, P. R. Jha, and Amogh Katti Brain Tissues Segmentation in Neurosurgery: A Systematic Analysis for Quantitative Tractography Approaches. Acta Neurol. Belgica. 124, 1\u201315 (2023).","journal-title":"Acta Neurol. Belgica"},{"key":"41137_CR38","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1016\/j.nicl.2018.02.033","volume":"18","author":"BY Park","year":"2018","unstructured":"Park, B. Y. et al. DEWS (DEep White matter hyperintensity Segmentation framework): A fully automated pipeline for detecting small deep white matter hyperintensities in migraineurs. NeuroImage: Clin. 18, 638\u2013647 (2018).","journal-title":"NeuroImage: Clin."},{"key":"41137_CR39","first-page":"4223","volume":"15","author":"PR Kumar","year":"2023","unstructured":"Kumar, P. R., Shilpa, B., Jha, R. K. & Mohanty, S. N. A novel end\u2013to\u2013end approach for epileptic seizure classification from scalp EEG data using deep learning technique. Int. J. Inform. Technol. 15, 4223\u20134231 (2023).","journal-title":"Int. J. Inform. Technol."},{"key":"41137_CR40","first-page":"501","volume-title":"International MICCAI Brainlesion Workshop","author":"Y Xu","year":"2017","unstructured":"Xu, Y., G\u00e9raud, T., Puybareau, \u00c9., Bloch, I. & Chazalon, J. White matter hyperintensities segmentation in a few seconds using fully convolutional network and transfer learning. In International MICCAI Brainlesion Workshop (501\u2013514). Cham: Springer. (2017), September."},{"key":"41137_CR41","doi-asserted-by":"crossref","unstructured":"Kumar, P. R., Mohammad, T. K., Kumar, A. P., Kassym, R. & Akmaral, T. Tolegenova A. S, and Synthesizing Multi-Modal Imaging for Enhanced Brain Mapping in Neurology: A State-of-the-art Review, 5th International Conference on Communications, Information, Electronic and Energy Systems (CIEES), pp. 1\u20136, (2025).","DOI":"10.1109\/CIEES62939.2024.10811448"},{"key":"41137_CR42","doi-asserted-by":"crossref","unstructured":"Kumar, P. R., Jha, R. K. & Akhendra Kumar, P. Segmentation of White Matter Lesions in MRI Images Using Optimization-based Deep Neural Network, 4th International Conference on Image Processing and Capsule Networks, pp. 253\u2013267, (2023).","DOI":"10.1007\/978-981-99-7093-3_17"},{"key":"41137_CR43","doi-asserted-by":"crossref","unstructured":"Kumar, P. R., Sangeetha, K., Rabi Narayan Satpathy & Mohanty, S. N. A Comprehensive analysis on EEG Signal Classification on Human Brain, 9th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO), pp. 1\u20136, (2021).","DOI":"10.1109\/ICRITO51393.2021.9596296"},{"key":"41137_CR44","doi-asserted-by":"crossref","unstructured":"Ithapu, V., Singh, V., Lindner, C., Austin, B. P., Hinrichs, C., Carlsson, C. M.,\u2026 Johnson, S. C. (2014). Extracting and summarizing white matter hyperintensities using supervised segmentation methods in Alzheimer\u2019s disease risk and aging studies.Human Brain Mapping, 35(8), 4219\u20134235.","DOI":"10.1002\/hbm.22472"},{"key":"41137_CR45","doi-asserted-by":"crossref","unstructured":"Tsai, J. Z., Peng, S. J., Chen, Y. W., Wang, K. W., Li, C. H., Wang, J. Y., \u2026 Hsin,Y. L. (2014). Automated segmentation and quantification of white matter hyperintensities in acute ischemic stroke patients with cerebral infarction. PloS One, 9(8), e104011.","DOI":"10.1371\/journal.pone.0104011"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-41137-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-41137-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-41137-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:01:57Z","timestamp":1781640117000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-41137-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["41137"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-41137-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]},"assertion":[{"value":"28 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2026","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":"16211"}}