Abstract
White matter hyperintensities (WMH) are commonly found in the brains of healthy elderly individuals and have been associated with various neurological and geriatric disorders. Automatic WMH segmentation is essential for evaluating the natural disease course and the efficacy of clinical interventions, especially drug discovery. This work presents a hybrid method, which combines the novel metaheuristic Slime Mold Algorithm with the Harris Hawk's Optimization algorithm to train the Deep Convolutional Neural Network (DCNN) as a robust model to optimize the Kapur’s entropy for WMH segmentation. We named it as Slime Mold Harris Hawk's Optimization-based DCNN (SMHHO-DCNN). The proposed method was tested on the open WMH segmentation challenge MICCAI 2017 and in-house dataset. However, the WMH regions would appear blurry and globally inconsistent. In order to solve the fuzzy problem, we improved the network architecture by incorporating skip connections across the mirrored layers with in encoder and decoder stacks. As a result, the segmented WMH output appears more realistic and coherent with its surrounding contexts, which enables the hybrid attention module to further enhance the precision of WMH localization by extracting the supporting information of high-level characteristics and low-level features. As a result, that the proposed hybrid optimization, skip connections, has increased the segmentation performance of Dice score to 87.2%, precision 90.3%, recall 89.5%, and f1-score 88.8% for MRI dataset which is superior compared to other approaches. The proposed technique outperformed existing state-of-the-art methodologies in both qualitative and quantitative measurements across a wide range of medical modalities. Furthermore, the dataset contains T1-w, T2-w, and FLAIR images, demonstrating the adaptability and robustness of the model.
Similar content being viewed by others
Data availability
The datasets analyzed during the current study are not publicly available due to individual privacy but are available from the corresponding author on reasonable request.
References
Chandra A, Verma S, Raghuvanshi A et al (2023) PCcS-RAU-Net: automated parcellated Corpus callosum segmentation from brain MRI images using modified residual attention U-Net. Biocybern Biomed Eng 43(2):403–427. https://doi.org/10.1016/j.bbe.2023.02.003
Huang F, Xia P, Vardhanabhuti V et al (2023) Semisupervised white matter hyperintensities segmentation on MRI. Hum Brain Mapp 44(4):1344–1358. https://doi.org/10.1002/hbm.26109
Todea AR, Melie-Garcia L, Barakovic M et al (2023) A Multicenter Longitudinal MRI Study Assessing LeMan-PV Software Accuracy in the Detection of White Matter Lesions in Multiple Sclerosis Patients. J Magn Reson Imaging. https://doi.org/10.1002/jmri.28618
Solé-Guardia G, Custers E, de Lange A et al (2023) Association between hypertension and neurovascular inflammation in both normal-appearing white matter and white matter hyperintensities. Acta Neuropathol Commun 11(1):2. https://doi.org/10.1186/s40478-022-01497-3
Balakrishnan Ramya, del Maria C, Hernández Valdés, Farrall Andrew J (2021) Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data – A systematic review. Comput Med Imaging Graphics. https://doi.org/10.1016/j.compmedimag.2021.101867
Gaubert Malo, Lange Catharina, Zimmermann, et al (2023) Performance evaluation of automated white matter hyperintensity segmentation algorithms in a multicenter cohort on cognitive impairment and dementia. Front Psychiatry. https://doi.org/10.3389/fpsyt.2022.1010273
Shehata LAO, Ibrahim O, El-Kammash TH et al (2023) Gad Brain volumetric and white matter structural connectivity alterations in autistic children case–control study. Egypt J Radiol Nucl Med. https://doi.org/10.1186/s43055-023-00985-3
Kuroda T, Ono K, Honma M et al (2023) Cerebral white matter lesions and regional blood flow are associated with reduced cognitive function in early-stage cognitive impairment. Front Aging Neurosci 16(15):1126618. https://doi.org/10.3389/fnagi.2023.1126618
Zhang H, Zhu C, Lian X, Hua F (2023) A Nested Attention Guided UNet++ Architecture for White Matter Hyperintensity Segmentation. IEEE Access. https://doi.org/10.1109/ACCESS.2023.3281201
Zhu W, Huang H, Zhou Y et al (2022) Automatic segmentation of white matter hyperintensities in routine clinical brain MRI by 2D VB-Net: a large-scale study. Front Aging Neurosci 14:915009. https://doi.org/10.3389/fnagi.2022.915009
Li X, Zhao Y, Jiang J et al (2022) White matter hyperintensities segmentation using an ensemble of neural networks. Hum Brain Mapp 43(3):929–939. https://doi.org/10.1002/hbm.25695
Zhang Y, Duan Y, Wang X et al (2022) A deep learning algorithm for white matter hyperintensity lesion detection and segmentation. Neuroradiology 64:727–734. https://doi.org/10.1007/s00234-021-02820-w
Pious AE, Sridevi UK (2023) A novel segment white matter hyperintensities approach for detecting Alzheimer. Comput Syst Sci Eng 44(3):2715–2726
Park G, Hong J, Duffy BA et al (2021) White matter hyperintensities segmentation using the ensemble U-Net with multi-scale highlighting foregrounds. Neuroimage 237:118140. https://doi.org/10.1016/j.neuroimage.2021.118140
Li H, Jiang G, Zhang J et al (2018) Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images. Neuroimage 183:650–665. https://doi.org/10.1016/j.neuroimage.2018.07.005
Thawkar S (2022) Feature selection and classification in mammography using hybrid crow search algorithm with Harris hawk’s optimization. Biocyber Biomed Eng 42(4):1094–1111. https://doi.org/10.1016/j.bbe.2022.09.001
Tran P, Thoprakarn U, Gourieux E et al (2022) Automatic segmentation of white matter hyperintensities: validation and comparison with state-of-the-art methods on both Multiple Sclerosis and elderly subjects. NeuroImage Clin 33:102940. https://doi.org/10.1016/j.nicl.2022.102940
Yang D, Masurkar A (2022) Early-stage MRI volumetric differences in white matter hyperintensity and temporal lobe volumes between autopsy-confirmed alzheimer’s disease, cerebral small vessel disease, and mixed pathologies. Dement Geriatr Cogn Dis Extra 12(1):69–75. https://doi.org/10.1159/000524499
Moeskops P, de Bresser J, Kuijf HJ et al (2018) Evaluation of a deep learning approach for the segmentation of brain tissues and white matter hyperintensities of presumed vascular origin in MRI. Neuroimage Clin 17:251–262. https://doi.org/10.1016/j.nicl.2017.10.007
Dadar Mahsa, Manera Ana Laura, Ducharme Simon et al (2022) White matter hyperintensities are associated with grey matter atrophy and cognitive decline in Alzheimer’s disease and frontotemporal dementia. Neurobio Aging 111:54–63. https://doi.org/10.1016/j.neurobiolaging.2021.11.007
Zhang D, Zhu P, Yin B et al (2021) Frontal white matter hyperintensities effect on default mode network connectivity in acute mild traumatic brain injury. Front Aging Neurosci. https://doi.org/10.3389/fnagi.2021.793491
Aetesam Hazique, Maji Suman Kumar (2021) Noise dependent training for deep parallel ensemble denoising in magnetic resonance images. Biomed Signal Process Control 66:102405. https://doi.org/10.1016/j.bspc.2020.102405
Wang J, Zhou Y, He Y et al (2022) Impact of different white matter hyperintensities patterns on cognition: a cross-sectional and longitudinal study. NeuroImage Clin. https://doi.org/10.1016/j.nicl.2022.102978
Ami Tsuchida, Philippe Boutinaud, Violaine Verrecchia, et al. (2023) Early detection of white matter hyperintensities using SHIVA-WMH detector. bioRxiv. doi: https://doi.org/10.1101/2023.02.03.526961
Gautam A, Raman B, Raghuvanshi S (2018) A hybrid approach for the delineation of brain lesion from CT images. Biocyber Biomed Eng 38(3):504–518. https://doi.org/10.1016/j.bbe.2018.04.003
Parent O, Bussy A, Devenyi GA et al. (2023) Assessment of white matter hyperintensity severity using multimodal MRI in Alzheimer′s Disease. bioRxiv. doi: https://doi.org/10.1101/2023.01.20.524929.
Lai M, Lee J, Li X et al (2023) Lifestyle changes reduced estimated white matter hyperintensities based on retinal image analysis. Int J Environ Res Public Health 20(4):3530. https://doi.org/10.3390/ijerph20043530
Sandrone S, Aiello M, Cavaliere C et al (2023) Mapping myelin in white matter with T1-weighted/T2-weighted maps: discrepancy with histology and other myelin MRI measures. Brain Struct Funct 228:525–535. https://doi.org/10.1007/s00429-022-02600-z
Rieu Z, Kim J, Kim RE et al (2021) Semi-Supervised Learning in Medical MRI Segmentation: Brain Tissue with White Matter Hyperintensity Segmentation Using FLAIR MRI. Brain Science 11:720. https://doi.org/10.3390/brainsci11060720
Rehan Afzal HM, Luo S, Ramadan S et al (2021) Automatic and robust segmentation of multiple sclerosis lesions with convolutional neural networks. Comput Mater Contin 66(1):977–991. https://doi.org/10.32604/cmc.2020.012448
Guo X, Ye C, Yang Y et al (2022) Ensemble learning via supervision augmentation for white matter hyperintensity segmentation. Front Neurosci 16:946343. https://doi.org/10.3389/fnins.2022.946343
Rajwar K, Deep K, Das S (2023) An exhaustive review of the metaheuristic algorithms for search and optimization: taxonomy, applications, and open challenges. Artif Intell Rev 56:13187–13257. https://doi.org/10.1007/s10462-023-10470-y
Xue T, Zhang F, Zhang C et al (2023) Superficial white matter analysis: an efficient point-cloud-based deep learning framework with supervised contrastive learning for consistent tractography parcellation across populations and dMRI acquisitions. Med Image Anal 85:102759. https://doi.org/10.1016/j.media.2023.102759
Cuesta P, Chino B, Orozco LH et al (2023) The effects of white matter hyperintensities on MEG power spectra in population with mild cognitive impairment. Front Human Neurosci. https://doi.org/10.3389/fnhum.2023.1068216
Li W, Yuan J, Han F et al (2023) White matter and gray matter changes related to cognition in community populations. Front Aging Neurosci. https://doi.org/10.3389/fnagi.2023.1065245
Ashina H, Christensen RH, Al-Khazali HM et al (2023) White matter hyperintensities and cerebral microbleeds in persistent post-traumatic headache attributed to mild traumatic brain injury: a magnetic resonance imaging study. J Headache Pain 24(1):15. https://doi.org/10.1186/s10194-023-01545-w
Schilling KG, Li M, Rheault F, et al. (2023) Whole-brain, gray and white matter time-locked functional signal changes with simple tasks and model-free analysis. bioRxiv. doi:https://doi.org/10.1101/2023.02.14.528557
Arola A, Laakso HM, Pitkänen J et al (2021) Associations of cognitive reserve and psychological resilience with cognitive functioning in subjects with cerebral white matter hyperintensities. Eur J Neurol 28(8):2622–2630. https://doi.org/10.1111/ene.14910
Swetha MD, Aditya CR (2022) Sparse feature aware noise removal technique for brain multiple sclerosis lesions using magnetic resonance imaging. Int J Adv Comput Sci Appl (IJACSA) 13(6):527–533. https://doi.org/10.14569/ijacsa.2022.0130664
Bhutto JA, Tian L, Du Q et al (2022) CT and MRI medical image fusion using noise-removal and contrast enhancement scheme with convolutional neural network. Entropy 24:393. https://doi.org/10.3390/e24030393
Becktepe JS, Busse J, Jensen-Kondering U et al (2021) White matter hyperintensities are associated with severity of essential tremor in the elderly. Front Neurol 12:694286. https://doi.org/10.3389/fneur.2021.694286
Gwo C-Y, Zhu DC, Zhang R (2019) Brain white matter hyperintensity lesion characterization in T2 fluid-attenuated inversion recovery magnetic resonance images: shape, texture, and potential growth. Front Neurosci 13:353. https://doi.org/10.3389/fnins.2019.00353
Heidari Ali Asghar, Mirjalili Seyedali, Faris Hossam et al (2019) Harris Hawks optimization: Algorithm and applications. Futur Gener Comput Syst 97:849–872. https://doi.org/10.1016/j.future.2019.02.028
Li S, Chen H, Wang M et al (2020) Slime mould algorithm: a new method for stochastic optimization. Futur Gener Comput Syst 111:300–323. https://doi.org/10.1016/j.future.2020.03.055
Rathore S, Niazi T, Iftikhar MA et al (2020) Multimodal ensemble-based segmentation of white matter lesions and analysis of their differential characteristics across major brain regions. Appl Sci 10:1903. https://doi.org/10.3390/app10061903
Abdel-Basset M, Chang V, Mohamed R (2020) HSMA_WOA: a hybrid novel Slime mould algorithm with whale optimization algorithm for tackling the image segmentation problem of chest X-ray images. Appl Soft Comput 95:106642. https://doi.org/10.1016/j.asoc.2020.106642
Di Martino F, Sessa S (2020) PSO Image thresholding on images compressed via fuzzy transforms. Inf Sci 506:308–324. https://doi.org/10.1016/j.ins.2019.07.088
Xu Y, Géraud T, Puybareau É et al (2018) White matter hyperintensities segmentation in a few seconds using fully convolutional network and transfer learning. Lect Notes Comput Sci. https://doi.org/10.1007/978-3-319-75238-9_42
Huo F, Sun X, Ren W (2020) Multilevel image threshold segmentation using an improved bloch quantum artificial bee colony algorithm. Multimed Tools Appl 79(3):2447–2471. https://doi.org/10.1007/s11042-019-08231-7
El Aziz MA, Ewees AA, Hassanien AE (2017) Whale optimization algorithm and moth-flame optimization for multilevel thresholding image segmentation. Expert Syst Appl 83:242–256. https://doi.org/10.1016/j.eswa.2017.04.023
Diaz-Hurtado M, Martínez-Heras E, Solana E et al (2022) Recent advances in the longitudinal segmentation of multiple sclerosis lesions on magnetic resonance imaging: a review. Neuroradiology 64(11):2103–2117. https://doi.org/10.1007/s00234-022-03019-3
Kuijf HJ, Biesbroek JM, Bresser JD et al (2019) Standardized assessment of automatic segmentation of white matter hyperintensities and results of the WMH segmentation challenge. IEEE Trans Med Imaging 38:2556–2568. https://doi.org/10.1109/TMI.2019.2905770
Tubi MA, Feingold FW, Kothapalli D et al (2020) Alzheimer’s disease neuroimaging initiative white matter hyperintensities and their relationship to cognition: effects of segmentation algorithm. Neuroimage 206:116327. https://doi.org/10.1016/j.neuroimage.2019.116327
Zhang H, Cui Y, Zhao Y et al (2019) Effects of sartans and low-dose statins on cerebral white matter hyperintensities and cognitive function in older patients with hypertension: a randomized, double-blind and placebo-controlled clinical trial. Hypertens Res 42(5):717–729. https://doi.org/10.1038/s41440-018-0165-7
Zhao Y, Ke Z, He W et al (2019) Volume of white matter hyperintensities increases with blood pressure in patients with hypertension. J Int Med Res 47(8):3681–3689. https://doi.org/10.1177/0300060519858023
Chakraborty NF, Nandi D, Roy PK (2019) Oppositional symbiotic organisms search optimization for multilevel thresholding of color image. Appl Soft Computing 82:105577. https://doi.org/10.1016/j.asoc.2019.105577
Zhao X, Ke C, Ang E et al (2021) Application of Artificial Intelligence techniques for the detection of Alzheimer’s disease using structural MRI images. Biocyber Biomed Eng 41(2):456–473. https://doi.org/10.1016/j.bbe.2021.02.006
Langen CD, Cremers LGM, de Groot M et al (2018) Disconnection due to white matter hyperintensities is associated with lower cognitive scores. Neuroimage 183:745–756. https://doi.org/10.1016/j.neuroimage.2018.08.037
Kynast J, Lampe L, Luck T et al (2018) White matter hyperintensities associated with small vessel disease impair social cognition beside attention and memory. J Cereb Blood Flow Metab 38(6):996–1009. https://doi.org/10.1177/0271678X17719380
Devi CN, Chandrasekharan A, V.K., S., et al (2018) Automatic segmentation of infant brain MR images: With special reference to myelinated white matter. Biocyber Biomed Eng 37(1):143–158. https://doi.org/10.1016/j.bbe.2016.11.004
Li Y, Li M, Zhang X et al (2017) Higher blood-brain barrier permeability is associated with higher white matter hyperintensities burden. J Neurol 264(7):1474–1481. https://doi.org/10.1007/s00415-017-8550-8
Çelik G, Talu MF (2022) A new 3D MRI segmentation method based on generative adversarial network and atrous convolution. Biomed Signal Process Control 71:103155. https://doi.org/10.1016/j.bspc.2021.103155
Acknowledgments
We would like to express our sincere appreciation and gratitude to Dr. Surendra Nath Senapati, Department of Radiation Oncology, SCB Medical College & Hospital, Cuttack, India, for his invaluable contribution to the clinical validation of our research work.
Funding
No funding was received for conducting this study.
Author information
Authors and Affiliations
Contributions
Puranam Revanth Kumar helped in conceptualization, methodology, software, data collection, implementation, and writing—original draft preparation. Rajesh Kumar Jha helped in data collection, visualization, writing—review, and supervision. P Akhendra Kumar helped in visualization, writing—review, and supervision (support).
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Ethical Approval
Not applicable.
Consent to Participate
Not Applicable.
Consent to Publish
I, the corresponding author, give my consent for the publication in the journal.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kumar, P.R., Jha, R.K. & Kumar, P.A. Brain hyperintensities: automatic segmentation of white matter hyperintensities in clinical brain MRI images using improved deep neural network. J Supercomput (2024). https://doi.org/10.1007/s11227-024-06080-2
Accepted:
Published:
DOI: https://doi.org/10.1007/s11227-024-06080-2