Abstract
Voxel-based morphometry is an analysis technique used to quantify matter volume in the human brain from magnetic resonance imaging studies. Atrophies and morphologic changes can be signs of neuronal depletion that can lead to various degenerative diseases. Two of the most worldwide used tools for brain volume assessment and segmentation in white matter, grey matter, and cerebrospinal fluid are the Functional Magnetic Resonance Imaging of the Brain (FMRIB) Software Library (FSL) and Statistical Parameter Mapping (SPM). However, the main issue of these tools is related to the choice of the best parameter setting.
In this paper, a novel and unsupervised segmentation system, without any user parameter setting, that uses both the k-means clustering algorithm and artificial neural network is proposed. Performance of this system was evaluated on the Internet Brain Segmentation Repository (IBSR) dataset (v.2.0) and results were compared with FSL and SPM results.
The dice similarity score was calculated to compare the segmentations obtained with FSL, SPM, and the proposed system with the reference segmentations. The proposed system resulted fast and reliable, and reduced any error (the dice similarity score was greater than 83%, 86%, and 65% for white matter, grey matter, and cerebrospinal fluid, respectively) demonstrating an improvement in the discrimination among white matter, grey matter, and cerebrospinal fluid.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Dora, L., Agrawal, S., Panda, R., Abraham, A.: State-of-the-art methods for brain tissue segmentation: a review (2017)https://doi.org/10.1109/RBME.2017.2715350
Comelli, A., et al.: Tissue classification to support local active delineation of brain tumors. In: Zheng, Y., Williams, B.M., Chen, K.E. (eds.) MIUA 2019. CCIS, vol. 1065, pp. 3–14. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39343-4_1
Staffaroni, A.M., et al.: Neuroimaging in dementia. Semin. Neurol. 37, 510–537 (2017). https://doi.org/10.1055/s-0037-1608808
Alongi, P., et al.: 18F-Florbetaben PET/CT to assess Alzheimer’s disease: a new analysis method for regional amyloid quantification. J. Neuroimaging. 29, 383–393 (2019). https://doi.org/10.1111/jon.12601
Alongi, P., et al.: Radiomics analysis of brain [18F]FDG PET/CT to predict Alzheimer’s disease in patients with amyloid PET positivity: a preliminary report on the application of SPM cortical segmentation. Pyradiom. Mach. Learn. Anal. Diagn. 12, 933 (2022). https://doi.org/10.3390/diagnostics12040933
Griffanti, L., et al.: Classification and characterization of periventricular and deep white matter hyperintensities on MRI: a study in older adults. Neuroimage 170, 174–181 (2018). https://doi.org/10.1016/J.NEUROIMAGE.2017.03.024
Kennedy, D.N., Filipek, P.A., Caviness, V.S.: Anatomic segmentation and volumetric calculations in nuclear. Magn. Reson. Imaging (1989). https://doi.org/10.1109/42.20356
Stefano, A., Gallivanone, F., Messa, C.L., Gilardi, M.C.L., Castiglioni, I.: Metabolic impact of partial volume correction of [18F]FDG PET-CT oncological studies on the assessment of tumor response to treatment. Q. J. Nucl. Med. Mol. Imaging. 58, 413–423 (2014)
Alongi, P., et al.: Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients. Eur. Radiol. 31(7), 4595–4605 (2021). https://doi.org/10.1007/s00330-020-07617-8
Vernuccio, F., Cannella, R., Comelli, A., Salvaggio, G., Lagalla, R., Midiri, M.: Radiomics and artificial intelligence: new frontiers in medicine. Recent. Prog. Med. 111(3), 130–135 (2020). Italian. https://doi.org/10.1701/3315.32853
Comelli, A., et al.: A Kernel support vector machine based technique for Crohn’s disease classification in human patients. In: Barolli, L., Terzo, O. (eds.) CISIS 2017. AISC, vol. 611, pp. 262–273. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-61566-0_25
Licari, L., et al.: Use of the KSVM-based system for the definition, validation and identification of the incisional hernia recurrence risk factors. G. Chir. 40, 32–38 (2019)
Cuocolo, R., et al.: Clinically significant prostate cancer detection on MRI: a radiomic shape features study. Eur. J. Radiol. 116, 144–149 (2019). https://doi.org/10.1016/j.ejrad.2019.05.006
Tsang, O., Gholipour, A., Kehtarnavaz, N., Gopinath, K., Briggs, R., Panahi, I.: Comparison of tissue segmentation algorithms in neuroimage analysis software tools. In: Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2008 - “Personalized Healthcare through Technology.”, pp. 3924–3928 (2008). https://doi.org/10.1109/iembs.2008.4650068
Klauschen, F., Goldman, A., Barra, V., Meyer-Lindenberg, A., Lundervold, A.: Evaluation of automated brain MR image segmentation and volumetry methods. Hum. Brain Mapp. 30, 1310–1327 (2009). https://doi.org/10.1002/hbm.20599
Rajagopalan, V., Pioro, E.P.: Disparate voxel based morphometry (VBM) results between SPM and FSL softwares in ALS patients with frontotemporal dementia: Which VBM results to consider? BMC Neurol. 15, (2015). https://doi.org/10.1186/s12883-015-0274-8
Kazemi, K., Noorizadeh, N.: Quantitative comparison of SPM, FSL, and Brainsuite for Brain MR image segmentation. J. Biomed. Phys. Eng. 4, 13–26 (2014)
Tudorascu, D.L., et al.: Reproducibility and bias in healthy brain segmentation: comparison of two popular neuroimaging platforms. Front. Neurosci. 10 (2016). https://doi.org/10.3389/fnins.2016.00503
Fellhauer, I., et al.: Comparison of automated brain segmentation using a brain phantom and patients with early Alzheimer’s dementia or mild cognitive impairment (2015).https://doi.org/10.1016/j.pscychresns.2015.07.011
Stefano, A., et al.: A fully automatic method for biological target volume segmentation of brain metastases. Int. J. Imaging Syst. Technol. 26, 29–37 (2016). https://doi.org/10.1002/ima.22154
Agnello, L., Comelli, A., Ardizzone, E., Vitabile, S.: Unsupervised tissue classification of brain MR images for voxel-based morphometry analysis. Int. J. Imaging Syst. Technol. 26, 136–150 (2016). https://doi.org/10.1002/ima.22168
Comelli, A., Stefano, A.: A fully automated segmentation system of positron emission tomography studies. In: Zheng, Y., Williams, B.M., Ke., Chen (eds.) MIUA 2019. CCIS, vol. 1065, pp. 353–363. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39343-4_30
Woolrich, M.W., et al.: Bayesian analysis of neuroimaging data in FSL. Neuroimage 45, S173–S186 (2009). https://doi.org/10.1016/j.neuroimage.2008.10.055
Friston, K.J.: Statistical Parametric Mapping: The Analysis of Functional Brain Images (2006)
Sharma, G., Martin, J.: MATLAB®: A language for parallel computing. Int. J. Parallel Program. 37, 3–36 (2009). https://doi.org/10.1007/s10766-008-0082-5
Rohlfing, T.: Image similarity and tissue overlaps as surrogates for image registration accuracy: Widely used but unreliable. IEEE Trans. Med. Imaging. 31, 153–163 (2012). https://doi.org/10.1109/TMI.2011.2163944
Hunter, D., Yu, H., Pukish, M.S., Kolbusz, J., Wilamowski, B.M.: Selection of proper neural network sizes and architectures-A comparative study. IEEE Trans. Ind. Informatics. (2012). https://doi.org/10.1109/TII.2012.2187914
Stefano, A., et al.: A graph-based method for PET image segmentation in radiotherapy planning: a pilot study. In: Petrosino, A. (ed.) ICIAP 2013. LNCS, vol. 8157, pp. 711–720. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-41184-7_72
Russo, G., et al.: Feasibility on the use of radiomics features of 11[C]-MET PET/CT in central nervous system tumours: Preliminary results on potential grading discrimination using a machine learning model. Curr. Oncol. 28, 5318–5331 (2021). https://doi.org/10.3390/curroncol28060444
Comelli, A., Stefano, A., Benfante, V., Russo, G.: Normal and abnormal tissue classification in positron emission tomography oncological studies. Pattern Recognit. Image Anal. 28, 106–113 (2018). https://doi.org/10.1134/S1054661818010054
Laudicella, R., Iagaru, A., Minutoli, F., Gaeta, M., Baldari, S., Bisdas, S.: PET/MR in neuro-oncology: is it ready for prime-time? Clin. Transl. Imaging 8(4), 233–235 (2020). https://doi.org/10.1007/s40336-020-00377-x
Cuocolo, R., et al.: Deep learning whole-gland and zonal prostate segmentation on a public MRI dataset. J. Magn. Reson. Imaging. 54, 452–459 (2021). https://doi.org/10.1002/jmri.27585
Stefano, A., Comelli, A.: Customized efficient neural network for covid-19 infected region identification in CT images. J. Imaging. 7, 131 (2021). https://doi.org/10.3390/jimaging7080131
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Laudicella, R., Agnello, L., Comelli, A. (2022). Unsupervised Brain Segmentation System Using K-Means and Neural Network. In: Mazzeo, P.L., Frontoni, E., Sclaroff, S., Distante, C. (eds) Image Analysis and Processing. ICIAP 2022 Workshops. ICIAP 2022. Lecture Notes in Computer Science, vol 13373. Springer, Cham. https://doi.org/10.1007/978-3-031-13321-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-13321-3_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13320-6
Online ISBN: 978-3-031-13321-3
eBook Packages: Computer ScienceComputer Science (R0)