Abstract
Childhood medulloblastoma (MB) is the most common embryo brain tumor and an area that needs utmost attention, as clinical diagnosis can be very difficult in case of infants and children. The rate of survival can increase with prompt diagnosis. Till date, there is no computer aided methodology for identification of childhood medulloblastoma and its subtypes. The diagnosis depends on qualitative visual inspection of the histological slides of the biopsy samples by clinical experts. We convert this qualitative judgment to quantitative features after digitization of the images. The feature set obtained from digital analysis from these biopsy tissues is very large and is computationally expensive. In this study, we examine whether the features are statistically significant for analysis towards classifying childhood MB from normal samples and its various subtypes, using MANOVA. Further, this technique is used as a feature reduction technique, which proves that it can be effectively used as such. Infact, the simplicity of the technique makes it a better choice when considering a sizeably high number of features.
Similar content being viewed by others
References
Ahmed S, Saikia B, Borah AL, Agarwal S (2012) Clinicopathological study of cns tumors with smear correlation. In: Proceedings of NERC-Indian Association of Pathologists and Microbiologists, Dibrugarh, India
Albregtsen F (2008) Statistical texture measures computed from gray level coocurrence matrices. Sci Rep 7:1–14
Armitage P, Colton T (2005) Encyclopedia of biostatistics, vol 8, 2nd edn. wiley, Amsterdam
Awwad A, Rodriguez D, Jaspan T, Grundy R, Auer PD (2012) T1 based texture analysis for the classification of paediatric medulloblastoma, ependymoma and their anaplastic subtypes. In: Proceedings of 36th European Society of Neuroradiology (ESNR) Annual Meeting, Edinburgh
Berwick R (2011) An idiot’s guide to support vector machine (svm).http://web.mit.edu/6.034/wwwbob/svm-notes-long-08.pdf
Boswell D (2002) Introduction to support vector machines. http://dustwell.com/PastWork/IntroToSVM.pdf
Das D, Mahanta BL, Ahmed S, Baishya KB, Haque I (2018) Study on contribution of biological interpretable and computer-aided features towards the classification of childhood medulloblastoma cells. J Med Syst 42:1–12
Duffner PK, Cohen ME (1986) Recent developments in pediatric neuro oncology. Cancer 58:561–568
Fetita AE, Novak J, Peetb AC, Arvanitis TN (2015) Three-dimensional textural features of conventional mri improve diagnostic classification of childhood brain tumours. NMR Biomed 28:1174–1184
Galaro J, Judkins AR, Ellison D, Baccon J, Madabhushi A (2011) An integrated texton and bag of words classifier for identifying anaplastic medulloblastomas. In: Proceedings of Annual International Conferenxce of the IEEE Enginering in Medicine Biology Society EMBS, Boston, USA, pp 3343–3346
Graham ID, Lantos LP (2015) Greenfield’s neuropathology, vol 2, 9th edn. CRC Press, London
Gupta S, Walia P, Singla C, Dhankar S, Mishra T, Khandelwal A, Bhardwaj M (2016) Segmentation, feature extraction and classification of astrocytoma in mr images. Indian J Sci Technol 9:1–7
Haque I (2018) A clinical study of medulloblastoma in correlation with molecular biology and histological variations in childhood medulloblastoma. Master’s thesis, Srimanta Sankardeva University of Health Sciences
Harlick RM, Shanmugam K, Dinstein I (1971) Texture fetures for image classifications. IEEE Trans Syst Man Cybern 3:610–621
Huang G, Kumar S, Mitra M, Zhu WJ, Zabih R (2017) Image indexing using color correlograms. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, USA
Kather NJ, Cleo-AronWeis Bianconi M, Melcher MS, Schad RL, TimoGaiser Marx A, Zöllner FG (2016) Multi-class texture analysis in colorectal cancer histology. Sci Rep. https://doi.org/10.1038/srep27988
Kim K, Jung K, Park SH, Kim HJ (2002) Support vector machines for texture classification. IEEE Trans Pattern Anal Mach Intell 24:1542–1550
Kumar R, Srivastava R, Srivastava S (2015) Detection and classification of cancer from microscopic biopsy images using clinically significant and biologically interpretable features. J Med Eng. https://doi.org/10.1038/srep27988
Lai Y, Viswanatha S, Baccon J, Ellison D, Judkins AR, Madabhushi A (2011) A texture-based classifier to discriminate anaplastic from non-anaplastic medulloblastoma. In: Proceedings of IEEE 37th Annual Northeast Bioengineering Conference Troy, NY, USA, https://doi.org/10.1109/NEBC.2011.5778641
Mathew T (1989) Manova in the multivariate components of variance model. J Multivar Anal 29:30–38
Meiburger K, Salvi M, Giacchino M, Acharya UR, Minetto MA, Caresio C, Molinari F (2018) Quantitative analysis of patellar tendon abnormality in asymptomatic professional “pallapugno” players:a texture-based ultrasound approach. Appl Sci 8:660
Méndez AJ, Tahoces PG, Lado MJ, Souto M, Vidal JJ (1998) Computer-aided diagnosis: automatic detection of malignant masses in digitized mammograms. Med Phys 25:957–64
Muzio BD, Gaillard AF (2016) Who classification of cns tumours. https://radiopaedia.org/articles/who-classification-of-cns-tumours-1
Ojala T, Pietikinen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24:971–987
Paschos G (2000) Fast color texture recognition using chromaticity moments. Pattern Recogn Lett 21:837–841
Polednak AP, Flannery JT (1995) Brain, other central nervous system and eye cancer. Cancer 75:330–337
Reitermanova Z (2010) Data splitting. In: Proceedings of WDS’10 Proceedings of Contributed Papers, Prague
Roa AC, Arévalo J, Judkins A, Madabhushi A, González F (2015) A method for medulloblastoma tumor differentiation based on convolutional neural networks and transfer learning. In: Proceedings of 11th International Symposium on Medical Information Processing and Analysis, Ecuador, vol 9681, https://doi.org/10.1117/12.2208825
Roberts RO, Lynch CF, Jones MP, Hart MN (1991) Medulloblastoma: a population-based study of 532 cases. J Neuropathol Exp Neurol 50:134–144
Srivastava DK, Bhambhu L (2010) Data classification using support vector machine. J Theor Appl Inform Technol 12:1–7
Tamura H, Hideyuki Mori S, Yamawaki T (1978) Textural features corresponding to visual perception. Syst Man Cybern 6:460–473
Tang X (1998) Texture information in run-length matrices. In: Proceedings of IEEE Transactions on Image Processing, https://doi.org/10.1109/83.725367
Tomic I, Dedijar S, Juric I, Pal M (2016) The effect of scanning resolution and displacement value on the glcm-based features for paper texture characterization. In: Proc. 8th International Symposium on Graphic Engineering and Design - GRID 08, Novi Sad
Tong S, Koller D (2001) Support vector machine active learning with applications to text classification. J Mach Learn Res 2:45–66
Waheed S, Moffitt RA, Chaudhry Q, Young AN, Wang MD (2007) Computer aided histopathological classification of cancer subtypes. In: Proceedings of IEEE 7th International Symposium on BioInformatics and BioEngineering, Boston, USA, https://doi.org/10.1109/BIBE.2007.4375608
Wilson M, Gill SK, MacPherson L, English M, Arvanitis TN, Peet AC (2014) Non-invasive detection of glutamate predicts survival in pediatric medulloblastoma. Clin Cancer Res 20:4532–4539
Zarinabad N, Wilson M, Gill SK, Manias KA, Davies NP (2017) Multiclass imbalance learning: Improving classification of pediatric brain tumors from magnetic resonance spectroscopy. Magn Reson Med 77:2114–2124
Zhang S, Qiao H (2003) Face recognition with support vector machine. In: Proceedings of International Conference on Robotics,Intelligent Systems and Signal Processing, Changsha, China
Acknowledgements
We would like to convey our sincere thanks to Dr. Basanta Kr. Baishya, Head of the department of neurosurgery, Guwahati Medical College, and Dr. Inamul Haque, MCH Trainee from the Department of Neurosurgery, Guwahati Medical College for providing us the tissue blocks and Dr. Anup Das from Ayursundra Healthcare Pvt. Ltd. For processing the slides. We would further thank Dr. Shabnam Ahmed of Guwahati Neurological Research Centre, Sixmile for dedicating her time and effort and helping us in image acquisition and providing the ground truth. We are grateful to Institute of Advanced Study in Science and Technology (IASST), Guwahati for giving us the platform to perform our research.
Author information
Authors and Affiliations
Contributions
D.D wrote the paper and performed the experiments. L.B.M supervised the whole idea and write up. S.A. and B.K.B was the medical guidance throughout the study.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Das, D., Mahanta, L.B., Ahmed, S. et al. A study on MANOVA as an effective feature reduction technique in classification of childhood medulloblastoma and its subtypes. Netw Model Anal Health Inform Bioinforma 9, 16 (2020). https://doi.org/10.1007/s13721-020-0221-5
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13721-020-0221-5