A complete pipeline for glioma grading using intelligible AI on multimodal MRI data

Main Article Content

Paul Dequidt Pascal Bourdon Benoit Tremblais Mathieu Naudin Pierre Fayolle Clément Giraud Carole Guillevin Christine Fernandez-Maloigne Rémy Guillevin


1) Objectives: Machine learning for binary glioma grading have been extensively used on anatomical MRI, especially using the BraTS dataset. The relevance of radiomic criteria based on multimodal imaging, including diffusion, perfusion and spectroscopy data is to be explored, as multimodal datasets are scarce, and there is no common benchmark for performance comparison.

2) Material and methods: Poitiers University Hospital provides 123 multimodal patient data. We computed 124 features and let a recursive feature elimination algorithm (RFE) yield a relevant, reduced subset of features. We trained a SVM classifier on this subset. We proposed a method to adapt the BraTS dataset to allow performance comparison with the literature. We got a performance reference point by training on anatomical data only, and showed improvements when multimodalities were added. We explored the feature relevance through the RFE subset. The RFE subset is not constant and induce variability in the performances. To smooth the variability, we applied the RFE algorithm 100 times and incremented the selected features, resulting in a global feature ranking. We also show the best classifier reached on these 100 trainings and its feature subset.

3) Results: The best classifier reached 86.5% accuracy, with a mean accuracy on 100 trainings of 78.6%. The rankings shows that anatomical and perfusion sequences are the most relevant for glioma grading, especially T1 post-gadolinium, cerebral blood volume and flow. Intensity and texture features are frequently selected, while anisotropic diffusion coefficient, time to peak and mean time transit mappings seem irrelevant.

4) Conclusion: Multimodal radiomics improve the classification and are consistent with the radiological analysis.

Keywords: glioma grading, glioma grading using intelligible AI, AI

Article Details

How to Cite
DEQUIDT, Paul et al. A complete pipeline for glioma grading using intelligible AI on multimodal MRI data. Medical Research Archives, [S.l.], v. 11, n. 5, may 2023. ISSN 2375-1924. Available at: <https://esmed.org/MRA/mra/article/view/3793>. Date accessed: 21 apr. 2024. doi: https://doi.org/10.18103/mra.v11i5.3793.
Research Articles


[1] Bahar Ryan C., Merkaj Sara, Cassinelli Petersen Gabriel I., Tillmanns Niklas, Subramanian Harry, Brim Waverly Rose, Zeevi Tal, Staib Lawrence, Kazarian Eve, Lin MingDe, Bousabarah Khaled, Huttner Anita J., Pala Andrej, Payabvash Seyedmehdi, Ivanidze Jana, Cui Jin, Malhotra Ajay, Aboian Mariam S., “Machine Learning Models for Classifying High- and Low-Grade Gliomas: A Systematic Review and Quality of Reporting Analysis”, Frontiers in Oncology, vol 12 , 2022, DOI: 10.3389/fonc.2022.856231, ISSN=2234-943X

[2] Menze B, Isensee F, Wiest R, Wiestler B, Maier-Hein K, Reyes M, Bakas S., “Analyzing magnetic resonance imaging data from glioma patients using deep learning”, Comput Med Imaging Graph. 2021 Mar;88:101828. doi: 10.1016/j.compmedimag.2020.101828. Epub 2020 Dec 2. PMID: 33571780; PMCID: PMC8040671.

[3] Lo, Chung-Ming, Yu-Chih Chen, Rui-Cian Weng, and Kevin Li-Chun Hsieh. 2019. "Intelligent Glioma Grading Based on Deep Transfer Learning of MRI Radiomic Features" Applied Sciences 9, no. 22: 4926. https://doi.org/10.3390/app9224926

[4] D. N. Louis, A. Perry, G. Reifenberger, A. Von Deimling, D. Figarella-Branger, W. K. Cavenee, H. Ohgaki, O. D. Wiestler, P. Kleihues, D. W. 14260 Ellison, The 2016 world health organization classification of tumors of the central nervous system: a summary, Acta neuropathologica 131 (6) (2016) 803–820.

[5] P. Dequidt, P. Bourdon, O. B. Ahmed, B. Tremblais, C. Guillevin, M. Naudin, C. Fernandez-Maloigne, R. Guillevin, Recent advances in glioma grade classification using machine and deep learning on MR data, in: 2019 Fifth International Conference on Advances in Biomedical Engi- neering (ICABME), IEEE, 2019, pp. 1–4.

[6] B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, Y. Burren, N. Porz, J. Slotboom, R. Wiest, et al., The multimodal brain tumor image segmentation benchmark (BraTS), IEEE transactions on medical imaging 34 (10) (2014) 1993–2024.

[7] S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, J. B. Freymann, K. Farahani, C. Davatzikos, Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features, Scientific data 4 (2017) 170117.

[8] S. Bakas, M. Reyes, A. Jakab, S. Bauer, M. Rempfler, A. Crimi, R. T. Shinohara, C. Berger, S. M. Ha, M. Rozycki, et al., Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BraTS challenge, arXiv preprint arXiv:1811.02629.

[9] C. Ge, Q. Qu, I. Y.-H. Gu, A. S. Jakola, 3d multi-scale convolutional net- works for glioma grading using mr images, in: 2018 25th IEEE International Conference on Image Processing (ICIP), IEEE, 2018, pp. 141–145.

[10] G. Cui, J. Jeong, B. Press, Y. Lei, H.-K. Shu, T. Liu, W. Curran, H. Mao, X. Yang, Machine-learning-based classification of lower-grade gliomas and high-grade gliomas using radiomic features in multi-parametric MRI, arXiv preprint arXiv:1911.10145.

[11] P. Dequidt, P. Bourdon, B. Tremblais, C. Guillevin, B. Gianelli, C. Boutet, J.-P. Cottier, J.-N. Vallée, C. Fernandez-Maloigne, R. Guillevin, Assigning a new glioma grade label ground-truth for the brats dataset using radiologic criteria, in: 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE, 2020, pp. 1–6.

[12] N. Upadhyay, A. Waldman, Conventional MRI evaluation of gliomas, The British journal of radiology 84 (special issue 2) (2011) S107–S111.

[13] J.-L. Dietemann, Neuro-imagerie diagnostique, Elsevier Health Sciences, 2018.

[14] F. Citak-Er, Z. Firat, I. Kovanlikaya, U. Ture, E. Ozturk-Isik, Machine- learning in grading of gliomas based on multi-parametric magnetic resonance imaging at 3t, Computers in biology and medicine 99 (2018) 154 – 300

[15] A. Vamvakas, S. Williams, K. Theodorou, E. Kapsalaki, K. Fountas, C. Kappas, K. Vassiou, I. Tsougos, Imaging biomarker analysis of advanced multiparametric MRI for glioma grading, Physica Medica 60 (2019) 188–198.

[16] Jainy Sachdeva, Vinod Kumar, Indra Gupta, Niranjan Khandelwal, Chirag Kamal Ahuja, A package-SFERCB- “Segmentation, feature extraction, reduction and classification analysis by both SVM and ANN for brain tumors”, Applied Soft Computing,Volume 47,2016,Pages 151-167,ISSN 1568-4946, https://doi.org/10.1016/j.asoc.2016.05.020.

[17] Latif G, Ben Brahim G, Iskandar DNFA, Bashar A, Alghazo J. Glioma Tumors' Classification Using Deep-Neural-Network-Based Features with SVM Classifier. Diagnostics (Basel). 2022 Apr 18;12(4):1018. doi: 10.3390/diagnostics12041018. PMID: 35454066; PMCID: PMC9032951.

[18] B. L. Dean, B. P. Drayer, C. R. Bird, R. A. Flom, J. A. Hodak, S. W. Coons, R. G. Carey, Gliomas: classification with MR imaging., Radiology 174 (2) (1990) 411–415.

[19] Gates EDH, Lin JS, Weinberg JS, Prabhu SS, Hamilton J, Hazle JD, Fuller GN, Baladandayuthapani V, Fuentes DT, Schellingerhout D. Imaging-Based Algorithm for the Local Grading of Glioma. AJNR Am J Neuroradiol. 2020 Mar;41(3):400-407. doi: 10.3174/ajnr.A6405. Epub 2020 Feb 6. PMID: 32029466; PMCID: PMC7077885.

[20] R. Cavaliere, M. B. S. Lopes, D. Schiff, Low-grade gliomas: an update on pathology and therapy, The Lancet Neurology 4 (11) (2005) 760–770.

[21] R. Guillevin, Metabolic-oncological MR imaging of diffuse low-grade glioma: A dynamic approach, in: Diffuse Low-Grade Gliomas in Adults, Springer, 2013, pp. 219–234.

[22] Inano R, Oishi N, Kunieda T, Arakawa Y, Yamao Y, Shibata S, Kikuchi T, Fukuyama H, Miyamoto S., Voxel-based clustered imaging by multiparameter diffusion tensor images for glioma grading., Neuroimage Clin. 2014 Aug 7;5:396-407. doi: 10.1016/j.nicl.2014.08.001. eCollection 2014.PMID: 25180159

[23] Chengjun Yao, Shunzeng Lv, Hong Chen, Weijun Tang, Jun Guo, Dongxiao Zhuang, Nikos Chrisochoides, Jinsong Wu, Ying Mao & Liangfu Zhou (2016) The clinical utility of multimodal MR image-guided needle biopsy in cerebral gliomas,International Journal of Neuroscience, 126:1, 53-61, DOI: 10.3109/00207454.2014.992429

[24] Ning Z, Luo J, Xiao Q, Cai L, Chen Y, Yu X, Wang J, Zhang Y. Multi-modal magnetic resonance imaging-based grading analysis for gliomas by integrating radiomics and deep features. Ann Transl Med. 2021 Feb;9(4):298. doi: 10.21037/atm-20-4076. PMID: 33708925; PMCID: PMC7944310

[25] J. J. Van Griethuysen, A. Fedorov, C. Parmar, A. Hosny, N. Aucoin, V. Narayan, R. G. Beets-Tan, J.-C. Fillion-Robin, S. Pieper, H. J. Aerts, Computational radiomics system to decode the radiographic phenotype, Cancer research 77 (21) (2017) e104–e107.

[26] A. Zwanenburg, S. Leger, M. Vallières, S. Löck, et al., Image biomarker standardisation initiative-feature definitions, arXiv preprint arXiv:1612.07003.

[27] I. Guyon, J. Weston, S. Barnhill, V. Vapnik, Gene selection for cancer classification using support vector machines, Machine learning 46 (1-3) (2002) 389–422.

[28] R. Beare, B. Lowekamp, Z. Yaniv, Image segmentation, registration and characterization in r with simpleitk, Journal of statistical software 86.

[29] Z. Yaniv, B. C. Lowekamp, H. J. Johnson, R. Beare, Simpleitk image analysis notebooks: a collaborative environment for education and reproducible research, Journal of digital imaging 31 (3) (2018) 290–303.

[30] B. C. Lowekamp, D. T. Chen, L. Ibáñez, D. Blezek, The design of simpleitk, Frontiers in neuroinformatics 7 (2013) 45.

[31] P. Bandettini, M. Jenkinson, C. Beckmann, T. Behrens, M. Woolrich, S. Smith, FSL, NeuroImage 62 (2) (2012) 782–790.

[32] M. Naudin, Visualisation et aide à la décision pour la neuro-navigation per-opératoire, Ph.D. thesis, Poitiers (2018).

[33] S. M. Smith, Fast robust automated brain extraction, Human brain mapping 17 (3) (2002) 143–155.

[34] T. Zhou, S. Ruan, S. Canu, A review: Deep learning for medical image segmentation using multi-modality fusion, Array 3 (2019) 100004.

[35] F. Isensee, P. Kickingereder, W. Wick, M. Bendszus, K. H. Maier-Hein, Brain tumor segmentation and radiomics survival prediction: Contribution to the BraTS 2017 challenge, in: International MICCAI Brainlesion Workshop, Springer, 2017, pp. 287–297.

[36] A. Fenneteau, P. Bourdon, D. Helbert, C. Fernandez-Maloigne, C. Habas, R. Guillevin, Investigating efficient CNN architecture for multiple sclerosis lesion segmentation, Journal of Medical Imaging 8 (1) (2021) 014504.

[37] Pascal Bourdon, Olfa Ben Ahmed, Thierry Urruty, Khalifa Djemal, Christine Fernandez-Maloigne, Explainable AI for medical imaging: knowledge matters, pages 267-292, chapter of Multi-faceted Deep Learning, Models and Data, Editors: Benois-Pineau Jenny, Zemmari Akka, Springer 2021