Radiomics, providing quantitative data extracted from medical images, has emerged as a critical role in diagnosis and classification of diseases such as glioma. One main challenge is how to uncover key disease-relevant features from the large amount of extracted quantitative features. Many existing methods suffer from low accuracy or overfitting. We propose a new method, Multiple-Filter and Multi-Objective-based method (MFMO), to identify predictive and robust biomarkers for disease diagnosis and classification. This method combines a multi-filter feature extraction with a multi-objective optimization-based feature selection model, which identifies a small set of predictive radiomic biomarkers with less redundancy. Taking magnetic resonance imaging (MRI) images-based glioma grading as a case study, we identify 10 key radiomic biomarkers that can accurately distinguish low-grade glioma (LGG) from high-grade glioma (HGG) on both training and test datasets. Using these 10 signature features, the classification model reaches training Area Under the receiving operating characteristic Curve (AUC) of 0.96 and test AUC of 0.95, which shows superior performance over existing methods and previously identified biomarkers.
Citation: Jingren Niu, Qing Tan, Xiufen Zou, Suoqin Jin. Accurate prediction of glioma grades from radiomics using a multi-filter and multi-objective-based method[J]. Mathematical Biosciences and Engineering, 2023, 20(2): 2890-2907. doi: 10.3934/mbe.2023136
| [1] | McKenna S. Vininski, Sunanda Rajput, Nicholas J. Hobbs, Joseph J. Dolence . Understanding sex differences in the allergic immune response to food. AIMS Allergy and Immunology, 2022, 6(3): 90-105. doi: 10.3934/Allergy.2022009 |
| [2] | Shkar Rzgar K. Rostam, Khattab Ahmed Mustafa Shekhany, Harem Othman Smail . Prevalence of common food allergies in Erbil Province, Kurdistan Region of Iraq. AIMS Allergy and Immunology, 2020, 4(4): 117-127. doi: 10.3934/Allergy.2020010 |
| [3] | Joseph J. Dolence, Hirohito Kita . Allergic sensitization to peanuts is enhanced in mice fed a high-fat diet. AIMS Allergy and Immunology, 2020, 4(4): 88-99. doi: 10.3934/Allergy.2020008 |
| [4] | Moufag Mohammed Saeed Tayeb . Role of IgG food test in patients with allergic diseases. AIMS Allergy and Immunology, 2023, 7(2): 154-163. doi: 10.3934/Allergy.2023010 |
| [5] | Chunyan Li, Wojciech Dawicki, Xiaobei Zhang, Chris Rudulier, John R. Gordon . IL-10- and retinoic acid-induced regulatory dendritic cells are therapeutically equivalent in mouse models of asthma and food allergy. AIMS Allergy and Immunology, 2021, 5(2): 73-91. doi: 10.3934/Allergy.2021007 |
| [6] | Katarzyna Nazimek . The complex functions of microRNA-150 in allergy, autoimmunity and immune tolerance. AIMS Allergy and Immunology, 2021, 5(4): 195-221. doi: 10.3934/Allergy.2021016 |
| [7] | Xiujuan Li, Jianmin Lin, Yan Li, Min Zhu, Minchuan Lin, Chenxi Li . Inhalation allergen sensitization patterns in children with allergic rhinitis and asthma. AIMS Allergy and Immunology, 2024, 8(4): 254-264. doi: 10.3934/Allergy.2024015 |
| [8] | Omer Qibi, Severine Audusseau, Andrea Mogas, Zoulfia Allakhverdi, Abdelilah Soussi Gounni, Saba Al Heialy, Qutayba Hamid . No evidence for IgE receptor FcεRI expression on bronchial epithelial cells of asthmatic patients. AIMS Allergy and Immunology, 2018, 2(4): 165-179. doi: 10.3934/Allergy.2018.4.165 |
| [9] | Anna Fusco, Logan Pucci, Kevin Pierre, Adam Wolberg, Coulter Small, John Cerillo, Mohammad Reza Hosseini Siyanaki, Brandon Lucke-Wold . Contrast allergies for neurological imaging: When to proceed. AIMS Allergy and Immunology, 2022, 6(4): 216-227. doi: 10.3934/Allergy.2022016 |
| [10] | Howard J Mason, Laura Willerton . Airborne exposure to laboratory animal allergens. AIMS Allergy and Immunology, 2017, 1(2): 78-88. doi: 10.3934/Allergy.2017.2.78 |
Radiomics, providing quantitative data extracted from medical images, has emerged as a critical role in diagnosis and classification of diseases such as glioma. One main challenge is how to uncover key disease-relevant features from the large amount of extracted quantitative features. Many existing methods suffer from low accuracy or overfitting. We propose a new method, Multiple-Filter and Multi-Objective-based method (MFMO), to identify predictive and robust biomarkers for disease diagnosis and classification. This method combines a multi-filter feature extraction with a multi-objective optimization-based feature selection model, which identifies a small set of predictive radiomic biomarkers with less redundancy. Taking magnetic resonance imaging (MRI) images-based glioma grading as a case study, we identify 10 key radiomic biomarkers that can accurately distinguish low-grade glioma (LGG) from high-grade glioma (HGG) on both training and test datasets. Using these 10 signature features, the classification model reaches training Area Under the receiving operating characteristic Curve (AUC) of 0.96 and test AUC of 0.95, which shows superior performance over existing methods and previously identified biomarkers.
| [1] |
P. Y. Wen, J. T. Huse, 2016 World Health Organization classification of central nervous system tumors, Continuum (Lifelong Learn. Neurol.), 23 (2017), 1531–1547. https://doi.org/10.1212/con.0000000000000536 doi: 10.1212/con.0000000000000536
|
| [2] |
S. C. Thust, S. Heiland, A. Falini, H. R. Jager, A. D. Waldman, P. C. Sundgren, et al., Glioma imaging in Europe: A survey of 220 centres and recommendations for best clinical practice, Eur. Radiol., 28 (2018), 3306–3317. https://doi.org/10.1007/s00330-018-5314-5 doi: 10.1007/s00330-018-5314-5
|
| [3] |
C. Gui, J. C. Lau, S. E. Kosteniuk, D. H. Lee, J. F. Megyesi, Radiology reporting of low-grade glioma growth underestimates tumor expansion, Acta Neurochir., 161 (2019), 569–576. https://doi.org/10.1007/s00701-018-03783-3 doi: 10.1007/s00701-018-03783-3
|
| [4] |
A. Bink, J. Benner, J. Reinhardt, A. De Vere-Tyndall, B. Stieltjes, N. Hainc, et al., Structured reporting in neuroradiology: Intracranial tumors, Front. Neurol., 9 (2018), 32. https://doi.org/10.3389/fneur.2018.00032 doi: 10.3389/fneur.2018.00032
|
| [5] |
L. B. Nabors, J. Portnow, M. Ahluwalia, J. Baehring, H. Brem, S. Brem, et al., Central nervous system cancers version 3.2020, NCCN clinical practice guidelines in oncology, JNCCN, 18 (2020), 1537–1570. https://doi.org/10.6004/jnccn.2020.0052 doi: 10.6004/jnccn.2020.0052
|
| [6] |
Z. Y. Lin, R. W. Yang, K. S. Li, G. Z. Yi, Z. Y. Li, J. L. Guo, et al., Establishment of age group classification for risk stratification in glioma patients, BMC Neurol., 20 (2020), 310. https://doi.org/10.1186/s12883-020-01888-w doi: 10.1186/s12883-020-01888-w
|
| [7] |
P. Grossmann, O. Stringfield, N. El-Hachem, M. M. Bui, E. R. Velazquez, C. Parmar, et al., Defining the biological basis of radiomic phenotypes in lung cancer, ELife, 6 (2017), e23421. https://doi.org/10.7554/elife.23421 doi: 10.7554/elife.23421
|
| [8] |
H. H. Cho, C. K. Kim, H. Park, Overview of radiomics in prostate imaging and future directions, Br. J. Radiol., 95 (2022), 1131. https://doi.org/10.1259/bjr.20210539 doi: 10.1259/bjr.20210539
|
| [9] |
J. E. van Timmeren, D. Cester, S. Tanadini-Lang, H. Alkadhi, B. Baessler, Radiomics in medical imaging-"how-to" guide and critical reflection, Insights Imaging, 11 (2020), 91. https://doi.org/10.1186/s13244-020-00887-2 doi: 10.1186/s13244-020-00887-2
|
| [10] |
P. Lambin, R. T. H. Leijenaar, T. M. Deist, J. Peerlings, E. E. C. de Jong, J. van Timmeren, et al., Radiomics: the bridge between medical imaging and personalized medicine, Nat. Rev. Clin. Oncol., 14 (2017), 749–762. https://doi.org/10.1038/nrclinonc.2017.141 doi: 10.1038/nrclinonc.2017.141
|
| [11] |
T. Asklund, R. Birgander, P. Brynolfsson, A. Garpebring, J. Hauksson, R. Henriksson, et al., ADC texture—An imaging biomarker for high grade glioma, Neuro-Oncol., 16 (2014), ii78. https://doi.org/10.1093/neuonc/nou174.299 doi: 10.1093/neuonc/nou174.299
|
| [12] | H. H. Cho, H. Park, Classification of low-grade and high-grade glioma using multi-modal image radiomics features, in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), (2017), 3081–3084. https://doi.org/10.1109/embc.2017.8037508 |
| [13] |
H. Aerts, E. R. Velazquez, R. T. H. Leijenaar, C. Parmar, P. Grossmann, S. Carvalho, et al., Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach, Nat. Commun., 5 (2014), 4006. https://doi.org/10.1038/ncomms5006 doi: 10.1038/ncomms5006
|
| [14] |
Q. J. Chen, L. H. Wang, L. Wang, Z. Y. Deng, J. Zhang, Y. M. Zhu, Glioma grade prediction using wavelet scattering-based radiomics, IEEE Access, 8 (2020), 106564–106575. https://doi.org/10.1109/ACCESS.2020.3000895 doi: 10.1109/ACCESS.2020.3000895
|
| [15] |
Y. W. Park, Y. S. Choi, S. S. Ahn, J. H. Chang, S. H. Kim, S. K. Lee, Radiomics MRI phenotyping with machine learning to predict the grade of lower-grade gliomas: A study focused on nonenhancing tumors, Korean J. Radiol., 20 (2019), 1381–1389. https://doi.org/10.3348/kjr.2018.0814 doi: 10.3348/kjr.2018.0814
|
| [16] | G. Cui, J. J. Jeong, B. Press, Y. Lei, H. K. G. Shu, T. X. Liu, et al., Machine-learning-based classification of lower-grade gliomas and high-grade gliomas using radiomic features in multi-parametric MRI, preprint, arXiv: 1911.10145. |
| [17] |
K. L. C. Hsieh, C. Y. Chen, C. M. Lo, Quantitative glioma grading using transformed gray-scale invariant textures of MRI, Comput. Biol. Med., 83 (2017), 102–108. https://doi.org/10.1016/j.compbiomed.2017.02.012 doi: 10.1016/j.compbiomed.2017.02.012
|
| [18] | T. H. Xiao, W. Q. Hua, C. Li, S. S. Wang, Glioma grading prediction by exploring radiomics and deep learning features, in Proceedings of the Third International Symposium on Image Computing and Digital Medicine, (2019), 208–213. https://doi.org/10.1145/3364836.3364877 |
| [19] |
M. Gao, S. Y. Huang, X. Q. Pan, X. Liao, R. Yang, J. Liu, Machine learning-based radiomics predicting tumor grades and expression of multiple pathologic biomarkers in gliomas, Front. Oncol., 10 (2020), 1676. https://doi.org/10.3389/fonc.2020.01676 doi: 10.3389/fonc.2020.01676
|
| [20] |
H. H. Cho, S. H. Lee, J. Kim, H. Park, Classification of the glioma grading using radiomics analysis, PeerJ, 6 (2018), e5982. https://doi.org/10.7717/peerj.5982 doi: 10.7717/peerj.5982
|
| [21] |
J. J. M. van Griethuysen, A. Fedorov, C. Parmar, A. Hosny, N. Aucoin, V. Narayan, et al., Computational radiomics system to decode the radiographic phenotype, Cancer Res., 77 (2017), e104–e107. https://doi.org/10.1158/0008-5472.can-17-0339 doi: 10.1158/0008-5472.can-17-0339
|
| [22] |
A. Lancichinetti, S. Fortunato, J. Kertész, Detecting the overlapping and hierarchical community structure in complex networks, New J. Phys., 11 (2009), 033015. https://dx.doi.org/10.1088/1367-2630/11/3/033015 doi: 10.1088/1367-2630/11/3/033015
|
| [23] |
K. Deb, A. Pratap, S. Agarwal, T. Meyarivan, A fast and elitist multiobjective genetic algorithm: NSGA-II, IEEE Trans. Evol. Comput., 6 (2002), 182–197. https://dx.doi.org/10.1109/4235.996017 doi: 10.1109/4235.996017
|
| [24] |
D. N. Reshef, Y. A. Reshef, H. K. Finucane, S. R. Grossman, G. McVean, P. J. Turnbaugh, et al., Detecting novel associations in large data sets, Science, 334 (2011), 6062. https://doi.org/10.1126/science.1205438 doi: 10.1126/science.1205438
|
| [25] | S. M. Lundberg, S. I. Lee, A unified approach to interpreting model predictions, in Advances in Neural Information Processing Systems 30 (NIPS 2017), (2017), 4768–4777. https://dl.acm.org/doi/10.5555/3295222.3295230 |
| [26] | F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, et al., Scikit-learn: Machine learning in Python, J. Mach. Learn. Res., 12 (2011), 2825–2830. https://dl.acm.org/doi/10.5555/1953048.2078195 |
| [27] |
Q. H. Kha, V. H. Le, T. N. K. Hung, N. Q. K. Le, Development and validation of an efficient MRI radiomics signature for improving the predictive performance of 1p/19q Co-deletion in lower-grade gliomas, Cancers, 13 (2021), 5398. https://doi.org/10.3390/cancers13215398 doi: 10.3390/cancers13215398
|
| [28] |
S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J. S. Kirby, et al., Data descriptor: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features, Sci. Data, 4 (2017), 170117. https://doi.org/10.1038/sdata.2017.117 doi: 10.1038/sdata.2017.117
|
| [29] |
K. Clark, B. Vendt, K. Smith, J. Freymann, J. Kirby, P. Koppel, et al., The cancer imaging archive (TCIA): Maintaining and operating a public information repository, J. Digital Imaging, 26 (2013), 1045–1057. https://doi.org/10.1007/s10278-013-9622-7 doi: 10.1007/s10278-013-9622-7
|
| [30] |
B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, et al., The multimodal brain tumor image segmentation benchmark (BRATS), IEEE Trans. Med. Imaging, 34 (2015), 1993–2024. https://doi.org/10.1109/tmi.2014.2377694 doi: 10.1109/tmi.2014.2377694
|
| [31] |
M. Kistler, S. Bonaretti, M. Pfahrer, R. Niklaus, P. Buchler, The virtual skeleton database: An open access repository for biomedical research and collaboration, J. Med. Int. Res., 15 (2013), e245. https://doi.org/10.2196/jmir.2930 doi: 10.2196/jmir.2930
|
| [32] |
M. Ghaffari, A. Sowmya, R. Oliver, Automated brain tumor segmentation using multimodal brain scans: A survey based on models submitted to the BraTS 2012–2018 Challenges, IEEE Rev. Biomed. Eng., 13 (2020), 156–168. https://doi.org/10.1109/rbme.2019.2946868 doi: 10.1109/rbme.2019.2946868
|
| [33] |
S. Pati, R. Verma, H. Akbari, M. Bilello, V. B. Hill, C. Sako, et al., Reproducibility analysis of multi-institutional paired expert annotations and radiomic features of the Ivy Glioblastoma Atlas Project (Ivy GAP) dataset, Med. Phys., 47 (2020), 6039–6052. https://doi.org/10.1002/mp.14556 doi: 10.1002/mp.14556
|
| [34] |
L. H. T. Lam, D. T. Do, D. T. N. Diep, D. L. N. Nguyet, Q. D. Truong, T. T. Tri, et al., Molecular subtype classification of low-grade gliomas using magnetic resonance imaging-based radiomics and machine learning, NMR Biomed., 35 (2022), e4792. https://doi.org/10.1002/nbm.4792 doi: 10.1002/nbm.4792
|
| [35] |
A. Zwanenburg, M. Vallieres, M. A. Abdalah, H. Aerts, V. Andrearczyk, A. Apte, et al., The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping, Radiology, 295 (2020), 328–338. https://doi.org/10.1148/radiol.2020191145 doi: 10.1148/radiol.2020191145
|
| [36] | T. M. Hamdani, J. M. Won, A. M. Alimi, F. Karray, Multi-objective feature selection with NSGA II, in International Conference on Adaptive and Natural Computing Algorithms, (2007), 240–247. https://doi.org/10.1007/978-3-540-71618-1_27 |
| [37] |
N. Q. K. Le, T. N. K. Hung, D. T. Do, L. H. T. Lam, L. H. Dang, T. T. Huynh, Radiomics-based machine learning model for efficiently classifying transcriptome subtypes in glioblastoma patients from MRI, Comput. Biol. Med., 132 (2021), 104320. https://doi.org/10.1016/j.compbiomed.2021.104320 doi: 10.1016/j.compbiomed.2021.104320
|
 mbe-20-02-136-supplementary.docx |
 |
Figures(7) / Tables(3)
Jingren Niu, Qing Tan, Xiufen Zou, Suoqin Jin. Accurate prediction of glioma grades from radiomics using a multi-filter and multi-objective-based method[J]. Mathematical Biosciences and Engineering, 2023, 20(2): 2890-2907. doi: 10.3934/mbe.2023136
DownLoad: