Glioma Grading by Integrating Radiomic Features from Peritumoral Edema in Fused MRI Images and Automated Machine Learning
Abstract
1. Introduction
2. Materials and Methods
2.1. MRI Images
2.2. Image Fusion
2.3. Mask Creation
2.4. Radiomics Feature Extraction
2.5. Feature Selection
2.6. Classification
2.7. Performance Evaluation
3. Results
4. Discussion
5. Conclusions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Lu, X.; Zhang, D. Expression of lncRNAs in glioma: A lighthouse for patients with glioma. Heliyon 2024, 10, e24799. [Google Scholar] [CrossRef]
- Ludwig, K.; Kornblum, H.I. Molecular markers in glioma. J. Neurooncol. 2017, 134, 505–512. [Google Scholar] [CrossRef]
- Norman, S.; Juthani, R.G.; Magge, R. Foundations of the diagnosis and management of low-grade gliomas. World Neurosurg. 2022, 166, 306–312. [Google Scholar] [CrossRef]
- Segura, P.P.; Quintela, N.V.; García, M.M.; del Barco Berrón, S.; Sarrió, R.G.; Gómez, J.G.; Castaño, A.G.; Martín, L.M.N.; Rubio, O.G.; Losada, E.P. SEOM-GEINO clinical guidelines for high-grade gliomas of adulthood (2022). Clin. Transl. Oncol. 2023, 25, 2634–2646. [Google Scholar] [CrossRef] [PubMed]
- Bulnes, S.; Argandona, E.G.; Bengoetxea, H.; Leis, O.; Ortuzar, N.; Lafuente, J.V. The role of eNOS in vascular permeability in ENU-induced gliomas. In Brain Edema XIV; Springer: Berlin/Heidelberg, Germany, 2009; pp. 277–282. [Google Scholar]
- Schneider, S.W.; Ludwig, T.; Tatenhorst, L.; Braune, S.; Oberleithner, H.; Senner, V.; Paulus, W. Glioblastoma cells release factors that disrupt blood-brain barrier features. Acta Neuropathol. 2004, 107, 272–276. [Google Scholar] [CrossRef]
- Wolburg, H.; Noell, S.; Fallier-Becker, P.; Mack, A.F.; Wolburg-Buchholz, K. The disturbed blood–brain barrier in human glioblastoma. Mol. Asp. Med. 2012, 33, 579–589. [Google Scholar] [CrossRef] [PubMed]
- Morita, K.; Matsuzawa, H.; Fujii, Y.; Tanaka, R.; Kwee, I.L.; Nakada, T. Diffusion tensor analysis of peritumoral edema using lambda chart analysis indicative of the heterogeneity of the microstructure within edema. J. Neurosurg. 2005, 102, 336–341. [Google Scholar] [CrossRef]
- Wu, M.; Luan, J.; Zhang, D.; Fan, H.; Qiao, L.; Zhang, C. Development and validation of a clinical prediction model for glioma grade using machine learning. Technol. Heal. Care 2024, 32, 1977–1990. [Google Scholar] [CrossRef] [PubMed]
- Pandey, S.; Trivedi, M.C.; Bharadwaj, B.; Singh, V.K. Brain Tumor Classification into High-Grade and Low-Grade Gliomas Using Adaboost. In Advances in Computational Intelligence and Communication Technology: Proceedings of CICT 2021; Springer: Berlin/Heidelberg, Germany, 2022; pp. 433–440. [Google Scholar]
- Zhou, H.; Xu, R.; Mei, H.; Zhang, L.; Yu, Q.; Liu, R.; Fan, B. Application of enhanced T1WI of MRI radiomics in glioma grading. Int. J. Clin. Pract. 2022, 2022, 3252574. [Google Scholar] [CrossRef] [PubMed]
- Cho, H.-H.; Lee, S.-H.; Kim, J.; Park, H. Classification of the glioma grading using radiomics analysis. PeerJ 2018, 6, e5982. [Google Scholar] [CrossRef]
- Hashido, T.; Saito, S.; Ishida, T. Radiomics-based machine learning classification for glioma grading using diffusion-and perfusion-weighted magnetic resonance imaging. J. Comput. Assist. Tomogr. 2021, 45, 606–613. [Google Scholar] [CrossRef]
- Rizzo, S.; Botta, F.; Raimondi, S.; Origgi, D.; Fanciullo, C.; Morganti, A.G.; Bellomi, M. Radiomics: The facts and the challenges of image analysis. Eur. Radiol. Exp. 2018, 2, 36. [Google Scholar] [CrossRef]
- Azemi, G.; Di Ieva, A. Radiomic fingerprinting of the peritumoral edema in brain tumors. Cancers 2025, 17, 478. [Google Scholar] [CrossRef] [PubMed]
- Min, Z.; Niu, C.; Rana, N.; Ji, H.; Zhang, M. Differentiation of pure vasogenic edema and tumor-infiltrated edema in patients with peritumoral edema by analyzing the relationship of axial and radial diffusivities on 3.0 T MRI. Clin. Neurol. Neurosurg. 2013, 115, 1366–1370. [Google Scholar] [CrossRef]
- Romanowski, C.A.J.; Hoggard, N.; Jellinek, D.A.; Levy, D.; Wharton, S.B.; Kotsarini, C.; Batty, R.; Wilkinson, I.D. Low Grade Gliomas. Can We Predict Tumour Behaviour from Imaging Features? Neuroradiol. J. 2008, 21, 47–66. [Google Scholar] [CrossRef]
- Vicente, A.M.G.; García, J.M.C.; Menéndez, C.L.; Moreno, J.M.B.; Castrejón, A.S. Low-Grade Versus High-Grade Glioma… That Is the Question. 18F-Fluorocholine PET in the Detection of Anaplastic Focus. Clin. Nucl. Med. 2020, 45, 394–397. [Google Scholar] [CrossRef]
- Pouratian, N.; Asthagiri, A.; Jagannathan, J.; Shaffrey, M.E.; Schiff, D. Surgery Insight: The role of surgery in the management of low-grade gliomas. Nat. Clin. Pract. Neurol. 2007, 3, 628–639. [Google Scholar] [CrossRef] [PubMed]
- Tian, Q.; Yan, L.-F.; Zhang, X.; Zhang, X.; Hu, Y.-C.; Han, Y.; Liu, Z.-C.; Nan, H.-Y.; Sun, Q.; Sun, Y.-Z.; et al. Radiomics strategy for glioma grading using texture features from multiparametric MRI. J. Magn. Reson. Imaging 2018, 48, 1518–1528. [Google Scholar] [CrossRef] [PubMed]
- Li, X.; Huang, X.; Shen, Y.; Yu, S.; Zheng, L.; Cai, Y.; Yang, Y.; Zhang, R.; Zhu, L.; Wang, E. Machine learning for grading prediction and survival analysis in high grade glioma. Sci. Rep. 2025, 15, 16955. [Google Scholar] [CrossRef]
- Wang, Q.; Li, Q.; Mi, R.; Ye, H.; Zhang, H.; Chen, B.; Li, Y.; Huang, G.; Xia, J. Radiomics nomogram building from multiparametric MRI to predict grade in patients with glioma: A cohort study. J. Magn. Reson. Imaging 2019, 49, 825–833. [Google Scholar] [CrossRef]
- Lin, K.; Cidan, W.; Qi, Y.; Wang, X. Glioma grading prediction using multiparametric magnetic resonance imaging-based radiomics combined with proton magnetic resonance spectroscopy and diffusion tensor imaging. Med. Phys. 2022, 49, 4419–4429. [Google Scholar] [CrossRef]
- Khorasani, A.; Tavakoli, M.B.; Saboori, M. Using of Laplacian Re-decomposition image fusion algorithm for glioma grading with SWI, ADC, and FLAIR images. Pol. J. Med. Phys. Eng. 2021, 27, 261–269. [Google Scholar] [CrossRef]
- Khorasani, A.; Tavakoli, M.B.; Saboori, M.; Jalilian, M. Preliminary study of multiple b-value diffusion-weighted images and T1 post enhancement magnetic resonance imaging images fusion with Laplacian Re-decomposition (LRD) medical fusion algorithm for glioma grading. Eur. J. Radiol. Open 2021, 8, 100378. [Google Scholar] [CrossRef]
- Khorasani, A.; Dadashi serej, N.; Jalilian, M.; Shayganfar, A.; Tavakoli, M.B. Performance comparison of different medical image fusion algorithms for clinical glioma grade classification with advanced magnetic resonance imaging (MRI). Sci. Rep. 2023, 13, 17646. [Google Scholar] [CrossRef]
- Li, X.; Guo, X.; Han, P.; Wang, X.; Li, H.; Luo, T. Laplacian redecomposition for multimodal medical image fusion. IEEE Trans. Instrum. Meas. 2020, 69, 6880–6890. [Google Scholar] [CrossRef]
- Van Griethuysen, J.J.M.; Fedorov, A.; Parmar, C.; Hosny, A.; Aucoin, N.; Narayan, V.; Beets-Tan, R.G.H.; Fillion-Robin, J.C.; Pieper, S.; Aerts, H.J.W.L. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017, 77, e104–e107. [Google Scholar] [CrossRef]
- Kursa, M.B.; Rudnicki, W.R. Feature selection with the Boruta package. J. Stat. Softw. 2010, 36, 1–13. [Google Scholar] [CrossRef]
- Le, T.T.; Fu, W.; Moore, J.H. Scaling tree-based automated machine learning to biomedical big data with a feature set selector. Bioinformatics 2020, 36, 250–256. [Google Scholar] [CrossRef]
- Hernandez, J.G.; Saini, A.K.; Ghosh, A.; Moore, J.H. The tree-based pipeline optimization tool: Tackling biomedical research problems with genetic programming and automated machine learning. Patterns 2025, 6, 101314. [Google Scholar] [CrossRef] [PubMed]
- Silva, M.; Vivancos, C.; Duffau, H. The concept of «peritumoral zone» in diffuse low-grade gliomas: Oncological and functional implications for a connectome-guided therapeutic attitude. Brain Sci. 2022, 12, 504. [Google Scholar] [CrossRef] [PubMed]
- Hasanzadeh, A.; Moghaddam, H.S.; Shakiba, M.; Jalali, A.H.; Firouznia, K. The role of multimodal imaging in differentiating vasogenic from infiltrative edema: A systematic review. Indian J. Radiol. Imaging 2023, 33, 514–521. [Google Scholar] [CrossRef] [PubMed]
- Deng, F.; Liu, Z.; Fang, W.; Niu, L.; Chu, X.; Cheng, Q.; Zhang, Z.; Zhou, R.; Yang, G. MRI radiomics for brain metastasis sub-pathology classification from non-small cell lung cancer: A machine learning, multicenter study. Phys. Eng. Sci. Med. 2023, 46, 1309–1320. [Google Scholar] [CrossRef] [PubMed]
- Zhang, X.; Huang, P.; Zhang, R. Evaluation and prediction of post-stroke cerebral edema based on neuroimaging. Front. Neurol. 2022, 12, 763018. [Google Scholar] [CrossRef] [PubMed]
- Uchida, Y.; Hou, Z.; Gomez-Isaza, L.; Luongo, M.; Troncoso, J.C.; Miller, M.I.; Mori, S.; Oishi, K. Quantification of perforant path fibers for early detection of Alzheimer’s disease. Alzheimer’s Dement. 2025, 21, e70142. [Google Scholar] [CrossRef]
- Uchida, Y.; Onda, K.; Nishimaki, K.; Kucharska-Newton, A.; Windham, B.G.; Wasserman, B.A.; Oishi, K. Longitudinal changes in brain diffusion characteristics associated with cognition and vascular risk factors: The ARIC-NCS study. Neurology 2025, 105, e213867. [Google Scholar] [CrossRef]
Image | Selected Features | |
---|---|---|
Original MRI images | FLAIR | Maximum 3D Diameter, JointEntropy, Correlation.1, DifferenceAverage.1, Imc1.1, Imc2.1, MCC.1, Complexity.2, Maximum.3, 10Percentile.4, DifferenceEntropy.5, LowGrayLevelEmphasis.7 |
T1 | SmallAreHighGrayLevelEmphasis, InterquartileRange.1, Median.2, Imc1.2, Kurtosis.3, 10Percentile.4, Kurtosis.5, SmallAreaLowGrayLevelEmphasis.5, MeanAbsoluteDeviation.6 | |
T1Gd | SmallDependenceLowGrayLevelEmphasis, Mean.1, Median.1, Mean.2, Idmn.2 | |
T2 | 10Percentile.1, RootMeanSquared 1, MCC.1, Uniformity.2, Maximum.3, Contrast.6, DifferenceAverage.3, Imc1.6, Kurtosis.7 | |
Fused images | T1+FLAIR | Idmn, Contrast.2, Imc2.1, GrayLevelVariance.6, Skewness.3, Idn.3, Imc1.7 |
T1Gd+FLAIR | DependenceVariance, 90Percentile.1, Median.1, Correlation.1, DifferenceVariance 1, Imc2.1, MCC.1, MaximumProbability.1, GrayLevelNonUniformityNormalized.3, Mean.2, Imc1.2, MaximumProbability.3, Imc1.4, MaximumProbability.5, MCC.7 | |
T1Gd+T1 | Clustershade, Contrast, DependenceVariance, 10Percentile.1, Maximum.1, Skewness.1, Cnotrast.2, Idm.1, Imc.1, Mean.2, MaximumProbability.2, Imc2.3 | |
T1Gd+T2 | Flatness, Kurtosis, LowGrayLevelZoneEmphasis, Entropy.1, Mean.1, Clustershade.1, DifferenceVariance.1, DependenceEntropy.1, DependenceNonUniformityNormalized.1, GrayLevelVariance.3, GrayLevelVariance.4, Entropy.2, Mean.2, Imc1.2, SmallAreaEmphasis, Correlation.3, Imc2.3, MaximumProbability.3, Kurtosis, Mean4, Autocorrelation5, Imc1.6, HighGrayLevelZoneEmphasis.6 | |
T2+FLAIR | DifferenceVariance.1, ZoneEntropy.1, Idmn.3, Skewness.4, DependenceEntropy.5 | |
T2+T1 | SurfaceVolumeRatio, Imc.1, HighGrayLevelZoneEmphasis, 10Percentile.1, 90Precentile.1, Entropy.1, MeanAbsoluteDeviation.1, Clustershade.1, Contrast.2, Imc2.1, GrayLevelNonUniformityNormalized.2, DifferenceAverage.2, HighGrayLevelZoneEmphasis.2, SmallAreaEmphasis.2, SmallAreaLowGrayLevelEmphasis.2, ZoneEntropy.2, ZonePercentage.2, Complexity.2, MaximumProbability.3, MeanAbsouluteDeviation.4, DependenceVariance.4, GrayLevelNonUniformityNormalized.9, ZoneEntropy.4, MaximumProbability.7 |
Image | Best Classifier | Parameters |
---|---|---|
FLAIR | Gradient Boosting | Learning_rate = 0.01, max_depth = 8, max_features = 1.0, min_samples_leaf = 11, min_samples_split = 14, n_estimators = 100, subsample = 0.6501 |
T1 | Gradient Boosting | Learning_rate = 0.5, max_depth = 2, max_features = 0.1, min_samples_leaf = 4, min_samples_split = 20, n_estimators = 100, subsample = 0.55 |
T1Gd | Bernoulli Naïve Bayes | Alpha = 100, fit_prior = False |
T2 | SGD Classifier | Alpha = 0.01, eta = 0.1, fit_intercept = False, l1_ratio = 0.25, learning_rate = `constant`, penalty = `elasticnet`, power_t = 10 |
T1+FLAIR | MLP | Alpha = 0.0001, learning_rate_init = 0.1 |
T1Gd+FLAIR | SGD Classifier | Alpha = 0.001, eta = 0.01, fit_intercept = True, l1_rati = 0.25, learning_rate = `invscaling`, penalty = `elasticnet`, power_t = 0.1 |
T1Gd+T1 | Gradient Boosting | Learning_rate = 0.1, max_depth = 3, max_features = 0.95, min_samples_leaf = 9, min_samples_split = 13, n_estimators = 100, subsample = 0.7 |
T1Gd+T2 | Gradient Boosting (Stacking Estimator) | Learning_rate = 0.1, max_depth = 10, max_features = 0.5, min_samples_leaf = 14, min_samples_split = 10, n_estimators = 100, subsample = 0.5 |
MLP (Stacking Estimator) | Alpha = 0.001, learning_rate_init = 1 | |
KNN (Classifier) | N_neighbors = 33, p = 1, weights = `distance` | |
T2+FLAIR | KNN | N_neighbors = 39, p = 1, weights = `uniform` |
T2+T1 | MLP | Alpha = 0.0001, learning_rate_init = 0.1 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Khorasani, A. Glioma Grading by Integrating Radiomic Features from Peritumoral Edema in Fused MRI Images and Automated Machine Learning. J. Imaging 2025, 11, 336. https://doi.org/10.3390/jimaging11100336
Khorasani A. Glioma Grading by Integrating Radiomic Features from Peritumoral Edema in Fused MRI Images and Automated Machine Learning. Journal of Imaging. 2025; 11(10):336. https://doi.org/10.3390/jimaging11100336
Chicago/Turabian StyleKhorasani, Amir. 2025. "Glioma Grading by Integrating Radiomic Features from Peritumoral Edema in Fused MRI Images and Automated Machine Learning" Journal of Imaging 11, no. 10: 336. https://doi.org/10.3390/jimaging11100336
APA StyleKhorasani, A. (2025). Glioma Grading by Integrating Radiomic Features from Peritumoral Edema in Fused MRI Images and Automated Machine Learning. Journal of Imaging, 11(10), 336. https://doi.org/10.3390/jimaging11100336