Automated Grading of Glioma Using Deep Neural Networks

Abstract

Gliomas are one of the most common tumors in the brain. It is possible to grade gliomas as Lower-Grade Glioma (LGG) and Glioblastoma Multiforme (GBM). Clinical and molecular/mutation factors come to the fore in the grading of gliomas. Molecular tests used to grade glioma are expensive and time consuming. In this study, deep learning networks were used for glioma grading. Long short-term memory (LSTM) and Convolutional neural network (CNN) were used together in the proposed model. The developed model was also compared with 6 different classifiers accepted in the literature. Among the models used in the study, the developed model achieved the highest performance. In this study, glioma grading was performed for the purpose of improving performance and reducing costs.

Keywords

• Classifiers
• CNN
• Deep Learning
• Glioma
• LSTM

References

1. Hakyemez, B., Erdogan, C., Ercan, I., Ergin, N., Uysal, S., & Atahan, S. (2005). High-grade and low-grade gliomas: differentiation by using perfusion MR imaging. Clinical radiology, 60(4), 493-502.
2. Nandihal, P., Shetty, V., Guha, T., & Pareek, P. K. (2022, October). Glioma Detection using Improved Artificial Neural Network in MRI Images. In 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon) (pp. 1-9). IEEE.
3. Gore, S., Chougule, T., Jagtap, J., Saini, J., & Ingalhalikar, M. (2021). A review of radiomics and deep predictive modeling in glioma characterization. Academic Radiology, 28(11), 1599-1621.
4. Saini, A., Kumar, M., Bhatt, S., Saini, V., & Malik, A. (2020). Cancer causes and treatments. International Journal of Pharmaceutical Sciences and Research, 11(7), 3121-3134.
5. Boele, F. W., Butler, S., Nicklin, E., Bulbeck, H., Pointon, L., Short, S. C., & Murray, L. (2023). Communication in the context of glioblastoma treatment: A qualitative study of what matters most to patients, caregivers and health care professionals. Palliative Medicine, 37(6), 834-843.
6. Tasci, E., et al., Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics. International Journal of Molecular Sciences, 2022. 23(22): p. 14155.
7. Cengil, E., Eroğlu, Y., Çınar, A., & Yıldırım, M. Detection and Localization of Glioma and Meningioma Tumors in Brain MR Images using Deep Learning. Sakarya University Journal of Science, 27(3), 550-563.
8. Yang, Y., Yan, L. F., Zhang, X., Han, Y., Nan, H. Y., Hu, Y. C., ... & Wang, W. (2018). Glioma grading on conventional MR images: a deep learning study with transfer learning. Frontiers in neuroscience, 12, 804.

9. Xiao, T., Hua, W., Li, C., & Wang, S. (2019, August). Glioma grading prediction by exploring radiomics and deep learning features. In Proceedings of the Third International Symposium on Image Computing and Digital Medicine (pp. 208-213).
10. Vafaeikia, P., Wagner, M. W., Hawkins, C., Tabori, U., Ertl-Wagner, B. B., & Khalvati, F. (2023). MRI-Based End-To-End Pediatric Low-Grade Glioma Segmentation and Classification. Canadian Association of Radiologists Journal, 08465371231184780.
11. Hastie, T., Rosset, S., Zhu, J., & Zou, H. (2009). Multi-class adaboost. Statistics and its Interface, 2(3), 349-360.
12. Turchetti Maia, T., Pádua Braga, A., & de Carvalho, A. F. (2008). Hybrid classification algorithms based on boosting and support vector machines. Kybernetes, 37(9/10), 1469-1491.
13. Qi, Y. (2012). Random forest for bioinformatics. Ensemble machine learning: methods and applications.
14. Rish, I. (2001, August). An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence (Vol. 3, No. 22, pp. 41-46).
15. Dong, J., Chen, Y., Yao, B., Zhang, X., & Zeng, N. (2022). A neural network boosting regression model based on XGBoost. Applied Soft Computing, 125, 109067.
16. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
17. Zhang, M. L., & Zhou, Z. H. (2007). ML-KNN: A lazy learning approach to multi-label learning. Pattern recognition, 40(7), 2038-2048.
18. Yildirim, M. (2023). Image Visualization and Classification Using Hydatid Cyst Images with an Explainable Hybrid Model. Applied Sciences, 13(17), 9926.
19. Url: https://archive.ics.uci.edu/dataset/759/glioma+grading+clinical+and+mutation+features+dataset.
20. Cengil, E., Çınar, A., & Yıldırım, M. (2022). A hybrid approach for efficient multi‐classification of white blood cells based on transfer learning techniques and traditional machine learning methods. Concurrency and Computation: Practice and Experience, 34(6), e6756.
21. Özbay, E., & Özbay, F. A. (2023). Interpretable features fusion with precision MRI images deep hashing for brain tumor detection. Computer Methods and Programs in Biomedicine, 231, 107387.
22. Özbay, E., Çinar, A., & Özbay, F. A. (2021). 3D Human Activity Classification with 3D Zernike Moment Based Convolutional, LSTM-Deep Neural Networks. Traitement du Signal, 38(2), 269-280.
23. Yücel, N., Yildirim, M., & Aslan, S. (2023). Performances of Pre-Trained Models in Classification of Body Cavity Fluid Cytology Images.