CLASSIFICATION WITH MACHINE LEARNING METHODS FROM MULTI-SEQUENCE MR IMAGES OF CHILDHOOD POSTERIOR FOSSA TUMORS

Year 2024, Volume: 7 Issue: 2, 86 - 105, 30.12.2024

Nuray Demiröz , Semra İçer , Zehra Filiz Karaman

https://doi.org/10.47137/uujes.1501424

Abstract

Childhood brain tumors rank high among the leading causes of mortality, being the second most common type of cancer after leukemia. Abnormal structures in the brain are visualized using MRI techniques, which are the most commonly employed tools for distinguishing the neural structure of the human brain. However, identifying and diagnosing these abnormal structures can be a time-consuming and critical process. In this study, tumors in the Magnetic Resonance images of patients with Posterior Fossa tumors were segmented using two different image segmentation methods. Subsequently, numerical features were extracted from these tumors, and significant numerical features among tumor groups were determined using the Student's T-test; based on these features, tumor types were classified using machine learning algorithms. The study focused on the three most common types of Posterior Fossa tumors: Medulloblastoma, Ependymoma, and Pilocytic Astrocytoma, utilizing T2, Contrast-Enhanced T1, and ADC sequences. A total of forty-eight different numerical features were extracted from the segmented tumors and then acquired significant features were classified using five different machine learning algorithms. Among PA-MB, EM-MB and EM-PA tumor types, the average result of the most successful method in the T1 sequence was 86.93%, while it was 93.7% for the T2 sequence and 92.06% for the ADC sequence. Decision tree, SVM and Ensemble classifiers gave more successful results than others. As a result of the detailed examination, our study not only makes valuable contributions to the literature, but also has a promising structure in terms of its potential to help clinicians.

Keywords

Posterior Fossa tumors, Image processing, Feature extraction, Machine Learning.

Ethical Statement

Makalemizde Erciyes Üniversitesi Etik Kurul onayı alınmıştır. Makalede gerekli bilgi mevcuttur.

References

• Lannering B, Marky I, & Nordborg, C. (1990). Brain tumors in childhood and adolescence in west sweden 1970–1984 epidemiology and survival. Cancer, 66(3), 604-609.
• Prasad, K. S. V., Ravi, D., Pallikonda, V., & Raman, B. V. S. (2017). Clinicopathological study of pediatric posterior fossa tumors. Journal of pediatric neurosciences, 12(3), 245.
• KaatschP, RickertC,KühlJ, Schüz J, Michaelis J. Population-based epidemiologic data on brain tumors in German children. Cancer 2001;92(12):3155–64
• O’Brien D, Caird J, Kennedy M, et al. Posterior fossa tumours in childhood: evaluation of presenting clinical features. Ir Med J 2001;94:52–53
• Orphanidou-Vlachou, E., Vlachos, N., Davies, N.P., Arvanitis, T.N., Grundy, R.G., and Peet, A.C., 2014. Texture analysis of T1-and T2-weighted MR images and use of probabilistic neural network to discriminate posterior fossa tumours in children, NMR in Biomedicine, 27(6):632–639.
• Zhou, H., Hu, R., Tang, O., Hu, C., Tang, L., Chang, K., ... & Zhu, C. (2020). Automatic machine learning to differentiate pediatric posterior fossa tumors on routine MR imaging. American Journal of Neuroradiology, 41(7), 1279-1285.
• Traverso A, Wee L, Dekker A, Gillies R. Repeatability and reproducibility of radiomic features: a systematic review. Int J Radiat Oncol Biol Phys 2018;102(4):1143–58
• Wang, S., Wang, G., Zhang, W., He, J., Sun, W., Yang, M., ... & Peet, A. (2022). MRI-based whole-tumor radiomics to classify the types of pediatric posterior fossa brain tumor. Neurochirurgie, 68(6), 601-607.
• Bidiwala, S., & Pittman, T. (2004). Neural network classification of pediatric posterior fossa tumors using clinical and imaging data. Pediatric neurosurgery, 40(1), 8-15.
• Gutierrez, D. R., Awwad, A., Meijer, L., Manita, M., Jaspan, T., Dineen, R. A., ... & Auer, D. P. (2014). Metrics and textural features of MRI diffusion to improve classification of pediatric posterior fossa tumors. American Journal of Neuroradiology, 35(5), 1009-1015.
• Li, M., Shang, Z., Yang, Z., Zhang, Y., & Wan, H. (2019). Machine learning methods for MRI biomarkers analysis of pediatric posterior fossa tumors. Biocybernetics and Biomedical Engineering, 39(3), 765-774.
• Zarinabad, N., Abernethy, L. J., Avula, S., Davies, N. P., Rodriguez Gutierrez, D., Jaspan, T., ... & Peet, A. (2018). Application of pattern recognition techniques for classification of pediatric brain tumors by in vivo 3T 1H‐MR spectroscopy—A multi‐center study. Magnetic Resonance in Medicine, 79(4), 2359-2366.
• Sotoudeh, H., Saadatpour, Z., Rezaei, A., Sotoudeh, M., Wheeler, C.A., Singhal, A., and Tanwar, M., 2023. Radiomics for differentiation of the posterior fossa pilocytic astrocytoma versus hemangioblastomas in adults. A pilot study, Clinical Imaging, 93:26–30.
• Li, M., Wang, H., Shang, Z., Yang, Z., Zhang, Y., and Wan, H., 2020. Ependymoma and pilocytic astrocytoma: Differentiation using radiomics approach based on machine learning, Journal of Clinical Neuroscience, 78:175–180.
• Quon, J., Bala, W., Chen, L., Wright, J., Kim, L., Han, M., Shpanskaya, K., Lee, E., Tong, E., Iv, M., et al., 2020. Deep learning for pediatric posterior fossa tumor detection and classification: a multi-institutional study, American Journal of Neuroradiology, 41(9):1718–1725.
• Fetit, A.E., Novak, J., Rodriguez, D., Auer, D.P., Clark, C.A., Grundy, R.G., Peet, A.C., and Arvanitis, T.N., 2018. Radiomics in paediatric neuro-oncology: a multicentre study on MRI texture analysis, NMR in Biomedicine, 31(1):e3781.
• Osmanoğlu, Usame Ömer, et al. "Görüntü işleme ve analizinin tıpta kullanımı ve bir uygulama." Osmangazi Tıp Dergisi 41.1 (2016): 6-16.
• Borman, S. (2004). The expectation maximization algorithm-a short tutorial. Submitted for publication, 41.
• Lankton, S., & Tannenbaum, A. (2008). Localizing region-based active contours. IEEE transactions on image processing, 17(11), 2029-2039.
• Bozkurt, Ferhat, Cemal Köse, and Ahmet Sarı. "Bolge-tabanlı Aktif Kontur ve Sınıflandırma ile BTA Goruntulerinden Karotid Arterlerin Bolutlenmesi."
• Chan, T. F., & Vese, L. A. (2001). Active contours without edges. IEEE Transactions on image processing, 10(2), 266-277.
• Zulpe, N., & Pawar, V. (2012). GLCM textural features for brain tumor classification. International Journal of Computer Science Issues (IJCSI), 9(3), 354.
• Saman, S., & Jamjala Narayanan, S. (2019). Survey on brain tumor segmentation and feature extraction of MR images. International journal of multimedia information retrieval, 8, 79-99.
• Chaudhary, A., & Bhattacharjee, V. (2020). An efficient method for brain tumor detection and categorization using MRI images by K-means clustering & DWT. International Journal of Information Technology, 12, 141-148.
• Faisal, Z., & El Abbadi, N. K. (2020). Detection and recognition of brain tumor based on DWT, PCA and ANN. Indonesian Journal of Electrical Engineering and Computer Science, 18(1), 56-63.
• Mostafiz, R., Uddin, M. S., Alam, N. A., Hasan, M. M., & Rahman, M. M. (2021). MRI-based brain tumor detection using the fusion of histogram oriented gradients and neural features. Evolutionary Intelligence, 14, 1075-1087.
• Singh, A., Thakur, N., & Sharma, A. (2016, March). A review of supervised machine learning algorithms. In 2016 3rd international conference on computing for sustainable global development (INDIACom) (pp. 1310-1315).
• Ray, S. (2019, February). A quick review of machine learning algorithms. In 2019 International conference on machine learning, big data, cloud and parallel computing (COMITCon) (pp. 35-39). IEEE.
• Costa, V. G., & Pedreira, C. E. (2023). Recent advances in decision trees: An updated survey. Artificial Intelligence Review, 56(5), 4765-4800.
• ÇİÇEK, A., & ARSLAN, Y. (2020). Müşteri Kayıp Analizi İçin Sınıflandırma Algoritmalarının Karşılaştırılması. İleri Mühendislik Çalışmaları ve Teknolojileri Dergisi, 1(1), 13-19.
• De Lucia, C., Pazienza, P., & Bartlett, M. (2020). Does good ESG lead to better financial performances by firms? Machine learning and logistic regression models of public enterprises in Europe. Sustainability, 12(13), 5317.
• Zhou, Y., Cheng, G., Jiang, S., & Dai, M. (2020). Building an efficient intrusion detection system based on feature selection and ensemble classifier. Computer networks, 174, 107247.
• Guo, Z., Xu, L., & Ali Asgharzadeholiaee, N. (2022). A homogeneous ensemble classifier for breast cancer detection using parameters tuning of MLP neural network. Applied Artificial Intelligence, 36(1), 2031820.
• O’Brien D, Caird J, Kennedy M, et al. Posterior fossa tumours in childhood: evaluation of presenting clinical features. Ir Med J 2001;94:52–53
• Brandão, L. A., & Poussaint, T. Y. (2017). Posterior fossa tumors. Neuroimaging Clinics, 27(1), 1-37.
• Kerleroux B, Cottier JP, Janot K, et al. Posterior fossa tumors in children: radiological tips & tricks in the age of genomic tumor classification and advance MR technology. J Neuroradiol 2020;47:46–53
• Jaremko, J. L., Jans, L. B. O., Coleman, L. T., & Ditchfield, M. R. (2010). Value and limitations of diffusion-weighted imaging in grading and diagnosis of pediatric posterior fossa tumors. American journal of neuroradiology, 31(9), 1613-1616.
• Schneider, J. F., Confort‐Gouny, S., Viola, A., Le Fur, Y., Viout, P., Bennathan, M., ... & Girard, N. (2007). Multiparametric differentiation of posterior fossa tumors in children using diffusion‐weighted imaging and short echo‐time 1H‐MR spectroscopy. Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine, 26(6), 1390-1398.
• Pringle, C., Kilday, J. P., Kamaly-Asl, I., & Stivaros, S. M. (2022). The role of artificial intelligence in paediatric neuroradiology. Pediatric Radiology, 52(11), 2159-2172.
• Ismael, S. A. A., Mohammed, A., & Hefny, H. (2020). An enhanced deep learning approach for brain cancer MRI images classification using residual networks. Artificial intelligence in medicine, 102, 101779.
• Buchlak, Q. D., Esmaili, N., Leveque, J. C., Bennett, C., Farrokhi, F., & Piccardi, M. (2021). Machine learning applications to neuroimaging for glioma detection and classification: An artificial intelligence augmented systematic review. Journal of Clinical Neuroscience, 89, 177-198.
• Massimino, M., Cefalo, G., Riva, D., Biassoni, V., Spreafico, F., Pecori, E., ... & Gandola, L. (2012). Long-term results of combined preradiation chemotherapy and age-tailored radiotherapy doses for childhood medulloblastoma. Journal of neuro-oncology, 108, 163-171.