Artificial Neural Network for Recognition of Glioblastomas in Brain SPECT Images with 99mTc-MIBI

Authors

  • Roberto León Castellón Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Departamento de Medicina Nuclear. La Habana, Cuba. https://orcid.org/0000-0002-6085-8565
  • Juan Miguel Martin Escuela Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Departamento de Medicina Nuclear. La Habana, Cuba. https://orcid.org/0000-0002-8710-0383
  • Silvia Salva Camaño Clínica Misericordia Internacional. Barranquilla, Colombia. https://orcid.org/0000-0001-8631-1958
  • Lissette Mejías Pérez Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Departamento de Medicina Nuclear. La Habana, Cuba. https://orcid.org/0000-0003-2126-8375
  • Lester Rodríguez Paleo Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Departamento de Medicina Nuclear. La Habana, Cuba. https://orcid.org/0000-0003-1489-1310
  • Yanaisa Sánchez Caballero Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Departamento de Medicina Nuclear. La Habana, Cuba. https://orcid.org/0009-0009-9815-6989
  • Denia Bonilla Padrón Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Departamento de Medicina Nuclear. La Habana, Cuba. https://orcid.org/0000-0003-4035-2337
  • Nelson Gómez Viera Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Servicio de Neurología. La Habana, Cuba. https://orcid.org/0000-0001-7077-6347
  • Adlin López Díaz Universidad de La Habana, Instituto de Tecnologías y Ciencias Aplicadas. La Habana, Cuba. https://orcid.org/0000-0002-1020-8775

Keywords:

glioblastoma, single photon emission tomography, artificial intelligence, artificial neural network

Abstract

Introduction: Gliomas represent approximately 25% of all brain tumors in adults, and glioblastoma is the most frequent malignant primary brain tumor. Artificial intelligence, particularly machine learning techniques have the potential to become very powerful diagnostic tools and reliable aids for clinical neurologists.

Objective: To determine the performance of an artificial neural network trained to identify glioblastomas by means of biomarkers extracted from brain SPECT images with 99mTc-MIBI using the multilayer perceptron.

Methods: An observational, cross-sectional, quantitative study was carried out, at Hermanos Ameijeiras Clinical Surgical Hospital, Havana, Cuba, from 2018 to 2020. The multilayer perceptron was used as algorithm and the k-fold cross validation method for validation. A class balance was performed on the training data using the Synthetic Minority Oversampling Technique algorithm in order to ensure higher quality metrics.

Results: Two hundred twenty images were analyzed, they were from early and late studies of brain single photon emission tomography with 99mTc-MIBI of 110 patients diagnosed with brain glioma. The general accuracy of the model was high, both in the training (97.3%) and in the test (97.1%) and the error was low, both for the training (2.7%) and for the test (2.9%). The retention index of the radiopharmaceutical was the variable with the greatest normalized weight from all the variables measured.

Conclusions: The proposed artificial neural network trained to recognize glioblastomas using the multilayer perceptron using biomarkers extracted from 99mTc-MIBI brain SPECT images in a database of brain gliomas had satisfactory training and excellent performance metrics.

Downloads

Download data is not yet available.

Author Biography

Roberto León Castellón, Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Departamento de Medicina Nuclear. La Habana, Cuba.

Doctor en Ciencias Médicas. Especialista II Grado en Neurología. Universidad de Ciencias Médicas de La Habana, Hospital Clínico Quirúrgico Hermanos Ameijeiras, Departamento de Medicina Nuclear. La Habana, Cuba.

References

1. Fordham AJ, Hacherl CC, Patel N, Jones K, Myers B, Abraham M, et al. Differentiating Glioblastomas from Solitary Brain Metastases: An Update on the Current Literature of Advanced Imaging Modalities. Cancers. 2021;13(12):2960. DOI: 10.3390/cancers13122960

2. Tan AC, Ashley DM, López GY, Malinzak M, Friedman HS, Khasraw M. Management of glioblastoma: State of the art and future directions. CA: A Cancer Journal for Clinicians. 2020;70(4):299-312. DOI: 10.3322/caac.21613

3. Thust SC, Heiland S, Falini A, Jäger HR, Waldman AD, Sundgren PC, et al. Glioma imaging in Europe: A survey of 220 centres and recommendations for best clinical practice. European Radiology. 2018;28(8):3306-17. DOI: 10.1007/s00330-018-5314-5.

4. Bruffaerts R. Machine learning in neurology: what neurologists can learn from machines and vice versa. Journal of Neurology. 2018;265(11):2745-8. DOI: 10.1007/s00415-018-8990-9

5. Bernstein A, Burnaev E, Kondratyeva E, Sushchinskaya S, Sharaev M, Andreev A, et al. Machine Learning pipeline for discovering neuroimaging-based biomarkers in neurology and psychiatry. Proceedings of Machine Learning Research, 2018;60:1-20. DOI: 10.48550/arXiv.1804.10163

6. Carleo G, Cirac I, Cranmer K, Daudet L, Schuld M, Tishby N, et al. Machine learning and the physical sciences. Reviews of Modern Physics. 2019;91(4). DOI: 10.1103/revmodphys.91.045002

7. Zander E, Ardeleanu A, Singleton R, Bede B, Wu Y, Zheng S. A functional artificial neural network for noninvasive pretreatment evaluation of glioblastoma patients. Neuro-Oncology Advances. 2021;4(1). DOI: 10.1093/noajnl/vdab167

8. Latif G, Ben Brahim, G, Iskandar DNFA, Bashar A, Alghazo J. Glioma Tumors’ classification using deep-neural-network-based features with SVM classifier. Diagnostics. 2022:1018. DOI: 10.3390/diagnostics12041018

9. Blanc Durand P, Van Der Gucht A, Schaefer N, Itti E, Prior JO. Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study. Sherman JH, editor. PLOS ONE. 2018;13(4):e0195798. DOI: 10.1371/journal.pone.0195798

10. Wei W, Ma L, Yang L, Lu R, Xi C. Artificial Intelligence Algorithm-Based Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) in the Treatment of Glioma Biopsy. Pallikonda Rajasekaran M, editor. Contrast Media & Molecular Imaging. 2022;2022:1-9. DOI: 10.1155/2022/5411801

11. Çinarer G, Emiroğlu BG, Yurttakal AH. Prediction of Glioma Grades Using Deep Learning with Wavelet Radiomic Features. Applied Sciences. 2020;10(18):6296. DOI: 10.3390/app10186296

12. Cassinelli Petersen GI, Shatalov J, Verma T, Brim WR, Subramanian H, Brackett A, et al. Machine Learning in Differentiating Gliomas from Primary CNS Lymphomas: A Systematic Review, Reporting Quality, and Risk of Bias Assessment. American Journal of Neuroradiology. 2022;43(4):526-33. DOI: 10.3174/ajnr.a7473

13. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research. 2002;16:321-57. DOI: 10.1613/jair.953

14. Ebrahimi Zade A, Shahabi Haghighi S, Soltani M. A neuro evolutionary algorithm for patient calibrated prediction of survival in Glioblastoma patients. Journal of Biomedical Informatics. 2021;115:103694. DOI: 10.1016/j.jbi.2021.103694

Downloads

Published

2023-10-11

How to Cite

1.
León Castellón R, Martin Escuela JM, Salva Camaño S, Mejías Pérez L, Rodríguez Paleo L, Sánchez Caballero Y, et al. Artificial Neural Network for Recognition of Glioblastomas in Brain SPECT Images with 99mTc-MIBI. Rev Cubana Neurol Neurocir [Internet]. 2023 Oct. 11 [cited 2025 Jul. 16];13(1). Available from: https://revneuro.sld.cu/index.php/neu/article/view/578

Issue

Vol. 13 No. 1 (2023): enero-abril

Section

Original research

License

Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)