Avaliação do uso de transfer learning para detecção de tumores cerebrais em imagens médicas
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1302Palavras-chave:
Transfer Learning, Rede Neural Convolucional, Tumor CerebralResumo
Objetivo: Com aumento da viabilidade da aplicação das neurais convolucionais (CNNs) foi objetivado avaliar o uso de desta tecnologia para a detecção de tumores cerebrais em imagens de ressonância magnética computadorizada Método: Foram desenvolvidos dois modelos distintos de CNNs, uma com o uso de Transfer learning e outra sem, para classificar a ocorrência de tumor cerebral. Resultados: foi obtido, com o modelo sem o uso de transfer learning uma acurácia de 99,67%, com sensibilidade de 100% e especificidade de 99,34%; já com o modelo que usou transfer learning, obteve uma acurácia de 98%, com sensibilidade de 98,32% e especificidade de 97,69%. Conclusão: Este estudo destaca a eficácia das CNNs na detecção de tumores cerebrais, sugerindo o uso de sistemas inteligentes como ferramentas de auxílio.
Referências
Rethemiotaki I. Brain tumour detection from magnetic resonance imaging using convolutional neural networks. Contemp Oncol [Internet]. 2023 [cited 2024 Apr 21];27(4):230. Available from: /pmc/articles/PMC10883197/ DOI: https://doi.org/10.5114/wo.2023.135320
Fritz A, Percy C, Jack A. International Classification of Diseases for Oncology. Third. Vol. 1. Switzerland: World Health Organization; 2000. 0–222 p.
Tandel GS, Biswas M, Kakde OG, Tiwari A, Suri HS, Turk M, et al. A review on a deep learning perspective in brain cancer classification. Cancers (Basel) [Internet]. 2019 Jan 18 [cited 2021 Dec 12];11(1):111. Available from: https://www.mdpi.com/2072-6694/11/1/111/htm DOI: https://doi.org/10.3390/cancers11010111
Kang J, Ullah Z, Gwak J. Mri-based brain tumor classification using ensemble of deep features and machine learning classifiers. Sensors [Internet]. 2021 Mar 22 [cited 2021 Dec 12];21(6):1–21. Available from: https://www.mdpi.com/1424-8220/21/6/2222/htm
Patel AP, Fisher JL, Nichols E, Abd-Allah F, Abdela J, Abdelalim A, et al. Global, regional, and national burden of brain and other CNS cancer, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet Neurol [Internet]. 2019 Apr 1 [cited 2024 Apr 22];18(4):376–93. Available from: https://pubmed.ncbi.nlm.nih.gov/30797715/
Naseer A, Yasir T, Azhar A, Shakeel T, Zafar K. Computer-Aided Brain Tumor Diagnosis: Performance Evaluation of Deep Learner CNN Using Augmented Brain MRI. Int J Biomed Imaging. 2021;2021.
Fernandes SL, Tanik UJ, Rajinikanth V, Karthik KA. A reliable framework for accurate brain image examination and treatment planning based on early diagnosis support for clinicians. Neural Comput Appl [Internet]. 2020 Oct 1 [cited 2024 Apr 22];32(20):15897–908. Available from: https://link.springer.com/article/10.1007/s00521-019-04369-5 DOI: https://doi.org/10.1007/s00521-019-04369-5
Naseer A, Yasir T, Azhar A, Shakeel T, Zafar K. Computer-Aided Brain Tumor Diagnosis: Performance Evaluation of Deep Learner CNN Using Augmented Brain MRI. Int J Biomed Imaging. 2021;2021. DOI: https://doi.org/10.1155/2021/5513500
Naseer A, Zafar K. Comparative Analysis of Raw Images and Meta Feature based Urdu OCR using CNN and LSTM. International Journal of Advanced Computer Science and Applications. 2018;9(1):419–24. DOI: https://doi.org/10.14569/IJACSA.2018.090157
Naseer A, Zafar K. Meta features-based scale invariant OCR decision making using LSTM-RNN. Comput Math Organ Theory [Internet]. 2019 Jun 1 [cited 2024 Apr 22];25(2):165–83. Available from: https://link.springer.com/article/10.1007/s10588-018-9265-9 DOI: https://doi.org/10.1007/s10588-018-9265-9
Papageorgiou V. Brain tumor detection based on features extracted and classified using a low-complexity neural network. Traitement du Signal. 2021 Jun 1;38(3):547–54.
Papageorgiou EI, Spyridonos PP, Glotsos DT, Stylios CD, Ravazoula P, Nikiforidis GN, et al. Brain tumor characterization using the soft computing technique of fuzzy cognitive maps. Applied Soft Computing Journal. 2008 Jan 1;8(1):820–8. DOI: https://doi.org/10.1016/j.asoc.2007.06.006
Deepak S, Ameer PM. Brain tumor classification using deep CNN features via transfer learning. Comput Biol Med [Internet]. 2019 Aug 1 [cited 2024 Apr 28];111. Available from: https://pubmed.ncbi.nlm.nih.gov/31279167/ DOI: https://doi.org/10.1016/j.compbiomed.2019.103345
Wu M, Liu Q, Yan C, Sen G. Multi-Classification of Brain Tumors on Magnetic Resonance Images Using an Ensemble of Pre-Trained Convolutional Neural Networks. Curr Med Imaging [Internet]. 2022 Apr 18 [cited 2024 Apr 28];19(1):65–76. Available from: https://pubmed.ncbi.nlm.nih.gov/35430973/ DOI: https://doi.org/10.2174/1573405618666220415122843
Swati ZNK, Zhao Q, Kabir M, Ali F, Ali Z, Ahmed S, et al. Brain tumor classification for MR images using transfer learning and fine-tuning. Comput Med Imaging Graph [Internet]. 2019 Jul 1 [cited 2024 Apr 28];75:34–46. Available from: https://pubmed.ncbi.nlm.nih.gov/31150950/ DOI: https://doi.org/10.1016/j.compmedimag.2019.05.001
Kang J, Ullah Z, Gwak J. Mri-based brain tumor classification using ensemble of deep features and machine learning classifiers. Sensors. 2021 Mar 22;21(6):1–21. DOI: https://doi.org/10.3390/s21062222
Br35H :: Detecção de tumor cerebral 2020 | Kaggle [Internet]. [cited 2021 Dec 12]. Available from: https://www.kaggle.com/ahmedhamada0/brain-tumor-detection
Papageorgiou V. Brain tumor detection based on features extracted and classified using a low-complexity neural network. Traitement du Signal. 2021 Jun 1;38(3):547–54. DOI: https://doi.org/10.18280/ts.380302
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. Int J Comput Vis [Internet]. 2016 Oct 7 [cited 2024 May 27];128(2):336–59. Available from: http://arxiv.org/abs/1610.02391 DOI: https://doi.org/10.1007/s11263-019-01228-7
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
A submissão de um artigo ao Journal of Health Informatics é entendida como exclusiva e que não está sendo considerada para publicação em outra revista. A permissão dos autores para a publicação de seu artigo no J. Health Inform. implica na exclusiva autorização concedida aos editores para incluí-lo na revista. Ao submeter um artigo, ao autor será solicitada a permissão eletrônica de um Termo de Transferência de Direitos Autorais. Uma mensagem eletrônica será enviada ao autor correspondente confirmando o recibo do manuscrito e o aceite da Declaração de Direito Autoral.
