CLASSIFICATION OF BRAIN TUMOR FROM MR IMAGES WITH LSTM-CNN HYBRID MODEL

Yıl 2024, Cilt: 11 Sayı: 22, 63 - 81, 30.04.2024

Emrah Aslan

https://doi.org/10.54365/adyumbd.1391157

Öz

Early detection of brain tumours is vital for effective treatment. Magnetic resonance imaging (MRI) is a fundamental tool for detecting brain tumours. There are many types of tumours such as glioma, meningioma, pituitary. Accurately determining the tumour type and making this determination is one of the most challenging aspects of classifying brain tumours. The use of artificial intelligence-based computer applications instead of traditional methods of disease detection can make significant contributions to experts in the detection of brain tumours. Especially deep learning methods are effective in disease detection based on the processing of medical images. In the literature, there are many deep learning-based approaches for categorising brain tumours. In this study, a model combining a CNN (Convolutional Neural Network) and a LSTM (Long Short Term Memory) deep learning layer is presented to detect brain tumours with MRI images. It is suggested that LSTM can support the feature extraction capabilities of CNN. In the experiments, it is found that the proposed LSTM-CNN model outperforms the standard CNN model. Using this model, an accuracy score of 98.1% was obtained in the detection of brain tumours. This result shows that it achieves a higher success compared to similar studies in the literature.

Anahtar Kelimeler

CNN, LSTM, Tumour, MRI

LSTM-ESA HİBRİT MODELİ İLE MR GÖRÜNTÜLERİNDEN BEYİN TÜMÖRÜNÜN SINIFLANDIRILMASI

Öz

Beyin tümörlerinin erken teşhisi, etkili bir tedavi için hayati öneme sahiptir. Manyetik rezonans (MR) görüntüleme, beyin tümörlerini tespit etmede temel bir araç olarak öne çıkmaktadır. Glioma, meningioma, pituitary gibi birçok tümör türü bulunmaktadır. Tümör türünü doğru bir şekilde belirlemek ve bu tespiti yapmak, beyin tümörlerini sınıflandırmanın en zorlu yönlerinden biridir. Geleneksel yöntemlerle hastalık tespiti yerine, yapay zekâ temelli bilgisayar uygulamalarının kullanılması, beyin tümörlerinin tespitinde uzmanlara önemli katkılar sağlayabilir. Özellikle derin öğrenme yöntemleri, medikal görüntülerin işlenmesine dayalı hastalık tespitinde etkili olmaktadır. Literatürde, beyin tümörlerini kategorize etmek için birçok derin öğrenme tabanlı yaklaşım bulunmaktadır. Bu çalışmada, MR görüntüleri ile beyin tümörlerini tespit etmek için bir ESA (Evrişimli Sinir Ağı) ve bir LSTM (Uzun Kısa Süreli Bellek) derin öğrenme katmanının birleştirilmiş olduğu bir model sunulmaktadır. LSTM'nin, ESA'nın özellik çıkarma yeteneklerini destekleyebileceği öne sürülmektedir. Yapılan deneylerde, önerilen LSTM-ESA modelinin standart ESA modelinden daha iyi performans gösterdiği belirlenmiştir. Bu modelin kullanılmasıyla, beyin tümörlerinin tespitinde %98,1 doğruluk skoru elde edilmiştir. Bu sonuç, literatürdeki benzer çalışmalarla karşılaştırıldığında daha yüksek bir başarı elde ettiğini göstermektedir.

Anahtar Kelimeler

LSTM, Tümör, MR, ESA

Kaynakça

• S. Abbas et al., "BCD-WERT: a novel approach for breast cancer detection using whale optimization based efficient features and extremely randomized tree algorithm," PeerJ Computer Science, 2021.
• C. Dhanamjaya et al., "Identification of malnutrition and prediction of BMI from facial images using real-time image processing and machine learning," IET Image Processing, 2021.
• T.R. Gadekallu et al., "Hand gesture classification using a novel CNN-crow search algorithm," Complex & Intelligent Systems, 2021, pp. 1–14.
• E.F. Badran et al., "An algorithm for detecting brain tumors in MRI images," in The 2010 International Conference on Computer Engineering & Systems, Cairo, Egypt, 2010, pp. 368–373.
• İ. Çetiner, "Konvolüsyonel Sinir Ağı Kullanılarak Sıtma Hastalığı Sınıflandırılması," Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, c. 9, no. 17, pp. 273–286, Ağu. 2022.
• H. Çetiner, "Multı-Label Text Analysıs Wıth A Cnn And Lstm Based Hybrıd Deep Learnıng Model," Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, c. 9, no. 17, pp. 447–457, Ağu. 2022.
• B. Srikanth and S. Venkata Suryanarayana, "Multi-Class classification of brain tumor images using data augmentation with deep neural network," in Materials Today: Proceedings, 2021.
• R. Hashemzehi et al., "Detection of brain tumors from MRI images base on deep learning using hybrid models CNN and NADE," Biocybern. Biomed. Eng., vol. 40, no. 3, pp. 1225–1232, 2020.
• S. Halimeh Sinar and M.D. Teshnehlab, "Diagnosing and Classification Tumor and M.S. Simultaneous Magnetic Resonance Images Using Convolution Neural Network," CFIS, 2019.
• P.M. Ameer and S. Deepak, "Brain tumor classification using deep CNN features via transfer learning," Computers in Biology and Medicine, vol. 111, 2019, Art. no. 103345.
• H.E.S.M. Mohsen and A.B.M. Salem, "Classification using deep learning neural networks for brain tumors," FCIJ, 2018, pp. 68–71.
• Z. Sobhaninia et al., "Brain tumor segmentation using deep learning by type-specific sorting of images," Computer Science, 2018.
• S. Sajid et al., "Brain tumor detection and Segmentation in M.R. images using deep learning," Arabian Journal for Science and Engineering, vol. 44, no. 11, pp. 9249–9261, 2019.
• S. Hussain and M. Majid, "Brain tumor segmentation using cascaded deep convolutional neural network," in 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju, Korea (South), 2017, pp. 1998–2001.
• S. Pereira, "Brain tumor segmentation using convolutional neural networks in MRI images," IEEE transactions on medical imaging, vol. 35, no. 5, pp. 1240–1251, 2016.
• M. Nagori and M. Joshi, "Methods and algorithms for extracting values from MRS Graph for brain tumor detection," in 2013 International Conference on Electronic Engineering and Computer Science (EECS 2013), Beijing, China, 2013, pp. 331–336.
• A. Carlos et al., "Automated classification of brain tumors from short echo time in vivo MRS data using gaussian decomposition and bayesian neural networks," Expert Syst. Appl., vol. 41, pp. 5296–5307, 2014.
• G. Swapna, K.P. Soman, and R. Vinayakumar, "Automated detection of diabetes using ESA and ESA-LSTM network and heart rate signals," Procedia Comput. Sci., vol. 132, pp. 1253–1262, 2018.
• S. Tanveer et al., "Cuffless blood pressure estimation from electrocardiogram and photoplethysmogram using waveform based ANN-LSTM network," Biomed. Signal Process. Control, vol. 51, pp. 382–392, 2019.
• B. Sartaj, "Kaggle Dataset, Brain Tumor Classification (MRI)," 7 April 2019 [Online]. Available: https://www.kaggle.com/datasets/sartajbhuvaji/brain-tumor-classification-mri.
• A.I. Tawk and W.H. Kamr, "Diagnostic value of 3D-FLAIR magnetic resonance sequence in detection of white matter brain lesions in multiple sclerosis," Egyptian J. Radiol. Nucl. Med., vol. 51, no. 1, pp. 1–9, Dec. 2020.
• Y. Özüpak, "Evrişimli Sinir Ağı (ESA) Mimarileri ile Hücre Görüntülerinden Sıtmanın Tespit Edilmesi," Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, vol. 39, no. 1, pp. 197–210, 2024.
• Y. Zhuge et al., "Automated glioma grading on conventional MRI images using deep convolutional neural networks," Med. Phys., vol. 47, no. 7, pp. 3044–3053, Jul. 2020.
• E. Aslan and Y. Özüpak, "Classification of Blood Cells with Convolutional Neural Network Model," Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 13, no. 1, pp. 314–326, 2024.
• I. Shahzadi et al., "CNN-LSTM: Cascaded framework for brain tumour classi_cation," in Proc. IEEE-EMBS Conf. Biomed. Eng. Sci. (IECBES), Dec. 2018, pp. 633–637.
• S.B. Jiang et al., "An efficient fault diagnostic method for three-phase induction motors based on incremental broad learning and non-negative matrix factorization," IEEE Access, vol. 7, pp. 17780–17790, 2019.
• A.A. Novikov et al., "Deep sequential segmentation of organs in volumetric medical scans," IEEE Trans. Med. Imag., vol. 38, no. 5, pp. 1207–1215, May 2019.
• M.M. Badža and M.Č. Barjaktarović, "Classification of brain tumors from MRI images using a convolutional neural network," Appl Sci., vol. 10, no. 6, Art. no. 1999, 2020.
• P. Afshar, A. Mohammadi, and K.N. Plataniotis, "Brain tumor type classification via capsule networks," in 2018 25th IEEE international conference on image processing (ICIP), IEEE, 2018, pp. 3129–3133.
• A. Gumaei et al., "A Hybrid feature extraction method with regularized extreme learning machine for brain tumor classification," IEEE Access, vol. 7, pp. 36266–36273, 2019.
• A. Pashaei, H. Sajedi, and N. Jazayeri, "Brain tumor classification via convolutional neural network and extreme learning machines," in 2018 8th international conference on computer and knowledge engineering (ICCKE), IEEE, 2018.
• N. Abiwinanda et al., "Brain tumor classification using convolutional neural network," in World congress on medical physics and biomedical engineering 2018, Singapore: Springer, 2019, pp. 183–189.
• D.J. Hemanth et al., "A modi_ed deep convolutional neural network for abnormal brain image classi_cation," IEEE Access, vol. 7, pp. 4275–4283, 2018.
• H. Mzoughi et al., "Deep multi-scale 3D convolutional neural network (CNN) for MRI gliomas brain tumor classi_cation," J. Digit. Imag., vol. 33, no. 4, pp. 903–915, Aug. 2020.