Texture, Morphology, and Statistical Analysis to Differentiate Primary Brain Tumors on Two-Dimensional Magnetic Resonance Imaging Scans Using Artificial Intelligence Techniques
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: A primary brain tumor starts to grow from brain cells, and it occurs as a result of errors in the DNA of normalcells. Therefore, this study was carried out to analyze the two-dimensional (2D) texture, morphology, and statistical featuresof brain tumors and to perform a classification using artificial intelligence (AI) techniques. Methods: AI techniques can helpradiologists to diagnose primary brain tumors without using any invasive measurement techniques. In this paper, we focusedon deep learning (DL) and machine learning (ML) techniques for texture, morphological, and statistical feature classificationof three tumor types (namely, glioma, meningioma, and pituitary). T1-weighted magnetic resonance imaging (MRI) 2D scanswere used for analysis and classification (multiclass and binary). A total of 102 features were calculated for each tumor, and the20 most significant features were selected using the three-step feature selection method, which included removing duplicatefeatures, Pearson correlations, and recursive feature elimination. Results: From the predicted results of multiclass and binaryclassification, a long short-term memory binary classification (glioma vs. meningioma) showed the best performance, withan average accuracy, recall, precision, F1-score, and kappa coefficient of 97.7%, 97.2%, 97.5%, 97.0%, and 94.7%, respectively. Conclusions: The early diagnosis of primary brain tumors is very important because it can be the key to effective treatment. Therefore, this research presents a method for early diagnoses by effectively classifying three types of primary brain tumors.
Abstract
Objectives: A primary brain tumor starts to grow from brain cells, and it occurs as a result of errors in the DNA of normalcells. Therefore, this study was carried out to analyze the two-dimensional (2D) texture, morphology, and statistical featuresof brain tumors and to perform a classification using artificial intelligence (AI) techniques. Methods: AI techniques can helpradiologists to diagnose primary brain tumors without using any invasive measurement techniques. In this paper, we focusedon deep learning (DL) and machine learning (ML) techniques for texture, morphological, and statistical feature classificationof three tumor types (namely, glioma, meningioma, and pituitary). T1-weighted magnetic resonance imaging (MRI) 2D scanswere used for analysis and classification (multiclass and binary). A total of 102 features were calculated for each tumor, and the20 most significant features were selected using the three-step feature selection method, which included removing duplicatefeatures, Pearson correlations, and recursive feature elimination. Results: From the predicted results of multiclass and binaryclassification, a long short-term memory binary classification (glioma vs. meningioma) showed the best performance, withan average accuracy, recall, precision, F1-score, and kappa coefficient of 97.7%, 97.2%, 97.5%, 97.0%, and 94.7%, respectively. Conclusions: The early diagnosis of primary brain tumors is very important because it can be the key to effective treatment. Therefore, this research presents a method for early diagnoses by effectively classifying three types of primary brain tumors.
참고문헌 (30)
- Herholz K, "Brain tumors", Semin Nucl Med, 42(6), pp.356~370 (2012)
- Kheirollahi M, "Brain tumors : special characters for research and banking", Adv Biomed Res, 4, pp.4~ (2015)
- Lapointe S, "Primary brain tumours in adults", Lancet, 392(10145), pp.432~446 (2018)
- Tunthanathip T, "Multiple, primary brain tumors with diverse origins and different localizations : case series and review of the literature", J Neurosci Rural Pract, 9(4), pp.593~607 (2018)
- Louis DN, "The 2016 World Health Organization Classification of Tumors of the Central Nervous System : a summary", Acta Neuropathol, 131(6), pp.803~820 (2016)
- Escudero Sanchez L, "Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle", Sci Rep, 11(1), pp.8262~ (2021)
- Babu PR, "ML and DL based classification model of lung cancer using nodule volume", Proceedings of 2020 4th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), pp.1001~1006 (2020)
- Kim CH, "Artificial intelligence techniques for prostate cancer detection through dual-channel tissue feature engineering", Cancers(Basel), 13(7), pp.1524~ (2021)
- "Brain tumor dataset" (2017)[URL]
- Cheng J, "Enhanced performance of brain tumor classification via tumor region augmentation and partition", PLoS One, 10(10), pp.e0140381~ (2015)[DOI]
- Duron L, "Gray-level discretization impacts reproducible MRI radiomics texture features", PLoS One, 14(3), pp.e0213459~ (2019)[DOI]
- Chen CH, "Radiomic features analysis in computed tomography images of lung nodule classification", PLoS One, 13(2), pp.e0192002~ (2018)[DOI]
- Chaddad A, "Automated feature extraction in brain tumor by magnetic resonance imaging using Gaussian mixture models", Int J Biomed Imaging, 2015, pp.868031~ (2015)
- Thibault G, "Shape and texture indexes application to cell nuclei classification", Int J Pattern Recognit Artif Intell, 27(01), pp.1357002~ (2013)
- Wah YB, "Feature selection methods : case of filter and wrapper approaches for maximising classification accuracy", Pertanika J Sci Technol, 26(1), pp.329~340 (2018)
- Hameed SS, "Filterwrapper combination and embedded feature selection for gene expression data", Int J Adv Soft Comput Appl, 10(1), pp.90~105 (2018)
- Hui KH, "An improved wrapper-based feature selection method for machinery fault diagnosis", PLoS One, 12(12), pp.e0189143~ (2017)[DOI]
- Karim F, "Insights into LSTM fully convolutional networks for time series classification", IEEE Access, 7, pp.67718~67725 (2019)
- Schuster M, "Bidirectional recurrent neural networks", IEEE Trans Signal Process, 45(11), pp.2673~2681 (1997)
- Ramachandran P, "Searching for activation functions", Proceedings of the 6th International Conference on Learning Representations (ICLR) (2018)
- Sultan HH, "Multi-classification of brain tumor images using deep neural network", IEEE Access, 7, pp.69215~69225 (2019)
- Machhale K, "MRI brain cancer classification using hybrid classifier (SVMKNN)", Proceedings of 2015 International Conference on Industrial Instrumentation and Control (ICIC), pp.60~65 (2015)
- Hossin M, "A review on evaluation metrics for data classification evaluations", Int J Data Min Knowl Manag Process, 5(2), pp.1~ (2015)
- Alqudah AM, "Brain tumor classification using deep learning technique : a comparison between cropped, uncropped, and segmented lesion images with different sizes", Int J Adv Trends Comput Sci Eng, 8(6), pp.3684~3691 (2019)
- Pashaei A, "Brain tumor classification via convolutional neural network and extreme learning machines", Proceedings of 2018 8th International Conference on Computer and Knowledge Engineering (ICCKE), pp.314~319 (2018)
- Diaz-Pernas FJ, "A Deep learning approach for brain tumor classification and segmentation using a multiscale convolutional neural network", Healthcare(Basel), 9(2), pp.153~ (2021)
- Swati ZN, "Brain tumor classification for MR images using transfer learning and fine-tuning", Comput Med Imaging Graph, 75, pp.34~46 (2019)
- Ismael MR, "Brain tumor classification via statistical features and back-propagation neural network", Proceedings of 2018 IEEE International Conference on Electro, 2018, 252~257
- Badza MM, "Classification of brain tumors from MRI images using a convolutional neural network", Appl Sci, 10(6), pp.1999~ (2020)
- Cheng J, "Retrieval of brain tumors by adaptive spatial pooling and Fisher vector representation", PLoS One, 11(6), pp.e0157112~ (2016)[DOI]