Brain tumor segmentation and classification by improved binomial thresholding and multi-features selection

被引:65
|
作者
Sharif M. [1 ]
Tanvir U. [1 ]
Munir E.U. [1 ]
Khan M.A. [2 ]
Yasmin M. [1 ]
机构
[1] Department of Computer Science, COMSATS University Islamabad, Wah Campus, Islamabad
[2] Department of Computer Science and Engineering, HITEC University, Museum Road, Taxila
关键词
Brain MRI; Geometric features; SVM; Texture features; Thresholding;
D O I
10.1007/s12652-018-1075-x
中图分类号
学科分类号
摘要
A malignant tumor in brain is detected using images from Magnetic Resonance scanners. Malignancy detection in brain and separation of its tissues from normal brain cells allows to correctly localizing abnormal tissues in brain’s Magnetic Resonance Imaging (MRI). In this article, a new method is proposed for the segmentation and classification of brain tumor based on improved saliency segmentation and best features selection approach. The presented method works in four pipe line procedures such as tumor preprocessing, tumor segmentation, feature extraction and classification. In the first step, preprocessing is performed to extract the region of interest (ROI) using manual skull stripping and noise effects are removed by Gaussian filter. Then tumor is segmented in the second step by improved thresholding method which is implemented by binomial mean, variance and standard deviation. In the third step, geometric and four texture features are extracted. The extracted features are fused by a serial based method and best features are selected using Genetic Algorithm (GA). Finally, support vector machine (SVM) of linear kernel function is utilized for the classification of selected features. The proposed method is tested on two data sets including Harvard and Private. The Private data set is collected from Nishtar Hospital Multan, Pakistan. The proposed method achieved average classification accuracy of above 90% for both data sets which shows its authenticity. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.
引用
收藏
页码:1063 / 1082
页数:19
相关论文
共 50 条
  • [41] Within-brain classification for brain tumor segmentation
    Mohammad Havaei
    Hugo Larochelle
    Philippe Poulin
    Pierre-Marc Jodoin
    International Journal of Computer Assisted Radiology and Surgery, 2016, 11 : 777 - 788
  • [42] Within-brain classification for brain tumor segmentation
    Havaei, Mohammad
    Larochelle, Hugo
    Poulin, Philippe
    Jodoin, Pierre-Marc
    INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2016, 11 (05) : 777 - 788
  • [43] Otsu's thresholding technique for MRI image brain tumor segmentation
    Nyo, Myat Thet
    Mebarek-Oudina, F.
    Hlaing, Su Su
    Khan, Nadeem A.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (30) : 43837 - 43849
  • [44] Otsu’s thresholding technique for MRI image brain tumor segmentation
    Myat Thet Nyo
    F. Mebarek-Oudina
    Su Su Hlaing
    Nadeem A. Khan
    Multimedia Tools and Applications, 2022, 81 : 43837 - 43849
  • [45] Multiclass Brain Tumor Classification using Region Growing based Tumor Segmentation and Ensemble Wavelet Features
    Latif, Ghazanfar
    Iskandar, D. N. F. Awang
    Alghazo, Jaafar
    2018 INTERNATIONAL CONFERENCE ON COMPUTING AND BIG DATA (ICCBD 2018), 2018, : 67 - 72
  • [46] Performance evaluation of brain tumor detection using watershed Segmentation and thresholding
    Mishra, Shruti
    Roy, Noyonika
    Bapat, Meghana
    Gudipalli, Abhishek
    INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS, 2021, 14 (01): : 1 - 12
  • [47] A Survey of Brain Tumor Segmentation and Classification Algorithms
    Biratu, Erena Siyoum
    Schwenker, Friedhelm
    Ayano, Yehualashet Megersa
    Debelee, Taye Girma
    JOURNAL OF IMAGING, 2021, 7 (09)
  • [48] An Efficient Algorithm for Segmentation and Classification of Brain Tumor
    Veer , Shubhangi S.
    Deshpande, Anupama.
    Patil, P. M.
    2018 INTERNATIONAL CONFERENCE ON ADVANCES IN COMMUNICATION AND COMPUTING TECHNOLOGY (ICACCT), 2018, : 83 - 88
  • [49] Deep-Net: Fine-Tuned Deep Neural Network Multi-Features Fusion for Brain Tumor Recognition
    Khan, Muhammad Attique
    Mostafa, Reham R.
    Zhang, Yu-Dong
    Baili, Jamel
    Alhaisoni, Majed
    Tariq, Usman
    Khan, Junaid Ali
    Kim, Ye Jin
    Cha, Jaehyuk
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 76 (03): : 3029 - 3047
  • [50] BRAIN TUMOR DETECTION AND CLASSIFICATION MODEL USING OPTIMAL KAPUR'S THRESHOLDING BASED SEGMENTATION WITH DEEP NEURAL NETWORKS
    Devanathan, Bakthavachalam
    Venkatachalapathy, Kaliyappan
    IIOAB JOURNAL, 2020, 11 (04) : 1 - 8