Machine learning based brain tumour segmentation on limited data using local texture and abnormality

被引:50
作者
Bonte, Stijn [1 ,2 ,3 ]
Goethals, Ingeborg [1 ]
Van Holen, Roel [2 ]
机构
[1] Ghent Univ Hosp, Dept Nucl Med, Ghent, Belgium
[2] Univ Ghent, Dept Elect & Informat Syst, Med Imaging & Signal Proc MEDISIP, Ghent, Belgium
[3] IBiTech, Campus UZ,Entrance 36,Corneel Heymanslaan 10, B-9000 Ghent, Belgium
关键词
Brain tumour; Segmentation; Random forests; Abnormality; Texture; Machine learning; CLASSIFICATION; SYSTEM;
D O I
10.1016/j.compbiomed.2018.05.005
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Brain tumour segmentation in medical images is a very challenging task due to the large variety in tumour shape, position, appearance, scanning modalities and scanning parameters. Most existing segmentation algorithms use information from four different MRI-sequences, but since this is often not available, there is need for a method able to delineate the different tumour tissues based on a minimal amount of data. We present a novel approach using a Random Forests model combining voxelwise texture and abnormality features on a contrast-enhanced T1 and FLAIR MRI. We transform the two scans into 275 feature maps. A random forest model next calculates the probability to belong to 4 tumour classes or 5 normal classes. Afterwards, a dedicated voxel clustering algorithm provides the final tumour segmentation. We trained our method on the BraTS 2013 database and validated it on the larger BraTS 2017 dataset. We achieve median Dice scores of 40.9% (low-grade glioma) and 75.0% (high-grade glioma) to delineate the active tumour, and 68.4%/80.1% for the total abnormal region including edema. Our fully automated brain tumour segmentation algorithm is able to delineate contrast enhancing tissue and oedema with high accuracy based only on post-contrast T1-weighted and FLAIR MRI, whereas for non-enhancing tumour tissue and necrosis only moderate results are obtained. This makes the method especially suitable for high-grade glioma.
引用
收藏
页码:39 / 47
页数:9
相关论文
共 50 条
  • [31] An empirical study of different machine learning techniques for brain tumor classification and subsequent segmentation using hybrid texture feature
    Biswajit Jena
    Gopal Krishna Nayak
    Sanjay Saxena
    Machine Vision and Applications, 2022, 33
  • [32] An empirical study of different machine learning techniques for brain tumor classification and subsequent segmentation using hybrid texture feature
    Jena, Biswajit
    Nayak, Gopal Krishna
    Saxena, Sanjay
    MACHINE VISION AND APPLICATIONS, 2022, 33 (01)
  • [33] Efficient Brain Tumour Segmentation Using Co-registered Data and Ensembles of Specialised Learners
    Shah, Beenitaben
    Madabushi, Harish Tayyar
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES (BRAINLES 2020), PT II, 2021, 12659 : 15 - 29
  • [34] Machine Learning Based Stroke Segmentation and Classification from CT-Scan: A Survey
    Zewde, Elbetel Taye
    Motuma, Mersibon Melese
    Ayano, Yehualashet Megersa
    Debelee, Taye Girma
    Feyisa, Degaga Wolde
    PAN-AFRICAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, PT I, PANAFRICON AI 2023, 2024, 2068 : 3 - 45
  • [35] Cancer detection and segmentation using machine learning and deep learning techniques: a review
    Rai, Hari Mohan
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (09) : 27001 - 27035
  • [36] Model-Based Learning of Local Image Features for Unsupervised Texture Segmentation
    Kiechle, Martin
    Storath, Martin
    Weinmann, Andreas
    Kleinsteuber, Martin
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (04) : 1994 - 2007
  • [37] An MRI brain tumour detection using logistic regression-based machine learning model
    Srinivasarao Gajula
    V. Rajesh
    International Journal of System Assurance Engineering and Management, 2024, 15 : 124 - 134
  • [38] Breast tumour detection using machine learning: review of selected methods from 2015 to 2021
    Sharma, Gouri
    Jindal, Neeru
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (22) : 32161 - 32189
  • [39] Walsh Hadamard kernel-based texture feature for multimodal MRI brain tumour segmentation
    Angulakshmi, M.
    Priya, G. G. Lakshmi
    INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 2018, 28 (04) : 254 - 266
  • [40] Brain tumor segmentation of MR images using SVM and fuzzy classifier in machine learning
    Vankdothu R.
    Hameed M.A.
    Measurement: Sensors, 2022, 24