Automated brain tumour detection and segmentation using superpixel-based extremely randomized trees in FLAIR MRI

• Published in: International journal for computer assisted radiology and surgery 2017-02, Vol.12 (2), p.183-203
• Main Authors: Soltaninejad, Mohammadreza, Yang, Guang, Lambrou, Tryphon, Allinson, Nigel, Jones, Timothy L., Barrick, Thomas R., Howe, Franklyn A., Ye, Xujiong
• Format: Article
• Language: English
• Subjects: Adult; Aged; Brain - diagnostic imaging; Brain Neoplasms - diagnostic imaging; Computer Imaging; Computer Science; Female; Glioma - diagnostic imaging; Health Informatics; Humans; Image Processing, Computer-Assisted - methods; Image segmentation; Imaging; Magnetic Resonance Imaging - methods; Male; Medicine; Medicine & Public Health; Middle Aged; Original; Original Article; Pattern Recognition and Graphics; Radiology; Reproducibility of Results; Support Vector Machine; Surgery; Vision; Young Adult
• ISSN: 1861-6410; 1861-6429
• DOI: 10.1007/s11548-016-1483-3

Purpose We propose a fully automated method for detection and segmentation of the abnormal tissue associated with brain tumour (tumour core and oedema) from Fluid- Attenuated Inversion Recovery (FLAIR) Magnetic Resonance Imaging (MRI). Methods The method is based on superpixel technique and classification of each superpixel. A number of novel image features including intensity-based, Gabor textons, fractal analysis and curvatures are calculated from each superpixel within the entire brain area in FLAIR MRI to ensure a robust classification. Extremely randomized trees (ERT) classifier is compared with support vector machine (SVM) to classify each superpixel into tumour and non-tumour. Results The proposed method is evaluated on two datasets: (1) Our own clinical dataset: 19 MRI FLAIR images of patients with gliomas of grade II to IV, and (2) BRATS 2012 dataset: 30 FLAIR images with 10 low-grade and 20 high-grade gliomas. The experimental results demonstrate the high detection and segmentation performance of the proposed method using ERT classifier. For our own cohort, the average detection sensitivity, balanced error rate and the Dice overlap measure for the segmented tumour against the ground truth are 89.48 %, 6 % and 0.91, respectively, while, for the BRATS dataset, the corresponding evaluation results are 88.09 %, 6 % and 0.88, respectively. Conclusions This provides a close match to expert delineation across all grades of glioma, leading to a faster and more reproducible method of brain tumour detection and delineation to aid patient management.