1) La descarga del recurso depende de la página de origen
2) Para poder descargar el recurso, es necesario ser usuario registrado en Universia


Opción 1: Descargar recurso

Detalles del recurso

Descripción

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 highgrade 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.

Pertenece a

Faculty of Technology ePrints Service  

Autor(es)

Soltaninejad, Mohammadreza -  Yang, Guang -  Lambrou, Tryphon -  Allinson, Nigel -  Jones, Timothy -  Barrick, Thomas -  Howe, Franklyn -  Ye, Xujiong - 

Id.: 69522335

Idioma: inglés  - 

Versión: 1.0

Estado: Final

Tipo:  application/pdf - 

Palabras claveG400 Computer Science - 

Tipo de recurso: Article  -  PeerReviewed  - 

Tipo de Interactividad: Expositivo

Nivel de Interactividad: muy bajo

Audiencia: Estudiante  -  Profesor  -  Autor  - 

Estructura: Atomic

Coste: no

Copyright: sí

: cc_by4

Formatos:  application/pdf - 

Requerimientos técnicos:  Browser: Any - 

Relación: [References] http://eprints.lincoln.ac.uk/25561/
[References] http://link.springer.com/article/10.1007/s11548-016-1483-3
[References] 10.1007/s11548-016-1483-3

Fecha de contribución: 07-ene-2017

Contacto:

Localización:
* Soltaninejad, Mohammadreza and Yang, Guang and Lambrou, Tryphon and Allinson, Nigel and Jones, Timothy and Barrick, Thomas and Howe, Franklyn and Ye, Xujiong (2017) Automated brain tumour detection and segmentation using superpixel-based extremely randomized trees in FLAIR MRI. International Journal of Computer Assisted Radiology and Surgery . ISSN 1861-6410

Otros recursos del mismo autor(es)

  1. Incremental Gaussian Discriminant Analysis based on Graybill and Deal weighted combination of estimators for brain tumour diagnosis In the last decade, machine learning (ML) techniques have been used for developing classifiers for a...
  2. Automatic image quality assessment and measurement of fetal head in two-dimensional ultrasound image Owing to the inconsistent image quality existing in routine obstetric ultrasound (US) scans that lea...
  3. Geant4-based simulations of charge collection in CMOS Active Pixel Sensors Geant4 is an object-oriented toolkit for the simulation of the interaction of particles and radiatio...
  4. Multi-atlas propagation based left atrium segmentation coupled with super-voxel based pulmonary veins delineation in late gadolinium-enhanced cardiac MRI Late Gadolinium-Enhanced Cardiac MRI (LGE CMRI) is a non-invasive technique, which has shown promise...
  5. Microwave impedance microscopy of nanostructured carbon Microwave impedance microscopy (MIM) is a scanning probe technique that measures local changes in ti...

Otros recursos de la mismacolección

  1. Almost Engel compact groups We say that a group $G$ is almost Engel if for every $g\in G$ there is a finite set ${\mathscr E}(g...
  2. How do flexibility i-deals relate to work performance? Exploring the roles of family performance and organizational context Drawing on the work–home resources (W-HR) model and conservation of resources (COR) theory, in this ...
  3. LDPC coded OFDM and its application to DVB-T2, DVB-S2 and IEEE 80216e Since the invention of Information Theory by Shannon in 1948, coding theorists have been trying to c...
  4. Optimal quantization and power allocation for energy-based distributed sensor detection We consider the decentralized detection of an unknown deterministic signal in a spatially uncorrelat...
  5. Classification of tongue - glossitis abnormalities An approach to classify tongue abnormality related to Diabetes Mellitus (DM) following Western Medic...

Aviso de cookies: Usamos cookies propias y de terceros para mejorar nuestros servicios, para análisis estadístico y para mostrarle publicidad. Si continua navegando consideramos que acepta su uso en los términos establecidos en la Política de cookies.