Mohammadreza Soltaninejad1, Guang Yang2, Tryphon Lambrou3, Nigel Allinson4, Timothy L Jones5, Thomas R Barrick6, Franklyn A Howe7, Xujiong Ye8. 1. School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK. Electronic address: msoltaninejad@lincoln.ac.uk. 2. National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK; Neurosciences Research Centre, Molecular and Clinical Sciences Institute, St. George's, University of London, London SW17 0RE, UK. Electronic address: g.yang@imperial.ac.uk. 3. School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK. Electronic address: tlambrou@lincoln.ac.uk. 4. School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK. Electronic address: nallinson@lincoln.ac.uk. 5. Academic Neurosurgery Unit, St. George's, University of London, London SW17 0RE, UK. Electronic address: timothy.jones@stgeorges.nhs.uk. 6. Neurosciences Research Centre, Molecular and Clinical Sciences Institute, St. George's, University of London, London SW17 0RE, UK. Electronic address: tbarrick@sgul.ac.uk. 7. Neurosciences Research Centre, Molecular and Clinical Sciences Institute, St. George's, University of London, London SW17 0RE, UK. Electronic address: howefa@sgul.ac.uk. 8. School of Computer Science, University of Lincoln, Lincoln LN6 7TS, UK. Electronic address: xye@lincoln.ac.uk.
Abstract
BACKGROUND: Accurate segmentation of brain tumour in magnetic resonance images (MRI) is a difficult task due to various tumour types. Using information and features from multimodal MRI including structural MRI and isotropic (p) and anisotropic (q) components derived from the diffusion tensor imaging (DTI) may result in a more accurate analysis of brain images. METHODS: We propose a novel 3D supervoxel based learning method for segmentation of tumour in multimodal MRI brain images (conventional MRI and DTI). Supervoxels are generated using the information across the multimodal MRI dataset. For each supervoxel, a variety of features including histograms of texton descriptor, calculated using a set of Gabor filters with different sizes and orientations, and first order intensity statistical features are extracted. Those features are fed into a random forests (RF) classifier to classify each supervoxel into tumour core, oedema or healthy brain tissue. RESULTS: The method is evaluated on two datasets: 1) Our clinical dataset: 11 multimodal images of patients and 2) BRATS 2013 clinical dataset: 30 multimodal images. For our clinical dataset, the average detection sensitivity of tumour (including tumour core and oedema) using multimodal MRI is 86% with balanced error rate (BER) 7%; while the Dice score for automatic tumour segmentation against ground truth is 0.84. The corresponding results of the BRATS 2013 dataset are 96%, 2% and 0.89, respectively. CONCLUSION: The method demonstrates promising results in the segmentation of brain tumour. Adding features from multimodal MRI images can largely increase the segmentation accuracy. The method provides a close match to expert delineation across all tumour grades, leading to a faster and more reproducible method of brain tumour detection and delineation to aid patient management.
BACKGROUND: Accurate segmentation of brain tumour in magnetic resonance images (MRI) is a difficult task due to various tumour types. Using information and features from multimodal MRI including structural MRI and isotropic (p) and anisotropic (q) components derived from the diffusion tensor imaging (DTI) may result in a more accurate analysis of brain images. METHODS: We propose a novel 3D supervoxel based learning method for segmentation of tumour in multimodal MRI brain images (conventional MRI and DTI). Supervoxels are generated using the information across the multimodal MRI dataset. For each supervoxel, a variety of features including histograms of texton descriptor, calculated using a set of Gabor filters with different sizes and orientations, and first order intensity statistical features are extracted. Those features are fed into a random forests (RF) classifier to classify each supervoxel into tumour core, oedema or healthy brain tissue. RESULTS: The method is evaluated on two datasets: 1) Our clinical dataset: 11 multimodal images of patients and 2) BRATS 2013 clinical dataset: 30 multimodal images. For our clinical dataset, the average detection sensitivity of tumour (including tumour core and oedema) using multimodal MRI is 86% with balanced error rate (BER) 7%; while the Dice score for automatic tumour segmentation against ground truth is 0.84. The corresponding results of the BRATS 2013 dataset are 96%, 2% and 0.89, respectively. CONCLUSION: The method demonstrates promising results in the segmentation of brain tumour. Adding features from multimodal MRI images can largely increase the segmentation accuracy. The method provides a close match to expert delineation across all tumour grades, leading to a faster and more reproducible method of brain tumour detection and delineation to aid patient management.