Fully automated multi-parametric brain tumour segmentation using superpixel based classification (original) (raw)
Related papers
© 2016 The Author(s)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.
IEEE Access, 2019
Brain tumor segmentation from Magnetic Resonance Imaging (MRI) is of great importance for better tumor diagnosis, growth rate prediction and radiotherapy planning. But this task is extremely challenging due to intrinsically heterogeneous tumor appearance, the presence of severe partial volume effect and ambiguous tumor boundaries. In this work, a unique approach of tumor segmentation is introduced based on superpixel level features extracted from all three planes (x-y, y-z, and z-x) of 3D volumetric MR images. In order to avoid the pixel randomness and to account for precise inhomogeneous boundaries of brain tumor, each of the images belonging to a particular plane is partitioned into irregular patches (superpixels) based on their intensity and spatial similarity. Next, various statistical and textural features are extracted from each superpixel where all three planes are considered separately in order to obtain better labeling on superpixels in tumor edges. A feature selection scheme is proposed based on their performance on histogram based consistency analysis and local descriptor pattern analysis, which offers a significant reduction in feature dimension without sacrificing classification performance. For the purpose of supervised classification, Extremely Randomized Trees is used to classify these superpixels into a tumor or a non-tumor class. Finally, pixel level decision is taken based on corresponding decisions obtained in each plane. Extensive simulations are carried out on publicly available dataset and it is found that the proposed method offers better tumor segmentation performance in comparison to that obtained by some state of the art methods.
Automatic Detection and Segmentation of Brain Tumor Using Random Forest Approach
Lecture Notes in Computer Science, 2016
Stereotactic treatments are today the reference techniques for the irradiation of brain metastases in radiotherapy. The dose per fraction is very high, and delivered in small volumes (diameter <1 cm). As part of these treatments, effective detection and precise segmentation of lesions are imperative. Many methods based on deep-learning approaches have been developed for the automatic segmentation of gliomas, but very little for that of brain metastases. We adapted an existing 3D convolutional neural network (DeepMedic) to detect and segment brain metastases on MRI. At first, we sought to adapt the network parameters to brain metastases. We then explored the single or combined use of different MRI modalities, by evaluating network performance in terms of detection and segmentation. We also studied the interest of increasing the database with virtual patients or of using an additional database in which the active parts of the metastases are separated from the necrotic parts. Our results indicated that a deep network approach is promising for the detection and the segmentation of brain metastases on multimodal MRI.
Computer methods and programs in biomedicine, 2018
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. 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. The method is evaluated on two datasets: 1) Our clinical...
Extremely randomized trees based brain tumor segmentation
2014
Random Decision Forest-based approaches have previously shown promising performance in the domain of brain tumor segmenta-<br> tion. We extend this idea by using an ExtraTree-classi er. Several features are calculated based on normalized T1, T2, T1 with contrast agent and T2 Flair MR-images. With these features an ExtraTree-classi er is trained and used to predict di erent tissue classes on voxel level. The results are compared to other state-of-the-art approaches by participating at the BraTS 2013 challenge.
In this paper a feasibility study of brain MRI dataset classification, using ROIs which have been segmented either manually or through a superpixel based method in conjunction with statistical pattern recognition methods is presented. In our study, 471 extracted ROIs from 21 Brain MRI datasets are used, in order to establish which features distinguish better between three grading classes. Thirty-eight statistical measurements were collected from the ROIs. We found by using the Leave-One-Out method that the combination of the features from the 1 st and 2 nd order statistics, achieved high classification accuracy in pair-wise grading comparisons.
Brain Tumor Segmentation Based on Random Forest
2016
LÁSZLÓ LEFKOVITS, SZIDÓNIA LEFKOVITS and MIRCEA-FLORIN VAIDA Department of Electrical Engineering, Faculty of Technical and Human Sciences, Sapientia University, Tg. Mureş, Romania Department of Informatics, Faculty of Science and Letters “Petru Maior” University, Tg. Mureş, Romania Department of Communications, Technical University of Cluj-Napoca, Romania Corresponding author: lefkolaci@ms.sapientia.ro
Brain Tumour Grading in Different MRI Protocols using SVM on Statistical
In this paper a feasibility study of brain MRI dataset classification, using ROIs which have been segmented either manually or through a superpixel based method in conjunction with statistical pattern recognition methods is presented. In our study, 471 extracted ROIs from 21 Brain MRI datasets are used, in order to establish which features distinguish better between three grading classes. Thirty-eight statistical measurements were collected from the ROIs. We found by using the Leave-One-Out method that the combination of the features from the 1 st and 2 nd order statistics, achieved high classification accuracy in pair-wise grading comparisons.
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
In this paper, we propose a novel learning based method for automated segmentation of brain tumor in multimodal MRI images. The machine learned features from fully convolutional neural network (FCN) and hand-designed texton features are used to classify the MRI image voxels. The score map with pixelwise predictions is used as a feature map which is learned from multimodal MRI training dataset using the FCN. The learned features are then applied to random forests to classify each MRI image voxel into normal brain tissues and different parts of tumor. The method was evaluated on BRATS 2013 challenge dataset. The results show that the application of the random forest classifier to multimodal MRI images using machine-learned features based on FCN and hand-designed features based on textons provides promising segmentations. The Dice overlap measure for automatic brain tumor segmentation against ground truth is 0.88, 080 and 0.73 for complete tumor, core and enhancing tumor, respectively.
Brain tumour grading in different MRI protocols using SVM on statistical features
In this paper a feasibility study of brain MRI data set classification, using ROIs which have been segmented either manually or throug h a superpixel based method in conjunction with statistical pattern recognition me thods is presented. In our study, 471 extracted ROIs from 21 Brain MRI datasets are u sed, in order to establish which features distinguish better between three grading c lasses. Thirty-eight statistical measurements were collected from the ROIs. We found by using the Leave-One-Out method that the combination of the features from th e 1 st and 2 nd order statistics, achieved high classification accuracy in pair-wise grading comparisons.