Accuracy Of Brain Tumor Segmentation Research Articles

Brain MRI Tumor Segmentation with 3D Intracranial Structure Deformation Features

Extraction of relevant features is of significant importance for brain tumor segmentation systems. To improve brain tumor segmentation accuracy, the authors present an improved feature extraction component that takes advantage of the correlation between intracranial structure deformation and the compression resulting from brain tumor growth. Using 3D nonrigid registration and deformation modeling techniques, the component measures lateral ventricular (LaV) deformation in volumetric magnetic resonance images. By verifying the location of the extracted LaV deformation feature data and applying the features on brain tumor segmentation with widely used classification algorithms, the authors evaluate the proposed component qualitatively and quantitatively with promising results on 11 datasets comprising real and simulated patient images.

Multiscale CNNs for Brain Tumor Segmentation and Diagnosis.

Early brain tumor detection and diagnosis are critical to clinics. Thus segmentation of focused tumor area needs to be accurate, efficient, and robust. In this paper, we propose an automatic brain tumor segmentation method based on Convolutional Neural Networks (CNNs). Traditional CNNs focus only on local features and ignore global region features, which are both important for pixel classification and recognition. Besides, brain tumor can appear in any place of the brain and be any size and shape in patients. We design a three-stream framework named as multiscale CNNs which could automatically detect the optimum top-three scales of the image sizes and combine information from different scales of the regions around that pixel. Datasets provided by Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized by MICCAI 2013 are utilized for both training and testing. The designed multiscale CNNs framework also combines multimodal features from T1, T1-enhanced, T2, and FLAIR MRI images. By comparison with traditional CNNs and the best two methods in BRATS 2012 and 2013, our framework shows advances in brain tumor segmentation accuracy and robustness.

SU-D-BRA-03: What Image Features Are Useful for Tumor Segmentation in Multi-Modal Images?

Purpose: We hypothesize that derived image features will improve accuracy of segmenting gross tumor volume (GTV) using (semi-)automatic methods when compared with raw intensities. Features from multi-modal images, however, require more CPU time and memory, for extraction, training and classification. In this study, we examine what image features are useful for segmenting GTV in multi-modal images. Methods: Eight cases of high grade brain tumor from MICCAI 2013 for brain tumor segmentation competition were examined. In each case, images of co-registered four MRI modalities: Flair, T1, T1 contrast and T2, as well as the ground truth are provided in the data set. Three cases were used for probing important features and the other five cases were for evaluation of segmentations with the selected features. Besides original image intensity, additional 7 candidate features were extracted: minimum, maximum, gradient, entropy, spot, ripple and edge, resulting in a 32-D (4 x 8) feature vector for each voxel. For selecting important features, a random forest with 100 decision trees was trained using 32-D features from the 3 probing cases. The top ranked features reported by the random forest were selected and used in a Conditional Random Fields (CRF) based semi-automatic method we previously developed to segment the 5 testing cases. Dice coefficent metric to the ground truth are reported and compared to intensity-only segmentation using the same segmentation method. Results: The feature selection random forest ranked intensity, minimum, maximum and entropy the most important features across all 4 MRI modalities. With the selected features (16-D), the CRF segmentation of 5 test cases yielded Dice coefficent 0.847±0.114 (mean±1SD), significantly better (p =0.016) than the Dice coefficient 0.797±0.135 of intensity-only (4-D) CRF segmentation. Conclusion: Multi-modal image features selected by a machine learning method can improve the accuracy of brain tumor segmentation significantly when compared with intensity-only features. Research supported by Varian Medical System

Brain Tumor Segmentation Using Geodesic Region-based Level Set without Re-initialization

Region-based level set segmentation is a paradigm for the automatic segmentation of brain tumor image. Unfortunately, region-based segmentation, which is relied on the intensity difference of different regions, has been of limited used in presence of complex background. In fact, the evoluting curve may leak out the boundary of tumor to reach a steady state by the global region force. In this work, we propose a new hybrid approach for brain tumor segmentation, which is relied on the approach of global intensity difference, local edge properties, curve evolution, and level set method. The regional information drives the contour to converge to the global minimum. By combining the edge information into the region-based framework, the images with intensity inhomogeneity and complex background can be efficiently segmented. To improve the accuracy of brain tumor segmentation, a skull-stripped method for brain images is proposed by utilizing the new morphological process. In addition, a penalizing energy is used for avoiding the time-consuming re-initialization step of the level set method. Finally, experiments are preformatted on some synthetic and real images. By visually assessments, results on patients demonstrate the new method can segment tumors with few iteration times. Moreover, comparisons with the most similar methods also show that the proposed method is effective for the segmentation of tumor in MR image.