Accurate Brain Tumor Segmentation Research Articles

Brain Tumor Segmentation from MRI Images using Hybrid Convolutional Neural Networks

Brain tumor segmentation is a process of identifying the cancerous brain tissues and labeling them automatically based on the tumor types. Manual segmentation of tumor from brain MRI is time-consuming and error-prone. There is a need for fast and accurate brain tumor segmentation technique. Convolutional Neural Networks (CNNs) have recently shown outstanding performance in computer vision for image segmentation and classification tasks. U-Net, SegNet and ResNet18 are the most popular CNN for image segmentation. The U-Net architecture uses skip connection that captures the fine and soars information but requires higher computational time for training. SegNet is computationally efficient. The ResNet18 also uses skip connection and has a layer which adds inputs from multiple neural network layers to get more accurate results. The proposed U-SegNet and Seg-UNet is a hybridization of the novel architecture, SegNet, and U-Net. The main difference between them is the depth, Seg-UNet uses five convolution blocks compared to U-SegNet, which has three convolution blocks and both the models has a skip connection inspired from U-Net after the first convolutional layer by using a depth concatenation layer. And proposed Res-SegNet is also a hybridization of SegNet and ResNet18. It is inspired by ResNet18 and uses an element-wise addition layer as a skip connection. The SegNet3, SegNet5, U-Net, Seg-UNet, U-SegNet, and Res-SegNet are implemented to compare the performance based on their accuracy. For experimentation, BraTS dataset are used for training and testing the models. From the simulation results, it is observed that the hybrid architecture has higher accuracy.

Automatic Detection Brain Segmentation to Detect Brain Tumor Using MRI

Brain tumors are a type of disease in the form of lumps of meat that grow in the brain. In differentiating brain tumor tissue from normal tissue become a difficulty caused by the same colors are an obstacle in seeing brain tumors using MRI images. Accuracy is needed in analyzing brain tumors. However, currently, radiographers (radiologists) still analyze the results of manual MRI images of brain tumors. Therefore we need a method that is able to segment MRI images precisely and automatically, with the aim of obtaining faster and more accurate image segmentation of brain tumors so that we can know the percentage of brain tumors found in the brain. To overcome difficulties when segmenting brain tumors in separating brain tumor tissue from other tissues such as normal brain tissue, cerebrospinal fluid, fat, and edema, a learning-based system method that will carry out the training process uses Haar training to narrow the MRI image so that it is more focused on the part of the head object. Then median filtering is performed to maintain the edge of the image on the MRI image. Then the segmentation process using the thresholding method is run, then repeated to take the largest area. Segmentation of brain is carried out by marking the brain area and the area outside the brain using the DAS method and then cleaning the skull using the cropping method. In this research, 12 images of MRI brain tumors were used. The results of segmentation compared to area of the brain tumor and area of the brain tissue. The system obtains a calculation of the tumor area having an average error of 10,5%.

A novel CT image segmentation algorithm using PCNN and Sobolev gradient methods in GPU frameworks

Accurate brain tumor segmentation plays a significant role in the area of radiotherapy diagnosis and in the proper treatment for brain tumor detection. Typically, the brain tumor has poor boundary and low contrast between normal and lesion soft tissues that makes segmentation of brain tumor in the CT images a challenging task. This paper presents a novel approach to brain image segmentation using pulse-coupled neural network (PCNN) and zero level set (ZL) with Sobolev gradient (SG) method. In this article, PCNN is designed to use as an edge mapper to provide a regional description for the ZL to segregate the CT images based on contour maps. The PCNN is used to estimate the exact threshold to obtain the prominent edges of the images. Resulting edges are utilized in the ZL to extract image contour from the source image. Due to the over-sensitivity of the ZL method on the initial contour, a level set with the SG has been equipped to overcome the limitation of the ZL method. The experimental results show satisfactory segmentation outcomes with excellent accuracy and acceleration in comparison with the state-of-the-art methods.

Segmenting brain tumors from FLAIR MRI using fully convolutional neural networks

Background and ObjectiveMagnetic resonance imaging (MRI) is an indispensable tool in diagnosing brain-tumor patients. Automated tumor segmentation is being widely researched to accelerate the MRI analysis and allow clinicians to precisely plan treatment—accurate delineation of brain tumors is a critical step in assessing their volume, shape, boundaries, and other characteristics. However, it is still a very challenging task due to inherent MR data characteristics and high variability, e.g., in tumor sizes or shapes. We present a new deep learning approach for accurate brain tumor segmentation which can be trained from small and heterogeneous datasets annotated by a human reader (providing high-quality ground-truth segmentation is very costly in practice). MethodsIn this paper, we present a new deep learning technique for segmenting brain tumors from fluid attenuation inversion recovery MRI. Our technique exploits fully convolutional neural networks, and it is equipped with a battery of augmentation techniques that make the algorithm robust against low data quality, and heterogeneity of small training sets. We train our models using only positive (tumorous) examples, due to the limited amount of available data. ResultsOur algorithm was tested on a set of stage II-IV brain-tumor patients (image data collected using MAGNETOM Prisma 3T, Siemens). Rigorous experiments, backed up with statistical tests, revealed that our approach outperforms the state-of-the-art approach (utilizing hand-crafted features) in terms of segmentation accuracy, offers very fast training and instant segmentation (analysis of an image takes less than a second). Building our deep model is 1.3 times faster compared with extracting features for extremely randomized trees, and this training time can be controlled. Finally, we showed that too aggressive data augmentation may lead to deteriorated performance of the model, especially in the fixed-budget training (with maximum numbers of training epochs). ConclusionsOur method yields the better performance when compared with the state of the art method which utilizes hand-crafted features. In addition, our deep network can be effectively applied to difficult (small, imbalanced, and heterogeneous) datasets, offers controllable training time, and infers in real-time.

Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging.

Aim: Brain tumors are among the most fatal cancers worldwide. Diagnosing and manually segmenting tumors are time-consuming clinical tasks, and success strongly depends on the doctor's experience. Automatic quantitative analysis and accurate segmentation of brain tumors are greatly needed for cancer diagnosis.Methods:This paper presents an advanced three-dimensional multimodal segmentation algorithm called nested dilation networks (NDNs). It is inspired by the U-Net architecture, a convolutional neural network (CNN) developed for biomedical image segmentation and is modified to achieve better performance for brain tumor segmentation. Thus, we propose residual blocks nested with dilations (RnD) in the encoding part to enrich the low-level features and use squeeze-and-excitation (SE) blocks in both the encoding and decoding parts to boost significant features. To prove the reliability of the network structure, we compare our results with those of the standard U-Net and its transmutation networks. Different loss functions are considered to cope with class imbalance problems to maximize the brain tumor segmentation results. A cascade training strategy is employed to run NDNs for coarse-to-fine tumor segmentation. This strategy decomposes the multiclass segmentation problem into three binary segmentation problems and trains each task sequentially. Various augmentation techniques are utilized to increase the diversity of the data to avoid overfitting.Results: This approach achieves Dice similarity scores of 0.6652, 0.5880, and 0.6682 for edema, non-enhancing tumors, and enhancing tumors, respectively, in which the Dice loss is used for single-pass training. After cascade training, the Dice similarity scores rise to 0.7043, 0.5889, and 0.7206, respectively.Conclusion: Experiments show that the proposed deep learning algorithm outperforms other U-Net transmutation networks for brain tumor segmentation. Moreover, applying cascade training to NDNs facilitates better performance than other methods. The findings of this study provide considerable insight into the automatic and accurate segmentation of brain tumors.

An Enhancement of Deep Learning Algorithm for Brain Tumor Segmentation Using Kernel Based CNN with M-SVM.

The brain tumor can be created by uncontrollable increase of abnormal cells in tissue of brain and it has two kinds of tumors: one is benign and another one is malignant tumor. The benign brain tumor does not affect the adjacent normal and healthy tissue but the malignant tumor can affect the neighboring tissues of brain that can lead to the death of person. An early detection of brain tumor can be required to protect the survival of patients. Usually, the brain tumor is detected using MRI scanning method. However, the radiologists are not providing the effective tumor segmentation in MRI image due to the irregular shape of tumors and position of tumor in the brain. Accurate brain tumor segmentation is needed to locate the tumor and it is used to give the correct treatment for a patient and it provides the key to the doctor who must execute the surgery for patient. In this paper, a novel deep learning algorithm (kernel based CNN) with M-SVM is presented to segment the tumor automatically and efficiently. This presented work contains several steps that are preprocessing, feature extraction, image classification and tumor segmentation of brain. The MRI image is smoothed and enhanced by Laplacian of Gaussian filtering method (LoG) with Contrast Limited Adaptive Histrogram Equalization (CLAHE) and feature can be extracted from it based on tumor shape position, shape and surface features in brain. Consequently, the image classification is done using M-SVM depending on the selected features. From MRI image, the tumor is segmented with help of kernel based CNN method.. Experimental results of proposed method can show that this presented technique can executes brain tumor segmentation accurately reaching almost 84% in evaluation with existing algorithms.

Brain Tumor Segmentation Using Multi-Cascaded Convolutional Neural Networks and Conditional Random Field

Accurate segmentation of brain tumor is an indispensable component for cancer diagnosis and treatment. In this paper, we propose a novel brain tumor segmentation method based on multi-cascaded convolutional neural network (MCCNN) and fully connected conditional random fields (CRFs). The segmentation process mainly includes the following two steps. First, we design a multi-cascaded network architecture by combining the intermediate results of several connected components to take the local dependencies of labels into account and make use of multi-scale features for the coarse segmentation. Second, we apply CRFs to consider the spatial contextual information and eliminate some spurious outputs for the fine segmentation. In addition, we use image patches obtained from axial, coronal, and sagittal views to respectively train three segmentation models, and then combine them to obtain the final segmentation result. The validity of the proposed method is evaluated on three publicly available databases. The experimental results show that our method achieves competitive performance compared with the state-of-the-art approaches.

Dual-force convolutional neural networks for accurate brain tumor segmentation

Brain tumor segmentation from Magnetic Resonance Imaging scans is vital for both the diagnosis and treatment of brain cancers. It is widely accepted that accurate segmentation depends on multi-level information. However, exiting deep architectures for brain tumor segmentation fail to explicitly encourage the models to learn high-quality hierarchical features. In this paper, we propose a series of approaches to enhance the quality of the learnt hierarchical features. Our contributions incorporate four aspects. First, we extend the popular DeepMedic model to Multi-Level DeepMedic to make use of multi-level information for more accurate segmentation. Second, we propose a novel dual-force training scheme to promote the quality of multi-level features learnt from deep models. It is a general training scheme and can be applied to many exiting architectures, e.g., DeepMedic and U-Net. Third, we design a label distribution-based loss function as an auxiliary classifier to encourage the high-level layers of deep models to learn more abstract information. Finally, we propose a novel Multi-Layer Perceptron-based post-processing approach to refine the prediction results of deep models. Extensive experiments are conducted on two most recent brain tumor segmentation datasets, i.e., BRATS 2017 and BRATS 2015 datasets. Results on the two databases indicate that the proposed approaches consistently promote the segmentation performance of the two popular deep models.

Automated 3D segmentation of brain tumor using visual saliency

There is a growing availability of medical imaging data from large number of patients, involving visual information from images in different modalities along with an associated complexity of the features of interest. It has therefore become essential to develop automated delineations to assist doctors and/or radiologists to analyze and speedup medical image understanding, preferably avoiding any user intervention. We present here a novel approach for the reliable, automated, and accurate 3D segmentation of brain tumors from multi-sequence magnetic resonance images. The tumor volume, detected using visual saliency, is evaluated in three-dimensions for small as well as large ROIs and/or VOIs. The proposed segmentation method is applied on the publicly available standard BRATS data set, and is found to achieve very high accuracy with good reliability (or repeatability) and robustness of results. Its robustness, is also investigated by measuring the impact of tumor size on segmentation accuracy, on the basis of the weak linear correlation. The results demonstrate that the segmentation generated by the proposed algorithm can be used for accurate, stable contouring, for both high- and low-grade tumors, as compared to several related state-of-the-art methods involving semi-automatic and supervised learning.

Brain tumor segmentation from multimodal magnetic resonance images via sparse representation.

Accurately segmenting and quantifying brain gliomas from magnetic resonance (MR) images remains a challenging task because of the large spatial and structural variability among brain tumors. To develop a fully automatic and accurate brain tumor segmentation algorithm, we present a probabilistic model of multimodal MR brain tumor segmentation. This model combines sparse representation and the Markov random field (MRF) to solve the spatial and structural variability problem. We formulate the tumor segmentation problem as a multi-classification task by labeling each voxel as the maximum posterior probability. We estimate the maximum a posteriori (MAP) probability by introducing the sparse representation into a likelihood probability and a MRF into the prior probability. Considering the MAP as an NP-hard problem, we convert the maximum posterior probability estimation into a minimum energy optimization problem and employ graph cuts to find the solution to the MAP estimation. Our method is evaluated using the Brain Tumor Segmentation Challenge 2013 database (BRATS 2013) and obtained Dice coefficient metric values of 0.85, 0.75, and 0.69 on the high-grade Challenge data set, 0.73, 0.56, and 0.54 on the high-grade Challenge LeaderBoard data set, and 0.84, 0.54, and 0.57 on the low-grade Challenge data set for the complete, core, and enhancing regions. The experimental results show that the proposed algorithm is valid and ranks 2nd compared with the state-of-the-art tumor segmentation algorithms in the MICCAI BRATS 2013 challenge.

Fast and accurate semiautomatic haptic segmentation of brain tumor in 3D MRI images

In this study, a novel virtual reality-based interactive method combined with the application of a graphical processing unit (GPU) is proposed for the semiautomatic segmentation of 3D magnetic resonance imaging (MRI) of the brain. The key point of our approach is to use haptic force feedback guidance for the selection of seed points in a bounded volume with similar intensity and gradient. For the automatic determination of a bounded volume of segmentation in real time, parallel computation on the GPU is used. Automatic segmentation is applied in this adjustable bounded spherical volume with a variable diameter, which is controlled according to the edge map acquired from the gradient map. The haptic force feedback is used in order to guide the user to remain in a volume, where the intensity and gradient change are under a defined threshold range. After each seed point selection, the segmentation algorithm works inside the bounded volume of the ball with an adjusted diameter. The proposed segmentation method based on force and visual feedback with the advantage of adjustable bounded volume is not only accurate and effective in narrow spaces near the boundaries of different layers, but also fast in large homogeneous spaces since the radius of the ball increases in such regions. Parallel programming on the GPU is used for computing gradient change in selected directions, which is needed for the self-adjustment of the sphere diameter. Gradient values are used for calculating the haptic force on the CPU in real time. In this study, two haptic devices are used, one for getting haptic force feedback and the other for camera guidance during 3D visualization. A comparison between manual segmentation of MRI by an expert surgeon and the proposed segmentation algorithm is done. The proposed segmentation procedure is completed 4 times faster than the manual segmentation with similar accuracy.

Brain tumor classification and segmentation using sparse coding and dictionary learning.

This paper presents a novel fully automatic framework for multi-class brain tumor classification and segmentation using a sparse coding and dictionary learning method. The proposed framework consists of two steps: classification and segmentation. The classification of the brain tumors is based on brain topology and texture. The segmentation is based on voxel values of the image data. Using K-SVD, two types of dictionaries are learned from the training data and their associated ground truth segmentation: feature dictionary and voxel-wise coupled dictionaries. The feature dictionary consists of global image features (topological and texture features). The coupled dictionaries consist of coupled information: gray scale voxel values of the training image data and their associated label voxel values of the ground truth segmentation of the training data. For quantitative evaluation, the proposed framework is evaluated using different metrics. The segmentation results of the brain tumor segmentation (MICCAI-BraTS-2013) database are evaluated using five different metric scores, which are computed using the online evaluation tool provided by the BraTS-2013 challenge organizers. Experimental results demonstrate that the proposed approach achieves an accurate brain tumor classification and segmentation and outperforms the state-of-the-art methods.

Automated Tumor Volumetry Using Computer-Aided Image Segmentation

Accurate segmentation of brain tumors, and quantification of tumor volume, is important for diagnosis, monitoring, and planning therapeutic intervention. Manual segmentation is not widely used because of time constraints. Previous efforts have mainly produced methods that are tailored to a particular type of tumor or acquisition protocol and have mostly failed to produce a method that functions on different tumor types and is robust to changes in scanning parameters, resolution, and image quality, thereby limiting their clinical value. Herein, we present a semiautomatic method for tumor segmentation that is fast, accurate, and robust to a wide variation in image quality and resolution. A semiautomatic segmentation method based on the geodesic distance transform was developed and validated by using it to segment 54 brain tumors. Glioblastomas, meningiomas, and brain metastases were segmented. Qualitative validation was based on physician ratings provided by three clinical experts. Quantitative validation was based on comparing semiautomatic and manual segmentations. Tumor segmentations obtained using manual and automatic methods were compared quantitatively using the Dice measure of overlap. Subjective evaluation was performed by having human experts rate the computerized segmentations on a 0-5 rating scale where 5 indicated perfect segmentation. The proposed method addresses a significant, unmet need in the field of neuro-oncology. Specifically, this method enables clinicians to obtain accurate and reproducible tumor volumes without the need for manual segmentation.

Review on MRI Brain Tumor Segmentation

Accurate segmentation of brain tumor from MRI is crucial in computer aided diagnosis as well as in other medical imaging applications. Brain tumor segmentation is a challenging task due to the diverse appearance of tumor tissues. A variety of brain tumor segmentation techniques have been explored in the literature. Here, a brief review of different brain tumor segmentation techniques has been discussed with their merits and demerits. We conclude with a discussion on the trend of future research in brain tumor segmentation.