Magnetic Resonance Imaging Brain Tumor Research Articles

Support vector machine based discrete wavelet transform for magnetic resonance imaging brain tumor classification

Here, a brain tumor classification method using the support vector machine (SVM) algorithm by utilizing discrete wavelet transform (DWT) transformation and feature extraction of gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP) has been implemented using the magnetic resonance imaging (MRI) image belong to the low-grade glioma (LGG) or high-grade glioma (HGG) group. SVM algorithm used as a classification method has been widely used in research that raises the topic of classification. Through the formation of a hyperplane between 2 data classes, the SVM algorithm can be said to be a reliable method but does not require complicated computations. The DWT transformation is intended to provide clearer feature details from the MRI image, so that when the feature extraction algorithm is applied, it is expected that the extracted features will differ between benign tumor MRI images and malignant tumor MRI images. In 1 level DWT using high-low (HL) sub-band yield the highest specificity, sensitivity, and accuracy than using 3 levels using HL or low-high (LH) sub-band in LGG MRI image.Compared with another research, our proposed method is slightly better in terms of accuracy to classify the brain tumor image with achieved the accuracy of 98.6486%.

K-NET+SEGAN-BASED SEGMENTATION WITH GANNET AQUILA OPTIMIZATION ALGORITHM-ENABLED DEEP MAXOUT NETWORK FOR BRAIN TUMOR CLASSIFICATION USING MRI

Segmentation and classification of brain tumor are time-consuming and challenging chore in clinical image processing. Magnetic Resonance Imaging (MRI) offers more information related to human soft tissues that assists in diagnosing brain tumor. Precise segmentation of the MRI images is vital to diagnose brain tumor by means of computer-aided medical tools. Afterwards suitable segmentation of MRI brain tumor images, tumor classification is performed that is a hard chore owing to complications. Therefore, Gannet Aquila Optimization Algorithm_deep maxout network (GAOA_DMN) and GAOA_K-Net+speech enhancement generative adversarial network (GAOA_K-Net+Segan) is presented for classification and segmentation of brain tumor utilizing MRI images. Here, pre-processing phase performs noise removal from input image utilizing the Laplacian filter and also the region of interest (ROI) extraction is also carried out. Then, segmentation of brain tumor is conducted by K-Net+Segan, which is combined by Motyka similarity. However, K-Net+Segan for segmentation is trained by GAOA that is an amalgamation of Gannet Optimization Algorithm (GOA) and Aquila Optimizer (AO). From segmented image, features are extracted for performing classification phase. At last, brain tumor classification is conducted by DMN, which is tuned by GAOA and thus, output is obtained. Furthermore, GAOA_K-Net+Segan obtained better outcomes in terms of segmentation accuracy whereas devised GAOA_DMN achieved maximum accuracy, true negative rate (TNR) and true positive rate (TPR) of 92.7%, 94.5% and 91.5%.

Magnetic Resonance Imaging (MRI) Brain Tumor Image Classification Based on Five Machine Learning Algorithms

With the emergence of new technologies, vast amounts of data have become pervasive in various aspects of social life, including public transportation, community services, and scientific research. As the population ages, healthcare has become increasingly crucial, and reducing the public burdens, especially in hospitals, has become an urgent issue. For instance, manually managing vast electronic medical files, such as MRI images, based on their types is practically impossible. However, accurate classification is fundamental and critical for subsequent tasks, such as diagnosis. In this article, we utilized machine learning techniques to classify MRI brain tumor images. We employed a range of machine learning models, including k-Nearest Neighbors (k-NN), decision tree, Support Vector Machine (SVM), logistic regression, and Stochastic Gradient Descent (SGD). The performance of each model type was measured by True Skill Statistics (TSS), based on the results obtained from the confusion matrix. The results showed that k-NN works most efficiently among all those classification models. However, due to the constraints of limited running time and computational power, further investigation of the models and parameter optimization are necessary for future work.

An improved grade based MRI brain tumor classification using hybrid DCNN-DH framework

Magnetic Resonance Imaging (MRI) is a technology to exhibit the complete image of the affected brain location. Recently, MRI scanning has been the most actively developing field. Still, it is very difficult for the radiologist to categorize the tumour since the input image contains some data related to disease or non-disease. Further, analyzing the tumor grade from the input data requires much time and workforce. Therefore, an automatic and effective tumor grade classification model is required to reduce that. In this paper, the grade-based brain tumor classification is done based on a Hybrid Deep convolutional neural network with Deer Hunting (Hybrid DCNN-DH) optimization to achieve such a goal. Initially, the input MRI brain image is pre-processed utilizing normalized bilateral filtering. Afterwards, density peak clustering with Social Ski-Driver optimization is utilized to effectively segment cerebrospinal fluid, abnormal region, gray matter and white matter. Subsequently, features including a pyramid histogram of the oriented gradient (PHOG), gray level co-occurrence matrix (GLCM), intensity-based features and modified local binary pattern (MLBP) are extracted. After that, Adaptive Sun Flower Optimization (ASFO) is utilized for effective feature selection to reduce the dimensionality from the extricated features. Finally, grade-based classification is performed through the Hybrid Deep convolutional neural network with Deer Hunting (Hybrid DCNN-DH). It classifies the images into normal, low grade and high-grade images. The experimental outcomes of the presented technique outperform in terms of sensitivity, false positive rate, accuracy, f-measure, precision, specificity, false negative rate, balanced error rate, and negative predictive value.

Tumor-Net: convolutional neural network modeling for classifying brain tumors from MRI images

Abnormal brain tissue or cell growth is known as a brain tumor. One of the body's most intricate organs is the brain, where billions of cells work together. As a head tumor grows, the brain suffers damage due to its increasingly dense core. Magnetic resonance imaging, or MRI, is a type of medical imaging that enables radiologists to view the inside of body structures without the need for surgery. The image-based medical diagnosis expert system is crucial for a brain tumor patient. In this study, we combined two Magnetic Resonance Imaging (MRI)-based image datasets from Figshare and Kaggle to identify brain tumor MRI using a variety of convolutional neural network designs. To achieve competitive performance, we employ several data preprocessing techniques, such as resizing and enhancing contrast. The image augmentation techniques (E.g., rotated, width shifted, height shifted, shear shifted, and horizontally flipped) are used to increase data size, and five pre-trained models employed, including VGG-16, VGG-19, ResNet-50, Xception, and Inception-V3. The model with the highest accuracy, ResNet-50, performs at 96.76 percent. The model with the highest precision overall is Inception V3, with a precision score of 98.83 percent. ResNet-50 performs at 96.96% for F1-Score. The prominent accuracy of the implemented model, i.e., ResNet-50, compared with several earlier studies to validate the consequence of this introspection. The outcome of this study can be used in the medical diagnosis of brain tumors with an MRI-based expert system.

Advanced imaging system for brain tumor automatic classification from MRI images using HOG and BOF feature extraction approaches

AbstractBrain tumors have recently become a widespread phenomenon that affects almost all age ranges. Magnetic resonance imaging (MRI) is a widely used technique nowadays to diagnose this life‐threatening disease. Therefore, using a computer‐aided diagnosis system is essential for the early identification and classification of brain tumors. This work aims to develop a fully automated classification framework for MRI brain tumor images using machine learning (ML) algorithms. In this article, four ML algorithms such as support vector machines (Cubic SVM), k‐nearest neighbors (fine KNN), decision tree (fine tree), and naive Bayes (Kernel) were implemented with two feature extraction approaches: histogram of oriented gradients (HOG) and a bag of features (BOF) approach. The novelty of this work is based on the original usage of BOF and HOG approaches over different types of ML algorithms for MRI brain tumor image classification. In addition, combining two public datasets that contain three brain tumor types to generalize and improve the proposed work. The results showed that the fine KNN algorithm achieved the greatest success among all algorithms using the HOG method with an accuracy of 98.62% on 6328 MRI images.

AUTOMATIC 2D AND 3D SEGMENTATION OF GLIOBLASTOMA BRAIN TUMOR

The brain tumor is the most common destructive and deadly disease. In general, various imaging modalities such as CT, MRI and PET are used to evaluate the brain tumor. Magnetic resonance imaging (MRI) is a prominent diagnostic method for evaluating these tumors. Gliomas, due to their malignant nature and rapid development, are the most common and aggressive form of brain tumors. In the clinical routine, the method of identifying tumor borders from healthy cells is still a difficult task. Manual segmentation takes time, so we use a deep convolutional neural network to improve efficiency. We present a combined DNN architecture using U-net and MobilenetV2. It exploits both local characteristics and more global contextual characteristics from the 2D MRI FLAIR images. The proposed network has encoder and decoder architecture. The performance metrices such as dice loss, dice coefficient, accuracy and IOU have been calculated. Automated segmentation of 3D MRI is essential for the identification, assessment, and treatment of brain tumors although there is significant interest in machine-learning algorithms for computerized segmentation of brain tumors. The goal of this work is to perform 3D volumetric segmentation using BraTumIA. It is a widely available software application used to separate tumor characteristics on 3D brain MR volumes. BraTumIA has lately been used in a number of clinical trials. In this work, we have segmented 2D slices and 3D volumes of MRI brain tumor images.

Binary swallow swarm optimization with convolutional neural network brain tumor classifier for magnetic resonance imaging images

SummaryThe brain tumor classification is implemented through biopsy, which is not normally executed before classic mind surgery. Machine learning (ML) algorithms assist radiologists in tumor analysis, not including obtrusive evaluations. The conventional ML strategies need separate feature extraction to tumor detect thus it needs more computation time to perform classification. Deep learning (DL) based convolution neural networks (CNNs) have been focused on brain tumor detection. In this paper, the CNN algorithm is improved based on meta‐heuristics, which are used for pre‐trained systems for databases to categorize MRI brain tumor images. Pre‐trained DL, binary swallow swarm optimization (BSSO) is used for improving the weight and predispositions of the CNN algorithm. It is a block‐wise calibrating system which is dependent on transfer learning. The current technique is assessed over a publically accessible magnetic resonance imaging (MRI) brain tumor database containing three categories as glioma, meningioma, and pituitary by the most noteworthy rate among everyone brain tumor in medical training. The proposed strategy is assessed over T1‐weighted contrast‐enhanced MRI (CE‐MRI) benchmark data. To assess the execution, utilize the proposed strategies to the CE‐MRI dataset for tumor detection and in the general execution of the BSSO‐CNN model is estimated using the execution assessment measurements such as precision, sensitivity (recall), specificity, F1‐score, and accuracy. Exploratory outcomes demonstrated with the purpose of the proposed strategy higher when compared to other methods to all metrics.

An improved hybrid quantum-classical convolutional neural network for multi-class brain tumor MRI classification

The efficiency of quantum computing has recently been extended to machine learning, which has made a significant impact on quantum machine learning. The hybrid structure of quantum and classical ones has developed into the most successful application mode currently due to noisy intermediate scale quantum limitations. In this paper, an improved hybrid quantum-classic convolutional neural network (HQC-CNN) with fast training speed, lightweight, and high performance is proposed. Its convolution layer realizes feature mapping through parameterized quantum circuit, while other layers keep classic operation and finally complete the task of four classifications of brain tumors. The experiment in this paper is based on kaggle brain tumor magnetic resonance imaging public dataset. The final experimental results show that HQC-CNN can effectively classify meningioma, glioma, pituitary, and no tumor with a classification accuracy of 97.8%. When compared to numerous well-known landmark models, HQC-CNN has obvious advantages.

MAU-Net: Mixed attention U-Net for MRI brain tumor segmentation.

Computer-aided brain tumor segmentation using magnetic resonance imaging (MRI) is of great significance for the clinical diagnosis and treatment of patients. Recently, U-Net has received widespread attention as a milestone in automatic brain tumor segmentation. Following its merits and motivated by the success of the attention mechanism, this work proposed a novel mixed attention U-Net model, i.e., MAU-Net, which integrated the spatial-channel attention and self-attention into a single U-Net architecture for MRI brain tumor segmentation. Specifically, MAU-Net embeds Shuffle Attention using spatial-channel attention after each convolutional block in the encoder stage to enhance local details of brain tumor images. Meanwhile, considering the superior capability of self-attention in modeling long-distance dependencies, an enhanced Transformer module is introduced at the bottleneck to improve the interactive learning ability of global information of brain tumor images. MAU-Net achieves enhancing tumor, whole tumor and tumor core segmentation Dice values of 77.88/77.47, 90.15/90.00 and 81.09/81.63% on the brain tumor segmentation (BraTS) 2019/2020 validation datasets, and it outperforms the baseline by 1.15 and 0.93% on average, respectively. Besides, MAU-Net also demonstrates good competitiveness compared with representative methods.

SDS-Net: A lightweight 3D convolutional neural network with multi-branch attention for multimodal brain tumor accurate segmentation.

The accurate and fast segmentation method of tumor regions in brain Magnetic Resonance Imaging (MRI) is significant for clinical diagnosis, treatment and monitoring, given the aggressive and high mortality rate of brain tumors. However, due to the limitation of computational complexity, convolutional neural networks (CNNs) face challenges in being efficiently deployed on resource-limited devices, which restricts their popularity in practical medical applications. To address this issue, we propose a lightweight and efficient 3D convolutional neural network SDS-Net for multimodal brain tumor MRI image segmentation. SDS-Net combines depthwise separable convolution and traditional convolution to construct the 3D lightweight backbone blocks, lightweight feature extraction (LFE) and lightweight feature fusion (LFF) modules, which effectively utilizes the rich local features in multimodal images and enhances the segmentation performance of sub-tumor regions. In addition, 3D shuffle attention (SA) and 3D self-ensemble (SE) modules are incorporated into the encoder and decoder of the network. The SA helps to capture high-quality spatial and channel features from the modalities, and the SE acquires more refined edge features by gathering information from each layer. The proposed SDS-Net was validated on the BRATS datasets. The Dice coefficients were achieved 92.7, 80.0 and 88.9% for whole tumor (WT), enhancing tumor (ET) and tumor core (TC), respectively, on the BRTAS 2020 dataset. On the BRTAS 2021 dataset, the Dice coefficients were 91.8, 82.5 and 86.8% for WT, ET and TC, respectively. Compared with other state-of-the-art methods, SDS-Net achieved superior segmentation performance with fewer parameters and less computational cost, under the condition of 2.52 M counts and 68.18 G FLOPs.

A distinctive ensemble deep learning model for brain tumor MRI image classification

Brain tumor detection is challenging for radiologists. The early detection of brain tumors is critical, and automated techniques are necessary to achieve this goal. In this study, an automated method is proposed to distinguish between malignant and non-cancerous brain Magnetic Resonance Images (MRI). An ensemble technique was proposed that includes two Deep Learning (DL) models, a 6-Convolutional Neural Network (6-CNN) model with an efficient end-to-end, and a pre-trained Residual Network50 (ResNet50) model. The MRI image classification was experimented in two directions: one using the average probabilities of the ensemble model, and the other considering the optimal weights of the ensemble model for a Support Vector Machine (SVM) classifier with different kernels. Two datasets, Harvard and Retrospective Image Registration Evaluation (RIDER), were used to evaluate the performance of the proposed model. The 6-CNN-ResNet-SVM model achieved the highest accuracy of 97.32% for 10-fold validation, with the remaining performance metrics being an Area Under the Curve (AUC) of 0.98%, sensitivity of 93.62%, specificity of 98%, False Negative Rate (FNR) of 0.06, and False Positive Rate (FPR) of 0.00 for the linear kernel. The proposed model can identify tumors more accurately and quickly than existing approaches.

Brain Tumor Classification for MR Images Using Transfer Learning and EfficientNetB3

Brain tumors are one of the diseases that take many lives in the world, moreover, brain tumors have various types. In the medical world, it has an technology called Magnetic Resonance Imaging (MRI) which functions to see the inside of the human body using a magnetic field. CNN is designed to determine features adaptively using backpropagation by applying layers such as convolutional layers, and pooling layers. This study aims to optimize and increase the accuracy of the classification of brain tumor MRI images using the Convolutional Neural Network (CNN) EfficientNet model. The proposed system consists of two main steps. First, preprocessing images using various methods then classifying images that have been preprocessed using CNN. This study used 3064 images containing three types of brain tumors (gliomata, meningiomas, and pituitary). This study resulted in an accuracy of 98.00%, a precision of 96.00%, and an average recall of 97.00% using the model that the researcher applied. 

Deep Learning-Based Segmentation and Classification Techniques for Brain Tumor MRI: A Review

Early detection of brain tumors is critical for enhancing treatment options and extending patient survival. Magnetic resonance imaging (MRI) scanning gives more detailed information, such as greater contrast and clarity than any other scanning method. Manually dividing brain tumors from many MRI images collected in clinical practice for cancer diagnosis is a tough and time-consuming task. Tumors and MRI scans of the brain can be discovered using algorithms and machine learning technologies, making the process easier for doctors because MRI images can appear healthy when the person may have a tumor or be malignant. Recently, deep learning techniques based on deep convolutional neural networks have been used to analyze medical images with favorable results. It can help save lives faster and rectify some medical errors. In this study, we look at the most up-to-date methodologies for medical image analytics that use convolutional neural networks on MRI images. There are several approaches to diagnosing and classifying brain cancers. Inside the brain, irregular cells grow so that a brain tumor appears. The size of the tumor and the part of the brain affected impact the symptoms.

Clinical Decision Support Framework for Segmentation and Classification of Brain Tumor MRIs Using a U-Net and DCNN Cascaded Learning Algorithm.

Brain tumors (BTs) are an uncommon but fatal kind of cancer. Therefore, the development of computer-aided diagnosis (CAD) systems for classifying brain tumors in magnetic resonance imaging (MRI) has been the subject of many research papers so far. However, research in this sector is still in its early stage. The ultimate goal of this research is to develop a lightweight effective implementation of the U-Net deep network for use in performing exact real-time segmentation. Moreover, a simplified deep convolutional neural network (DCNN) architecture for the BT classification is presented for automatic feature extraction and classification of the segmented regions of interest (ROIs). Five convolutional layers, rectified linear unit, normalization, and max-pooling layers make up the DCNN's proposed simplified architecture. The introduced method was verified on multimodal brain tumor segmentation (BRATS 2015) datasets. Our experimental results on BRATS 2015 acquired Dice similarity coefficient (DSC) scores, sensitivity, and classification accuracy of 88.8%, 89.4%, and 88.6% for high-grade gliomas. When it comes to segmenting BRATS 2015 BT images, the performance of our proposed CAD framework is on par with existing state-of-the-art methods. However, the accuracy achieved in this study for the classification of BT images has improved upon the accuracy reported in prior studies. Image classification accuracy for BRATS 2015 BT has been improved from 88% to 88.6%.

Convolutional Neural Network Based on Brain Tumor Identification and Classification

The human brain is one of the body's most major organs. If there are problems within the human brain, they may cause serious consequences, and even endangers the human life. One of the most fatal diseases for humans is a brain tumor. In the old days, tumor detection was done manually by doctors through reading magnetic resonance images, which might not be time efficient, and sometimes may even produce inaccurate results. Nowadays, with the development of science and technology, Artificial Intelligence (AI) is present in many fields in human life, including medical field. Tumor detection with AI is one of the applications that technology changes human life. The Convolution Neural Network (CNN), a prominent algorithm in deep learning, is widely employed in tumor identification. In this study, a CNN model is proposed. Over 7000 brain tumor magnetic resonance images, including glioma, meningioma, no tumor and pituitary are used in this study. The images are also preprocessed to improve the accuracy of the proposed models. In this study, the well-known VGG16 model, which is a pretrained deep learning model, is utilized to compare with the proposed model. The proposed model and the VGG16 model are trained and evaluated using both the original (uncropped) images and preprocessed (cropped) images. The results of the experiment indicate that the suggested model exceeds the VGG16 model in the light of loss and accuracy.

The multimodal MRI brain tumor segmentation based on AD-Net

Multimodal glioma images provide different features of tumor boundaries based on magnetic resonance imaging (MRI), where multimodal features are often challenging to extract for deep learning segmentation methods. Disturbance between features of different modes is an important factor restricting multimodal learning. To efficiently extract multimodal features, we propose an automatic weighted dilated convolutional network (AD-Net) to learn multimodal brain tumor features through channel feature separation learning. Specifically, the auto-weight dilated convolutional unit (AD unit) utilizes dual-scale convolutional feature maps to acquire channel separation features. We employ two learnable parameters to fuse dual-scale convolutional feature maps in encoding layers, and the two learnable parameters are automatically adjusted with the back propagation of the gradient. We adopt the Jensen–Shannon divergence to constrain the distribution of its feature map, which in turn regularizes the weights of the entire down-sampling. In addition, we use the training technique of deep supervision to achieve fast fitting. Our proposed method got dice scores of 0.90, 0.80, and 0.76 for the whole tumor (WT), the tumor core (TC), and the enhancing tumor (ET) on the BraTS20 dataset. The experimental results showed good performance with the AD-Net network.

Brain Tumor Segmentation using Automatic 3D Multi-channel Feature Selection Convolutional Neural Network

Brain tumor segmentation is an important topic in medical image processing. Three-dimensional (3D) convolutional neural networks (CNN) make full use of feature information and have better segmentation performance. However, conventional 3D CNNs involve a significant number of parameters and has high hardware requirements, which is not conducive to clinical application. To solve these issues, this study proposes a lightweight highly-efficient 3D CNN for brain tumor magnetic resonance imaging segmentation. We first replaced the conventional CNN with improved depth-wise CNN to save computational resources. Next, we employed a multi-channel convolution approach using convolution kernels of different sizes to aggregate features from different receptive fields. Finally, we used a squeeze-and-excitation unit to automatically extract useful feature information in the network. Application of the proposed model to the BraTS2019 validation set resulted in mean Dice scores of 0.9053, 0.8373, and 0.7847, with regard to whole tumor, tumor core, and enhanced tumor, respectively. This was achieved with 2.01 M parameters and 24.68 G floating point operations, and data training used 2.75 GB of video memory. The differences between our Dice scores and those derived using the network developed by the winner of the BraTS2019 challenge were only 0.0041, 0.0174, and 0.0274. Furthermore, the number of parameters and floating point operations were 2.3 times and 8.1 times lower and data training used 4 times lower video memory than the winning network. This indicates that the proposed network offers a higher precision for brain tumor segmentation while reducing computational requirements and effectively lowering hardware requirements for clinical applications.

Identifying overall survival in 98 glioblastomas using VASARI features at 3T

PurposeThis study aims to evaluate qualitative and quantitative imaging metrics along with clinical features affecting overall survival in glioblastomas and to classify them into high survival and low survival groups based on 12, 19, and 24 months thresholds using machine learning. MethodsThe cohort consisted of 98 adult glioblastomas. A standard brain tumor magnetic resonance (MR) imaging protocol, was performed on a 3T MR scanner. Visually Accessible REMBRANDT Images (VASARI) features were assessed. A Kaplan-Meier survival analysis followed by a log-rank test and multivariate Cox regression analysis were used to investigate the effects of VASARI features along with the age, gender, the extent of resection, pre- and post-KPS, ki67 and P53 mutation status on overall survival. Supervised machine learning algorithms were employed to predict the survival of glioblastoma patients based on 12, 19, and 24 months thresholds. ResultsTumor location (p<0.001), the proportion of non-enhancing component (p=0.0482), and proportion of necrosis (p=0.02) were significantly associated with overall survival based on Kaplan-Meier analysis. Multivariate Cox regression analysis revealed that increases in proportion of non-enhancing component (p=0.040) and proportion of necrosis (p=0.039) were significantly associated with overall survival. Machine-learning models were successful in differentiating patients living longer than 12 months with 96.40% accuracy (sensitivity=97.22%, specificity=95.55%). The classification accuracies based on 19 and 24 months survival thresholds were 70.87% (sensitivity=83.02%, specificity=60.11%) and 74.66% (sensitivity=67.58%, specificity=82.08%), respectively. ConclusionEmploying clinical and VASARI features together resulted in a successful classification of glioblastomas that would have a longer overall survival.

MBANet: A 3D convolutional neural network with multi-branch attention for brain tumor segmentation from MRI images

More than half of brain tumors are malignant tumors, so there is a need for fast and accurate segmentation of tumor regions in brain Magnetic Resonance Imaging (MRI) images. Traditional 2D brain tumor segmentation methods seriously ignore the spatial context features of brain tumor MRI images, so how to achieve accurate segmentation of brain tumor regions with multiple modalities is the main problem. The paper proposes a 3D convolutional neural network with 3D multi-branch attention - MBANet. First, the optimized shuffle unit is used to form the basic unit (BU) module of MBANet. In the BU module, the group convolution is used to perform convolution operation after the input channel is split, and the channel shuffle is used to scramble the convolutional channels after fusion. Then, MBANet uses a novel multi-branch 3D Shuffle Attention (SA) module as the attention layer in the encoder. The 3D SA module groups along the channel dimension and divides the feature maps into small features. For each small feature, the 3D SA module builds both channel attention and spatial attention while adopting the BU module. In addition, in order to recover the resolution of the upsampling semantic features better, a 3D SA module is also used in the skip connection of MBANet. Experiments on the BraTS 2018 and BraTS 2019 show that the dice of ET, WT and TC reach 80.18%, 89.80%, 85.47% and 78.21%, 89.79%, 83.04%, respectively. The excellent segmentation performance shows that MBANet is significantly improved compared with other state-of-the-art methods.