scholarly journals GenU-Net++: An Automatic Intracranial Brain Tumors Segmentation Algorithm on 3D Image Series with High Performance

Symmetry ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 2395
Author(s):  
Yan Zhang ◽  
Xi Liu ◽  
Shiyun Wa ◽  
Yutong Liu ◽  
Jiali Kang ◽  
...  
Keyword(s):  
Brain Tumor ◽  
Brain Tumors ◽  
Interpolation Method ◽  
Magnetic Resonance Images ◽  
Segmentation Algorithm ◽  
Validation Dataset ◽  
Tumor Segmentation ◽  
3D Image ◽  
Feature Maps ◽  
Image Series

Automatic segmentation of intracranial brain tumors in three-dimensional (3D) image series is critical in screening and diagnosing related diseases. However, there are various challenges in intracranial brain tumor images: (1) Multiple brain tumor categories hold particular pathological features. (2) It is a thorny issue to locate and discern brain tumors from other non-brain regions due to their complicated structure. (3) Traditional segmentation requires a noticeable difference in the brightness of the interest target relative to the background. (4) Brain tumor magnetic resonance images (MRI) have blurred boundaries, similar gray values, and low image contrast. (5) Image information details would be dropped while suppressing noise. Existing methods and algorithms do not perform satisfactorily in overcoming these obstacles mentioned above. Most of them share an inadequate accuracy in brain tumor segmentation. Considering that the image segmentation task is a symmetric process in which downsampling and upsampling are performed sequentially, this paper proposes a segmentation algorithm based on U-Net++, aiming to address the aforementioned problems. This paper uses the BraTS 2018 dataset, which contains MR images of 245 patients. We suggest the generative mask sub-network, which can generate feature maps. This paper also uses the BiCubic interpolation method for upsampling to obtain segmentation results different from U-Net++. Subsequently, pixel-weighted fusion is adopted to fuse the two segmentation results, thereby, improving the robustness and segmentation performance of the model. At the same time, we propose an auto pruning mechanism in terms of the architectural features of U-Net++ itself. This mechanism deactivates the sub-network by zeroing the input. It also automatically prunes GenU-Net++ during the inference process, increasing the inference speed and improving the network performance by preventing overfitting. Our algorithm’s PA, MIoU, P, and R are tested on the validation dataset, reaching 0.9737, 0.9745, 0.9646, and 0.9527, respectively. The experimental results demonstrate that the proposed model outperformed the contrast models. Additionally, we encapsulate the model and develop a corresponding application based on the MacOS platform to make the model further applicable.

scholarly journals Asymmetric Ensemble of Asymmetric U-Net Models for Brain Tumor Segmentation With Uncertainty Estimation

2021 ◽  
Vol 12 ◽  
Author(s):  
Sarahi Rosas-Gonzalez ◽  
Taibou Birgui-Sekou ◽  
Moncef Hidane ◽  
Ilyess Zemmoura ◽  
Clovis Tauber
Keyword(s):  
Brain Tumor ◽  
State Of The Art ◽  
Contextual Information ◽  
Magnetic Resonance Images ◽  
Validation Dataset ◽  
Tumor Segmentation ◽  
Dice Similarity Coefficient ◽  
Prediction Errors ◽  
Brain Tumor Segmentation ◽  
Multi Scale

Accurate brain tumor segmentation is crucial for clinical assessment, follow-up, and subsequent treatment of gliomas. While convolutional neural networks (CNN) have become state of the art in this task, most proposed models either use 2D architectures ignoring 3D contextual information or 3D models requiring large memory capacity and extensive learning databases. In this study, an ensemble of two kinds of U-Net-like models based on both 3D and 2.5D convolutions is proposed to segment multimodal magnetic resonance images (MRI). The 3D model uses concatenated data in a modified U-Net architecture. In contrast, the 2.5D model is based on a multi-input strategy to extract low-level features from each modality independently and on a new 2.5D Multi-View Inception block that aims to merge features from different views of a 3D image aggregating multi-scale features. The Asymmetric Ensemble of Asymmetric U-Net (AE AU-Net) based on both is designed to find a balance between increasing multi-scale and 3D contextual information extraction and keeping memory consumption low. Experiments on 2019 dataset show that our model improves enhancing tumor sub-region segmentation. Overall, performance is comparable with state-of-the-art results, although with less learning data or memory requirements. In addition, we provide voxel-wise and structure-wise uncertainties of the segmentation results, and we have established qualitative and quantitative relationships between uncertainty and prediction errors. Dice similarity coefficient for the whole tumor, tumor core, and tumor enhancing regions on BraTS 2019 validation dataset were 0.902, 0.815, and 0.773. We also applied our method in BraTS 2018 with corresponding Dice score values of 0.908, 0.838, and 0.800.

Integrating Improved U-Net and Continuous Maximum Flow Algorithm for 3D Brain Tumor Image Segmentation

2020 ◽  
Vol 64 (4) ◽  
pp. 40412-1-40412-11
Author(s):  
Kexin Bai ◽  
Qiang Li ◽  
Ching-Hsin Wang
Keyword(s):  
Brain Tumor ◽  
Data Augmentation ◽  
A Priori ◽  
Class Imbalance ◽  
Maximum Flow ◽  
Magnetic Resonance Images ◽  
Tumor Segmentation ◽  
Similarity Coefficients ◽  
Segmentation Algorithms ◽  
Flow Algorithm

Abstract To address the issues of the relatively small size of brain tumor image datasets, severe class imbalance, and low precision in existing segmentation algorithms for brain tumor images, this study proposes a two-stage segmentation algorithm integrating convolutional neural networks (CNNs) and conventional methods. Four modalities of the original magnetic resonance images were first preprocessed separately. Next, preliminary segmentation was performed using an improved U-Net CNN containing deep monitoring, residual structures, dense connection structures, and dense skip connections. The authors adopted a multiclass Dice loss function to deal with class imbalance and successfully prevented overfitting using data augmentation. The preliminary segmentation results subsequently served as the a priori knowledge for a continuous maximum flow algorithm for fine segmentation of target edges. Experiments revealed that the mean Dice similarity coefficients of the proposed algorithm in whole tumor, tumor core, and enhancing tumor segmentation were 0.9072, 0.8578, and 0.7837, respectively. The proposed algorithm presents higher accuracy and better stability in comparison with some of the more advanced segmentation algorithms for brain tumor images.

Recent advancements in Fuzzy C-means based techniques for brain MRI Segmentation

2021 ◽  
Vol 16 ◽  
Author(s):  
Ghazanfar Latif ◽  
Jaafar Alghazo ◽  
Fadi N. Sibai ◽  
D.N.F. Awang Iskandar ◽  
Adil H. Khan
Keyword(s):  
Brain Tumor ◽  
Brain Tumors ◽  
Brain Mri ◽  
Tumor Segmentation ◽  
Brain Anatomy ◽  
Mri Segmentation ◽  
Brain Tumor Segmentation ◽  
Brain Images ◽  
Low Contrast ◽  
Fuzzy C Means

Background: Variations of image segmentation techniques, particularly those used for Brain MRI segmentation, vary in complexity from basic standard Fuzzy C-means (FCM) to more complex and enhanced FCM techniques. Objective: In this paper, a comprehensive review is presented on all thirteen variations of FCM segmentation techniques. In the review process, the concentration is on the use of FCM segmentation techniques for brain tumors. Brain tumor segmentation is a vital step in the process of automatically diagnosing brain tumors. Unlike segmentation of other types of images, brain tumor segmentation is a very challenging task due to the variations in brain anatomy. The low contrast of brain images further complicates this process. Early diagnosis of brain tumors is indeed beneficial to patients, doctors, and medical providers. Results: FCM segmentation works on images obtained from magnetic resonance imaging (MRI) scanners, requiring minor modifications to hospital operations to early diagnose tumors as most, if not all, hospitals rely on MRI machines for brain imaging. In this paper, we critically review and summarize FCM based techniques for brain MRI segmentation.

Brain Tumor Detection via Asymmetry Quantification across Mid Sagittal Plane

2020 ◽  
Vol 13 ◽  
Author(s):  
Shoaib Amin Banday ◽  
Mohammad Khalid Pandit
Keyword(s):  
Brain Tumor ◽  
Brain Tumors ◽  
Sagittal Plane ◽  
Early Stage ◽  
Imaging Techniques ◽  
Complex Structure ◽  
Magnetic Resonance Images ◽  
Absolute Difference ◽  
Brain Hemispheres ◽  
The Brain

Introduction: Brain tumor is among the major causes of morbidity and mortality rates worldwide. According to National Brain Tumor Foundation (NBTS), the death rate has nearly increased by as much as 300% over last couple of decades. Tumors can be categorized as benign (non-cancerous) and malignant (cancerous). The type of the brain tumor significantly depends on various factors like the site of its occurrence, its shape, the age of the subject etc. On the other hand, Computer Aided Detection (CAD) has been improving significantly in recent times. The concept, design and implementation of these systems ascend from fairly simple ones to computationally intense ones. For efficient and effective diagnosis and treatment plans in brain tumor studies, it is imperative that an abnormality is detected at an early stage as it provides a little more time for medical professionals to respond. The early detection of diseases has predominantly been possible because of medical imaging techniques developed from past many decades like CT, MRI, PET, SPECT, FMRI etc. The detection of brain tumors however, has always been a challenging task because of the complex structure of the brain, diverse tumor sizes and locations in the brain. Method: This paper proposes an algorithm that can detect the brain tumors in the presence of the Radio-Frequency (RF) inhomoginiety. The algorithm utilizes the Mid Sagittal Plane as a landmark point across which the asymmetry between the two brain hemispheres is estimated using various intensity and texture based parameters. Result: The results show the efficacy of the proposed method for the detection of the brain tumors with an acceptable detection rate. Conclusion: In this paper, we have calculated three textural features from the two hemispheres of the brain viz: Contrast (CON), Entropy (ENT) and Homogeneity (HOM) and three parameters viz: Root Mean Square Error (RMSE), Correlation Co-efficient (CC), and Integral of Absolute Difference (IAD) from the intensity distribution profiles of the two brain hemispheres to predict any presence of the pathology. First a Mid Sagittal Plane (MSP) is obtained on the Magnetic Resonance Images that virtually divides brain into two bilaterally symmetric hemispheres. The block wise texture asymmetry is estimated for these hemispheres using the above 6 parameters.

scholarly journals Differential Deep Convolutional Neural Network Model for Brain Tumor Classification

2021 ◽  
Vol 11 (3) ◽  
pp. 352
Author(s):  
Isselmou Abd El Kader ◽  
Guizhi Xu ◽  
Zhang Shuai ◽  
Sani Saminu ◽  
Imran Javaid ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Brain Tumor ◽  
Magnetic Resonance ◽  
Brain Tumors ◽  
Medical Image ◽  
Resonance Imaging ◽  
Feature Maps ◽  
Deep Cnn

The classification of brain tumors is a difficult task in the field of medical image analysis. Improving algorithms and machine learning technology helps radiologists to easily diagnose the tumor without surgical intervention. In recent years, deep learning techniques have made excellent progress in the field of medical image processing and analysis. However, there are many difficulties in classifying brain tumors using magnetic resonance imaging; first, the difficulty of brain structure and the intertwining of tissues in it; and secondly, the difficulty of classifying brain tumors due to the high density nature of the brain. We propose a differential deep convolutional neural network model (differential deep-CNN) to classify different types of brain tumor, including abnormal and normal magnetic resonance (MR) images. Using differential operators in the differential deep-CNN architecture, we derived the additional differential feature maps in the original CNN feature maps. The derivation process led to an improvement in the performance of the proposed approach in accordance with the results of the evaluation parameters used. The advantage of the differential deep-CNN model is an analysis of a pixel directional pattern of images using contrast calculations and its high ability to classify a large database of images with high accuracy and without technical problems. Therefore, the proposed approach gives an excellent overall performance. To test and train the performance of this model, we used a dataset consisting of 25,000 brain magnetic resonance imaging (MRI) images, which includes abnormal and normal images. The experimental results showed that the proposed model achieved an accuracy of 99.25%. This study demonstrates that the proposed differential deep-CNN model can be used to facilitate the automatic classification of brain tumors.

IBRDM: An Intelligent Framework for Brain Tumor Classification Using Radiomics- and DWT-based Fusion of MRI Sequences

2022 ◽  
Vol 22 (1) ◽  
pp. 1-30
Author(s):  
Rahul Kumar ◽  
Ankur Gupta ◽  
Harkirat Singh Arora ◽  
Balasubramanian Raman
Keyword(s):  
Brain Tumor ◽  
Brain Tumors ◽  
Performance Metrics ◽  
Tumor Classification ◽  
Training Dataset ◽  
Tumor Segmentation ◽  
Discrete Wavelet ◽  
Low Grade ◽  
Brain Tumor Segmentation ◽  
Mri Sequences

Brain tumors are one of the critical malignant neurological cancers with the highest number of deaths and injuries worldwide. They are categorized into two major classes, high-grade glioma (HGG) and low-grade glioma (LGG), with HGG being more aggressive and malignant, whereas LGG tumors are less aggressive, but if left untreated, they get converted to HGG. Thus, the classification of brain tumors into the corresponding grade is a crucial task, especially for making decisions related to treatment. Motivated by the importance of such critical threats to humans, we propose a novel framework for brain tumor classification using discrete wavelet transform-based fusion of MRI sequences and Radiomics feature extraction. We utilized the Brain Tumor Segmentation 2018 challenge training dataset for the performance evaluation of our approach, and we extract features from three regions of interest derived using a combination of several tumor regions. We used wrapper method-based feature selection techniques for selecting a significant set of features and utilize various machine learning classifiers, Random Forest, Decision Tree, and Extra Randomized Tree for training the model. For proper validation of our approach, we adopt the five-fold cross-validation technique. We achieved state-of-the-art performance considering several performance metrics, 〈 Acc , Sens , Spec , F1-score , MCC , AUC 〉 ≡ 〈 98.60%, 99.05%, 97.33%, 99.05%, 96.42%, 98.19% 〉, where Acc , Sens , Spec , F1-score , MCC , and AUC represents the accuracy, sensitivity, specificity, F1-score, Matthews correlation coefficient, and area-under-the-curve, respectively. We believe our proposed approach will play a crucial role in the planning of clinical treatment and guidelines before surgery.

scholarly journals MRI-based brain tumor segmentation using FPGA-accelerated neural network

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Siyu Xiong ◽  
Guoqing Wu ◽  
Xitian Fan ◽  
Xuan Feng ◽  
Zhongcheng Huang ◽  
...  
Keyword(s):  
Neural Network ◽  
Energy Efficiency ◽  
Deep Learning ◽  
Brain Tumor ◽  
Brain Tumors ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Cad Systems ◽  
Segmentation Accuracy ◽  
The Brain

Abstract Background Brain tumor segmentation is a challenging problem in medical image processing and analysis. It is a very time-consuming and error-prone task. In order to reduce the burden on physicians and improve the segmentation accuracy, the computer-aided detection (CAD) systems need to be developed. Due to the powerful feature learning ability of the deep learning technology, many deep learning-based methods have been applied to the brain tumor segmentation CAD systems and achieved satisfactory accuracy. However, deep learning neural networks have high computational complexity, and the brain tumor segmentation process consumes significant time. Therefore, in order to achieve the high segmentation accuracy of brain tumors and obtain the segmentation results efficiently, it is very demanding to speed up the segmentation process of brain tumors. Results Compared with traditional computing platforms, the proposed FPGA accelerator has greatly improved the speed and the power consumption. Based on the BraTS19 and BraTS20 dataset, our FPGA-based brain tumor segmentation accelerator is 5.21 and 44.47 times faster than the TITAN V GPU and the Xeon CPU. In addition, by comparing energy efficiency, our design can achieve 11.22 and 82.33 times energy efficiency than GPU and CPU, respectively. Conclusion We quantize and retrain the neural network for brain tumor segmentation and merge batch normalization layers to reduce the parameter size and computational complexity. The FPGA-based brain tumor segmentation accelerator is designed to map the quantized neural network model. The accelerator can increase the segmentation speed and reduce the power consumption on the basis of ensuring high accuracy which provides a new direction for the automatic segmentation and remote diagnosis of brain tumors.

scholarly journals Multi-Task Deep Supervision on Attention R2U-Net for Brain Tumor Segmentation

2021 ◽  
Vol 11 ◽  
Author(s):  
Shiqiang Ma ◽  
Jijun Tang ◽  
Fei Guo
Keyword(s):  
Deep Learning ◽  
Brain Tumor ◽  
Computational Cost ◽  
Medical Image Segmentation ◽  
Validation Dataset ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Proposed Model ◽  
Fusion Methods ◽  
Tumor Area

Accurate automatic medical image segmentation technology plays an important role for the diagnosis and treatment of brain tumor. However, simple deep learning models are difficult to locate the tumor area and obtain accurate segmentation boundaries. In order to solve the problems above, we propose a 2D end-to-end model of attention R2U-Net with multi-task deep supervision (MTDS). MTDS can extract rich semantic information from images, obtain accurate segmentation boundaries, and prevent overfitting problems in deep learning. Furthermore, we propose the attention pre-activation residual module (APR), which is an attention mechanism based on multi-scale fusion methods. APR is suitable for a deep learning model to help the network locate the tumor area accurately. Finally, we evaluate our proposed model on the public BraTS 2020 validation dataset which consists of 125 cases, and got a competitive brain tumor segmentation result. Compared with the state-of-the-art brain tumor segmentation methods, our method has the characteristics of a small parameter and low computational cost.

Sign in / Sign up

Export Citation Format

Share Document