Brain Tumor MRI Image Segmentation Using Deep Learning Techniques
Brain Tumor MRI Image Segmentation Using Deep Learning Techniques offers a description of deep learning approaches used for the segmentation of brain tumors.The book demonstrates core concepts of deep learning algorithms by using diagrams, data tables and examples to illustrate brain tumor segmentat...
Uloženo v:
| Hlavní autor: | |
|---|---|
| Médium: | E-kniha |
| Jazyk: | angličtina |
| Vydáno: |
Chantilly
Elsevier Science & Technology
2021
Academic Press |
| Vydání: | 1 |
| Témata: | |
| ISBN: | 0323911714, 9780323911719 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
Obsah:
- 11.5 Conclusion -- References -- Chapter 12 On comparing optimizer of UNet-VGG16 architecture for brain tumor image segmentation -- 12.1 Introduction -- 12.2 Methodology -- 12.2.1 UNet-VGG16 with transfer learning + dropout -- 12.2.2 The optimizer -- 12.2.3 The evaluation metrics -- 12.3 Results and discussion -- 12.3.1 Dataset -- 12.3.2 Experimental design -- 12.3.3 Optimizer comparison -- 12.3.4 Segmentation results -- 12.4 Conclusion -- Reference -- Chapter 13 Comparative analysis of deformable models based segmentation methods for brain tumor classification -- 13.1 Introduction -- 13.1.1 Objectives of the proposed research -- 13.2 Proposed methods with results -- 13.2.1 Performance evaluation metrics -- 13.2.2 GVF active contour based brain tumor segmentation and classification using MR images -- 13.2.3 Fuzzy GVF deformable based brain tumor segmentation and classification using MR images -- 13.2.4 Optimization-driven deep convolution neural network for brain tumor segmentation and classification -- 13.3 Conclusion -- References -- Chapter 14 Brain tumor segmentation using deep learning: taxonomy, survey and challenges -- 14.1 Introduction -- 14.2 Previous works -- 14.3 Brain tumor -- 14.4 Brain tumor detection using image processing techniques -- 14.5 Brain tumor segmentation -- 14.5.1 Techniques -- 14.6 Deep learning -- 14.6.1 Basic working of deep neural network -- 14.6.2 Taxonomy -- 14.7 Challenges -- 14.7.1 Technical-biological-clinical validations -- 14.7.2 Uncertainty due to location and morphology -- 14.7.3 High performance graphics processing units (GPUs) for big data -- 14.7.4 Working with hyperparameters -- 14.7.5 Domain-specific solutions -- References -- Index -- Back cover
- Front cover -- Half title -- Title -- Copyright -- Contents -- Contributors -- Chapter 1 Brain MRI segmentation using deep learning: background study and challenges -- 1.1 Brain tumor and magnetic resonance imaging -- 1.2 Methods for brain MRI segmentation -- 1.2.1 Manual segmentation methods -- 1.2.2 Semiautomated segmentation methods -- 1.2.3 Fully automated segmentation methods -- 1.3 Deep learning -- 1.3.1 Fully convolutional networks -- 1.3.2 Convolutional models with graphical models -- 1.3.3 Encoder-decoder-based models -- 1.3.4 Multiscale and pyramid network-based models -- 1.4 Challenges of DL in the field of brain MRI segmentation -- 1.4.1 Data -- 1.4.2 Reliability -- 1.5 Summary -- References -- Chapter 2 Data preprocessing techniques for MRI brain scans using deep learning models -- 2.1 Introduction -- 2.2 Related works -- 2.3 Traditional NLM algorithm -- 2.4 Proposed method -- 2.5 Material and metrics -- 2.6 Results and discussion -- 2.7 Conclusion -- References -- Chapter 3 A survey of brain segmentation methods from magnetic resonance imaging -- 3.1 Introduction -- 3.2 Dataset -- 3.3 Methods -- 3.3.1 Preprocessing -- 3.3.2 Brain segmentation -- 3.4 Challenges -- 3.5 Conclusion and discussion -- References -- Chapter 4 Brain tumor segmentation and detection in magnetic resonance imaging (MRI) using convolutional neural network -- 4.1 Introduction -- 4.2 Literature survey -- 4.3 Proposed method -- 4.3.1 Software requirement specification -- 4.3.2 Design and implementation constraints -- 4.3.3 Assumptions and dependencies -- 4.4 Data preprocessing -- 4.4.1 Dataset details and data augmentation -- 4.4.2 Cropping and resizing -- 4.4.3 Plotting of input images -- 4.4.4 Performing watershed segmentation -- 4.4.5 Otsu's binarization to threshold the image -- 4.4.6 Image representation of the preprocessing model
- 4.5 Splitting the preprocessed data -- 4.6 Building the CNN architecture -- 4.7 Fitting the CNN architecture -- 4.8 Results of the experiment -- 4.8.1 Performance metrics -- 4.8.2 Efficient and computational complexity -- 4.9 Discussions and conclusion -- References -- Chapter 5 Simultaneous brain tumor segmentation and molecular profiling using deep learning and T2w magnetic resonance images -- 5.1 Introduction -- 5.1.1 Glioma molecular markers -- 5.1.2 2HG spectroscopy for IDH status -- 5.1.3 TCIA database -- 5.1.4 MRI and deep learning for glioma molecular markers -- 5.1.5 T2w versus multicontrast MRI data -- 5.2 Summary of the methods -- 5.2.1 Classification of IDH mutation status -- 5.2.2 Classification of 1p/19q codeletion status -- 5.2.3 MGMT methylation promoter -- 5.3 Discussion -- 5.4 Conclusion -- Acknowledgments -- References -- Chapter 6 An adaptive smart healthcare system to detect tumor from brain MRI using machine learning algorithm -- 6.1 Introduction -- 6.2 Related work -- 6.3 Experimental dataset -- 6.4 Existing CAD system -- 6.5 Performance evaluation -- 6.6 Concluding remark -- Conflict of interest -- Funding Information -- References -- Chapter 7 Deep learning-based decision support system for multicerebral disease classification and identification -- 7.1 Introduction -- 7.2 Interclassification of diseases -- 7.2.1 Brain tumor -- 7.2.2 Alzheimer's disease -- 7.2.3 Brain hemorrhage -- 7.3 Performance -- 7.3.1 Hardware specifications -- 7.3.2 Computational complexity -- 7.4 Proposed work -- 7.4.1 Interdisease classification -- 7.4.2 Brain tumor classification -- 7.4.3 Brain tumor segmentation -- 7.4.4 Alzheimer's disease classification -- 7.5 Conclusion and future work -- References -- Chapter 8 Multimodal MRI Brain Tumor Segmentation-A ResNet-based U-Net approach -- 8.1 Introduction -- 8.2 Related works
- 8.3 Materials and metrics -- 8.4 Methodology -- 8.4.1 Workflow of proposed segmentation method -- 8.4.2 Data preprocessing -- 8.4.3 Model development -- 8.5 Results and discussions -- 8.6 Conclusion and future enhancements -- References -- Chapter 9 Deep learning-based brain malignant neoplasm classification using MRI image segmentation assisted by bias field correction and histogram equalization -- 9.1 Overview of artificial intelligence -- 9.1.1 Machine learning -- 9.1.2 Deep learning -- 9.1.3 Artificial neural networks (ANN) -- 9.2 Activation functions in neural networks -- 9.2.1 Binary activation function -- 9.2.2 TanH activation function -- 9.2.3 ReLU activation function -- 9.2.4 Sigmoid activation function -- 9.3 Convolutional neural network -- 9.4 Proposed method -- 9.4.1 System model -- 9.4.2 Grayscale conversion -- 9.4.3 Bias field correction -- 9.4.4 Histogram equalization -- 9.4.5 Image segmentation -- 9.4.6 Deep learning model -- 9.4.7 Training and testing the model -- 9.5 Results -- 9.6 Conclusion -- References -- Chapter 10 Brain MRI segmentation techniques based on CNN and its variants -- 10.1 Introduction -- 10.2 Methodology -- 10.2.1 Dataset source -- 10.2.2 Dataset preprocessing -- 10.2.3 Evaluation metrics -- 10.3 Neural networks, image classification, and related terminology -- 10.3.1 Convolutional neural networks (CNN) -- 10.3.2 Semantic segmentation -- 10.4 CNN architectures and their uses in brain imaging -- 10.4.1 Autoencoders -- 10.4.2 U-Net -- 10.4.3 ResNet -- 10.4.4 PSPNet -- 10.5 Experiments performed and results -- 10.5.1 U-Net -- 10.5.2 ResNet -- 10.5.3 PSPNet -- 10.6 Conclusion -- 10.7 Future scope -- References -- Chapter 11 Detection of Brain Tumor with Magnetic Resonance Imaging using Deep Learning Techniques -- 11.1 Introduction -- 11.2 Literature survey -- 11.3 Proposed method -- 11.4 Results and discussion