Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review

@article{Bernal2019DeepCN,
  title={Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review},
  author={Jos{\'e} Bernal and Kaisar Kushibar and Daniel S. Asfaw and Sergi Valverde and Arnau Oliver and Robert Mart{\'i} and Xavier Llad{\'o}},
  journal={Artificial intelligence in medicine},
  year={2019},
  volume={95},
  pages={
          64-81
        }
}
In recent years, deep convolutional neural networks (CNNs) have shown record-shattering performance in a variety of computer vision problems, such as visual object recognition, detection and segmentation. These methods have also been utilised in medical image analysis domain for lesion segmentation, anatomical segmentation and classification. We present an extensive literature review of CNN techniques applied in brain magnetic resonance imaging (MRI) analysis, focusing on the architectures, pre… Expand
Quantitative Analysis of Patch-Based Fully Convolutional Neural Networks for Tissue Segmentation on Brain Magnetic Resonance Imaging
TLDR
This study implements eight FCNN architectures inspired by robust state-of-the-art methods on brain segmentation related tasks and uses them within a standard pipeline, and shows that the methods under evaluation can yield top performance on the three data collections. Expand
Deep Learning Models with Applications to Brain Image Analysis
TLDR
This chapter introduces the pre-processing steps for brain images and the fundamental concepts of deep neural networks, as well as their applications in brain image classification, segmentation, registration, and image synthesis/augmentation. Expand
Transfer Learning Using Convolutional Neural Network Architectures for Brain Tumor Classification from MRI Images
TLDR
This work uses brain contrast-enhanced magnetic resonance images (CE-MRI) benchmark dataset to classify three types of brain tumor (glioma, meningioma and pituitary), and outperforms the state-of-the-art methods and achieves 98.71% classification accuracy. Expand
Deep Learning Assisted Image Interactive Framework for Brain Image Segmentation
TLDR
Deep Learning Assisted Image Interactive Medical Image Segmentation (DL-IIMIS) is proposed to tackle brain image segmentation difficulties by including CNNs in the bounding box and scribble-based pipeline and to adapt a CNN model to one test frame. Expand
Y-net: a reducing gaussian noise convolutional neural network for MRI brain tumor classification with NADE concatenation
TLDR
This research introduces the Y-net, a new convolutional neural network (CNN) based on the Convolutional U-net architecture and shows that the model is resistant to white noise and can obtain excellent classification accuracy with a limited number of medical images. Expand
Brain Tumor Detection and Segmentation in MR Images Using Deep Learning
TLDR
The proposed hybrid convolutional neural network architecture uses patch-based approach and takes both local and contextual information into account, while predicting output label, improving results compared to the state-of-the-art techniques. Expand
Convolutional neural networks for multi-class brain disease detection using MRI images
TLDR
This model is ready to be tested with huge MRI images of brain abnormalities and the outcome of the model will also help the clinicians to validate their findings after manual reading of the MRI images. Expand
A Domain Guided CNN Architecture for Predicting Age from Structural Brain Images
TLDR
The results suggest that lessons learned from developing models on natural images may not directly transfer to neuroimaging tasks, and there remains a large space of unexplored questions regarding model development in this area. Expand
Supervised Domain Adaptation for Automatic Sub-cortical Brain Structure Segmentation with Minimal User Interaction
TLDR
The transfer learning strategy is employed to solve the domain shift problem and reduce the number of training images by leveraging the knowledge obtained by a pretrained network, and improve the training speed by reducing theNumber of trainable parameters of the CNN. Expand
MRI Images, Brain Lesions and Deep Learning
TLDR
The main conclusion is to establish multidisciplinary research groups to overcome the gap between CAD developments and their complete utilization in the clinical environment. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 217 REFERENCES
Sub-cortical brain structure segmentation using F-CNN'S
TLDR
A deep learning approach for segmenting sub-cortical structures of the human brain in Magnetic Resonance (MR) image data by interpreting the CNN output as potentials of a Markov Random Field (MRF), whose topology corresponds to a volumetric grid. Expand
Brain tumor segmentation with Deep Neural Networks
TLDR
A fast and accurate fully automatic method for brain tumor segmentation which is competitive both in terms of accuracy and speed compared to the state of the art, and introduces a novel cascaded architecture that allows the system to more accurately model local label dependencies. Expand
Deep convolutional neural networks for multi-modality isointense infant brain image segmentation
TLDR
This paper proposes to use deep convolutional neural networks (CNNs) for segmenting isointense stage brain tissues using multi-modality MR images, and compared the performance of the approach with that of the commonly used segmentation methods on a set of manually segmented isointENSE stage brain images. Expand
Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images.
TLDR
This paper proposes an automatic segmentation method based on Convolutional Neural Networks (CNN), exploring small 3 ×3 kernels, which allows designing a deeper architecture, besides having a positive effect against overfitting, given the fewer number of weights in the network. Expand
Multi-modal Brain Tumor Segmentation Using Stacked Denoising Autoencoders
TLDR
Stacked denoising autoencoder (SDAE), a deep neural network that reconstructs its input from multiple MRI sequences for accurate segmentation of gliomas from Magnetic Resonance Images (MRI). Expand
Deep MRI brain extraction: A 3D convolutional neural network for skull stripping
TLDR
A 3D convolutional deep learning architecture to address shortcomings of existing methods, not limited to non-enhanced T1w images, and may prove useful for large-scale studies and clinical trials. Expand
Deep neural networks for anatomical brain segmentation
  • A. D. Brébisson, G. Montana
  • Computer Science, Mathematics
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2015
TLDR
To the knowledge, this technique is the first to tackle the anatomical segmentation of the whole brain using deep neural networks and it does not require any non-linear registration of the MR images. Expand
A review on brain structures segmentation in magnetic resonance imaging
TLDR
There is not yet a single automatic segmentation approach that can emerge as a standard for the clinical practice, providing accurate brain structures segmentation, so future trends need to focus on combining multi-atlas methods with learning-based or deformable approaches. Expand
Multiscale CNNs for Brain Tumor Segmentation and Diagnosis
  • Liya Zhao, K. Jia
  • Computer Science, Medicine
  • Comput. Math. Methods Medicine
  • 2016
TLDR
An automatic brain tumor segmentation method based on Convolutional Neural Networks based on multiscale CNNs which could automatically detect the optimum top-three scales of the image sizes and combine information from different scale of the regions around that pixel. Expand
Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound
TLDR
A novel approach to perform segmentation by leveraging the abstraction capabilities of convolutional neural networks (CNNs) based on Hough voting, which is robust, multi-region, flexible and can be easily adapted to different modalities is proposed. Expand
...
1
2
3
4
5
...