On hierarchical brain tumor segmentation in MRI using fully convolutional neural networks: A preliminary study

Pereira, Sérgio; Oliveira, Américo; Alves, Victor

doi:10.1109/enbeng.2017.7889452

Cited by 43 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, we found that Pereira et al [ 39 ] also proposed a hierarchical brain tumor segmentation approach from MRI HGG images. The difference between their method and our method is that they adopted the FCN in both first and second steps.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network

Cui

Mao

Jiang

et al. 2018

Journal of Healthcare Engineering

163

View full text Add to dashboard Cite

Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Furthermore, the proposed method also yielded higher PPV values in the complete and enhancing tumor categories and a higher sensitivity in the core tumor category. Of note, Pereira et al [ 39 ] trained and tested on the BRATS 2013 dataset but we on the BRATS 2015 dataset.…”

Section: Resultsmentioning

confidence: 99%

Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network

Cui

Mao

Jiang

et al. 2018

Journal of Healthcare Engineering

163

View full text Add to dashboard Cite

show abstract

“…Given the problem of data imbalance between the tumor tissues and normal tissue, and following recent developments in brain tumor segmentation [25], [26], [27], we employ a hierarchical FCN-based brain tumor segmentation approach, as described in [18]. First, we detect the whole tumor as a binary segmentation problem.…”

Section: A Brain Tumor Segmentationmentioning

confidence: 99%

Adaptive Feature Recombination and Recalibration for Semantic Segmentation With Fully Convolutional Networks

Pereira

Pinto

Amorim

et al. 2019

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Fully Convolutional Networks have been achieving remarkable results in image semantic segmentation, while being efficient. Such efficiency results from the capability of segmenting several voxels in a single forward pass. So, there is a direct spatial correspondence between a unit in a feature map and the voxel in the same location. In a convolutional layer, the kernel spans over all channels and extracts information from them. We observe that linear recombination of feature maps by increasing the number of channels followed by compression may enhance their discriminative power. Moreover, not all feature maps have the same relevance for the classes being predicted. In order to learn the inter-channel relationships and recalibrate the channels to suppress the less relevant ones, Squeeze and Excitation blocks were proposed in the context of image classification with Convolutional Neural Networks. However, this is not well adapted for segmentation with Fully Convolutional Networks since they segment several objects simultaneously, hence a feature map may contain relevant information only in some locations. In this paper, we propose recombination of features and a spatially adaptive recalibration block that is adapted for semantic segmentation with Fully Convolutional Networks -the SegSE block. Feature maps are recalibrated by considering the cross-channel information together with spatial relevance. Experimental results indicate that Recombination and Recalibration improve the results of a competitive baseline, and generalize across three different problems: brain tumor segmentation, stroke penumbra estimation, and ischemic stroke lesion outcome prediction. The obtained results are competitive or outperform the state of the art in the three applications.

show abstract

“…Zhao et al [36] Utilized the Convolutional Neural Network (FCNN) and the CRF, a brain-based therapy with DICE 0.87. Pereira et al [28] is a preliminary Examination of the NMR-based FCN-based FCN-based muscle paralysis, a preliminary treatment step that demonstrates the DICE score of 0.85.…”

Section: Related Workmentioning

confidence: 99%

Deep Weber Dominant Local Order Based Feature Generator and Improved Convolution Neural Network for Brain Tumor Segmentation in MR Images

Joseph¹,

Thomas²,

Ramya³

2020

IJEAT

View full text Add to dashboard Cite

This paper introduces a scheme for retrieving deep features to carry out the procedure of recognising brain tumors from MR image. Initially, the MR brain image is denoised through the Modified Decision Based Unsymmetric Trimmed Median Filter (MDBUTMF) after that the contrast of the image is improved through Contrast Limited Adaptive Histogram Equalization (CLAHE). Once the pre-processing task is completed, the next phase is to extract the feature. In order to acquire the features of pre-processed images, this article offers a feature extraction technique named Deep Weber Dominant Local Order Based Feature Generator (DWDLOBFG). Once the deep features are retrieved, the next stage is to separate the brain tumor. Improved Convolution Neural Network (ICNN) is used to achieve this procedure. To explore the efficiency of deep feature extraction and in-depth machine learning methods, four performance indicators were used: Sensitivity (SEN), Jaccard Index (JI), Dice Similarity Coefficient (DSC) and Positive Predictive Value (PPV). The investigational outputs illustrated that the DWDLOBFG and ICNN achieve best outputs than existing techniques.

show abstract

On hierarchical brain tumor segmentation in MRI using fully convolutional neural networks: A preliminary study

Cited by 43 publications

References 10 publications

Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network

Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network

Adaptive Feature Recombination and Recalibration for Semantic Segmentation With Fully Convolutional Networks

Deep Weber Dominant Local Order Based Feature Generator and Improved Convolution Neural Network for Brain Tumor Segmentation in MR Images

Contact Info

Product

Resources

About