CANet: Context Aware Network for Brain Glioma Segmentation

Liu, Zhihua; Tong, Lei; Chen, Long; Zhou, Feixiang; Jiang, Zheheng; Zhang, Qianni; Wang, Yinhai; Shan, Caifeng; Li, Ling; Zhou, Huiyu

doi:10.1109/tmi.2021.3065918

Cited by 58 publications

(30 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results presented here are in the same range of reported findings of studies that used additional contextual information during model training. Overall, the reported results in literature and the ones obtained in this study show that the inclusion of context-awareness, by means of model architecture changes or additional information as input to the network, has marginal or no improvement on glioma segmentation [ 15 , 16 , 17 , 18 , 19 , 20 , 22 , 23 , 24 ]. This should not discourage future research on the topic, but instead promote studies that exploit contextual information for brain tumor segmentation by other approaches and perhaps a combination of the currently implemented methods, i.e., context-aware blocks and additional contextual information as input to the network.…”

Section: Discussionsupporting

confidence: 58%

“…A number of attempts have been made to evaluate the impact of the introduction of context-aware blocks in the model architecture on brain tumor segmentation [ 16 , 17 , 18 , 19 , 20 ]. For example, Pei et al [ 19 ] used a context-aware deep neural network which thanks to a context encoding module between the encoder and the decoder part of the network, helped in overcoming the class imbalance problem that challenges brain tumor segmentation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Does Anatomical Contextual Information Improve 3D U-Net-Based Brain Tumor Segmentation?

2021

View full text Add to dashboard Cite

Effective, robust, and automatic tools for brain tumor segmentation are needed for the extraction of information useful in treatment planning. Recently, convolutional neural networks have shown remarkable performance in the identification of tumor regions in magnetic resonance (MR) images. Context-aware artificial intelligence is an emerging concept for the development of deep learning applications for computer-aided medical image analysis. A large portion of the current research is devoted to the development of new network architectures to improve segmentation accuracy by using context-aware mechanisms. In this work, it is investigated whether or not the addition of contextual information from the brain anatomy in the form of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) masks and probability maps improves U-Net-based brain tumor segmentation. The BraTS2020 dataset was used to train and test two standard 3D U-Net (nnU-Net) models that, in addition to the conventional MR image modalities, used the anatomical contextual information as extra channels in the form of binary masks (CIM) or probability maps (CIP). For comparison, a baseline model (BLM) that only used the conventional MR image modalities was also trained. The impact of adding contextual information was investigated in terms of overall segmentation accuracy, model training time, domain generalization, and compensation for fewer MR modalities available for each subject. Median (mean) Dice scores of 90.2 (81.9), 90.2 (81.9), and 90.0 (82.1) were obtained on the official BraTS2020 validation dataset (125 subjects) for BLM, CIM, and CIP, respectively. Results show that there is no statistically significant difference when comparing Dice scores between the baseline model and the contextual information models (p > 0.05), even when comparing performances for high and low grade tumors independently. In a few low grade cases where improvement was seen, the number of false positives was reduced. Moreover, no improvements were found when considering model training time or domain generalization. Only in the case of compensation for fewer MR modalities available for each subject did the addition of anatomical contextual information significantly improve (p < 0.05) the segmentation of the whole tumor. In conclusion, there is no overall significant improvement in segmentation performance when using anatomical contextual information in the form of either binary WM, GM, and CSF masks or probability maps as extra channels.

show abstract

Section: Discussionsupporting

confidence: 58%

Section: Introductionmentioning

confidence: 99%

Does Anatomical Contextual Information Improve 3D U-Net-Based Brain Tumor Segmentation?

2021

View full text Add to dashboard Cite

show abstract

“…Variations of 3D U-Net were proven effective in 3D graphical information extraction from brain MRI images [22], [23], [24]. Recently, the contextual information of tumors and surroundings were modeled in a feature interaction graph to optimize latent feature representation [19]. Despite growing evaluation results, voxel ambiguity remains a challenging problem in brain glioma segmentation, which has yet to be solved.…”

Section: Related Workmentioning

confidence: 99%

“…Ground-truth annotations contain healthy tissues, enhancing tumor (ET), whole tumor (WT), and tumor core (TC). We followed pre-processing steps in [19] and performed five-fold cross-validation with a random division.…”

Section: Experiments a Dataset And Implementationmentioning

confidence: 99%

See 1 more Smart Citation

Residual Channel Attention Network for Brain Glioma Segmentation

Yao,

Qian,

Zhao

et al. 2022

Preprint

View full text Add to dashboard Cite

A glioma is a malignant brain tumor that seriously affects cognitive functions and lowers patients' life quality. Segmentation of brain glioma is challenging because of interclass ambiguities in tumor regions. Recently, deep learning approaches have achieved outstanding performance in the automatic segmentation of brain glioma. However, existing algorithms fail to exploit channel-wise feature interdependence to select semantic attributes for glioma segmentation. In this study, we implement a novel deep neural network that integrates residual channel attention modules to calibrate intermediate features for glioma segmentation. The proposed channel attention mechanism adaptively weights feature channel-wise to optimize the latent representation of gliomas. We evaluate our method on the established dataset BraTS2017. Experimental results indicate the superiority of our method.Clinical relevance-While existing glioma segmentation approaches do not leverage channel-wise feature dependence for feature selection, our method can generate segmentation masks with higher accuracies and provide more insights on graphic patterns in brain MRI images for further clinical reference.

show abstract

Brain tumor segmentation by combining MultiEncoder UNet with wavelet fusion

Pan,

Yong,

et al. 2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background and objectiveAccurate segmentation of brain tumors from multimodal magnetic resonance imaging (MRI) holds significant importance in clinical diagnosis and surgical intervention, while current deep learning methods cope with situations of multimodal MRI by an early fusion strategy that implicitly assumes that the modal relationships are linear, which tends to ignore the complementary information between modalities, negatively impacting the model's performance. Meanwhile, long‐range relationships between voxels cannot be captured due to the localized character of the convolution procedure.MethodAiming at this problem, we propose a multimodal segmentation network based on a late fusion strategy that employs multiple encoders and a decoder for the segmentation of brain tumors. Each encoder is specialized for processing distinct modalities. Notably, our framework includes a feature fusion module based on a 3D discrete wavelet transform aimed at extracting complementary features among the encoders. Additionally, a 3D global context‐aware module was introduced to capture the long‐range dependencies of tumor voxels at a high level of features. The decoder combines fused and global features to enhance the network's segmentation performance.ResultOur proposed model is experimented on the publicly available BraTS2018 and BraTS2021 datasets. The experimental results show competitiveness with state‐of‐the‐art methods.ConclusionThe results demonstrate that our approach applies a novel concept for multimodal fusion within deep neural networks and delivers more accurate and promising brain tumor segmentation, with the potential to assist physicians in diagnosis.

show abstract

CANet: Context Aware Network for Brain Glioma Segmentation

Abstract: The version in the Kent Academic Repository may differ from the final published version. Users are advised to check http://kar.kent.ac.uk for the status of the paper. Users should always cite the published version of record.

Cited by 58 publications

References 50 publications

Does Anatomical Contextual Information Improve 3D U-Net-Based Brain Tumor Segmentation?

Does Anatomical Contextual Information Improve 3D U-Net-Based Brain Tumor Segmentation?

Residual Channel Attention Network for Brain Glioma Segmentation

Brain tumor segmentation by combining MultiEncoder UNet with wavelet fusion

Contact Info

Product

Resources

About