Gradient-assisted deep model for brain tumor segmentation by multi-modality MRI volumes

Wang, Yuanyuan; Chen, Junzhang

doi:10.1016/j.bspc.2023.105066

Cited by 5 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different modalities of MRI brain tumor images provide different brain information, and there are certain differences between the lesion regions and normal tissues. Among them, the T1 modality emphasizes anatomical structures, T1ce provides better contrast for the tumor core region, [24][25][26][27] T2 modality expresses the lesion location more, and the FLAIR modality shows prominent edema regions. Therefore, fusing multimodal images in brain tumor segmentation tasks can improve segmentation performance.…”

Section: Multi-encoder Structurementioning

confidence: 99%

Multiencoder‐based federated intelligent deep learning model for brain tumor segmentation

Soni,

Singh,

Singh

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Glioma, a primary tumor derived from brain glial cells, is around 45% of all intracranial tumors. Magnetic resonance imaging's (MRI's) precise glioma segmentation is crucial for clinical purposes. This article presents a novel automatic brain tumor segmentation approach based on a multi‐encoder‐based federated intelligent deep learning framework. The suggested method uses a U‐shaped network design that multiplies the single contraction path into several paths to explore semantic information modalities deeply. The basic convolutional layer uses an Inception module and dilated convolutions to extract multi‐scale features from the images using artificial intelligent. To emphasize segmentation‐related information while ignoring redundant channel dimension information and improving the accuracy of network segmentation, lightweight channel attention efficient channel attention (ECA) modules are inserted into the bottleneck layer and decoder. The collection of data for the 2018 Brain Tumor Segmentation Challenge (BraTS 2018) is used to test the effectiveness of the suggested structure, and the findings indicate that the growth core, for the entire tumor and the augmented tumor regions, respectively, the average Dice coefficients are 0.880, 0.784, and 0.757. These findings support the proposed algorithm's ability to accurately and successfully segregate multimodal MRI brain tumors.

show abstract

Section: Multi-encoder Structurementioning

confidence: 99%

Multiencoder‐based federated intelligent deep learning model for brain tumor segmentation

Soni,

Singh,

Singh

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

MAEU‐NET: A novel supervised architecture for brain tumor segmentation

Kumar,

Biswal

2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

A brain tumor is an abnormal growth of cells that damages the neural system and may lead to severe conditions. These cells are irregular in shape and size, and as a result, the manual analysis of these cells from magnetic resonance (MR) images is a cumbersome and time‐consuming task. To alleviate these issues, a novel U‐Net inspired MAEU‐Net (Multiscale context Aggregation and Edge activation U‐Net) is implemented to detect the brain tumor pixels from MR images more precisely. The encoder block of the proposed model is improved by integrating with multiscale feature aggregation and convolution block attention modules (CBAM) enabling the model to extract both pertinent low‐level and high‐level features. Further, the extracted features are subjected to a parallel pooling module to elevate the features that extract the tumor pixels. In addition to this, the output features of the last encoder are fed to a parallel dilated context aggregation module to mitigate the hyper‐parameter size and further elevate the receptive field strength of the proposed model. Apart from this, edge‐enhanced modules are incorporated with skip connections which concatenate the feature maps of the decoder with respective edge‐enhanced encoder feature maps. As a result, this module increases the aspect ratio and reduces blurry edge problems. To illustrate the performance of the proposed MAEU‐Net, it is trained and tested using Kaggle LGG, BraTS 2018, and BraTS 2021 publicly available datasets. The proposed model outperformed the previously existing models by achieving the test loss, dice coefficient, sensitivity, and specificity of 0.0590, 0.901, 0.942, and 0.998, respectively. Simultaneously, the proposed model is quantitatively analyzed by performing ablation and comparative studies and presented that the proposed MAEU‐Net is superior to other previous existing models like U‐Net++, SegNet, etc.

show abstract

Deformation-aware and reconstruction-driven multimodal representation learning for brain tumor segmentation with missing modalities

Li,

Zhang,

et al. 2024

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Gradient-assisted deep model for brain tumor segmentation by multi-modality MRI volumes

Cited by 5 publications

References 29 publications

Multiencoder‐based federated intelligent deep learning model for brain tumor segmentation

Multiencoder‐based federated intelligent deep learning model for brain tumor segmentation

MAEU‐NET: A novel supervised architecture for brain tumor segmentation

Deformation-aware and reconstruction-driven multimodal representation learning for brain tumor segmentation with missing modalities

Contact Info

Product

Resources

About