A novel M-SegNet with global attention CNN architecture for automatic segmentation of brain MRI

Yamanakkanavar, Nagaraj; Lee, Bumshik

doi:10.1016/j.compbiomed.2021.104761

Cited by 31 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As measured by the DSC, JI, and HD metrics, the proposed method exhibits a significantly higher segmentation accuracy than existing methods. Our proposed network achieved a mean improvement of 7%, 4%, 3%, 2%, 1.5%, and 0.5% (in terms of DSC) with respect to SegNet [ 19 ], U-net [ 20 ], M-net [ 21 ], U-net++ [ 34 ], CE-Net [ 36 ], and M-SegNet [ 39 ] methods, respectively. This is because the proposed method uses information extracted from multi-scale side paths.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…Deng et al [ 38 ] propose an FDNN that derives information simultaneously from neural and fuzzy representations. In [ 39 ], an M-SegNet architecture with global attention was proposed for brain MRI segmentation as in our previous study, where the global attention approach captures rich contextual information by combining local features and global dependencies at the decoding stage.…”

Section: Methodsmentioning

confidence: 99%

“…As shown in Figure 2 , we create uniform patch sizes

by padding zeros throughout the boundaries of the image. In our previous work [ 39 , 52 ], several slices at the beginning and end of the brain MRI volume contain no useful information, and almost identical information will be exchanged between consecutive slices. As a result, to eliminate non-informative slices,

slices are extracted from the S slices in a constant interval of 3.…”

Section: Proposed Methodologymentioning

confidence: 99%

See 2 more Smart Citations

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

Yamanakkanavar

Choi

Lee

2022

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a novel squeeze M-SegNet (SM-SegNet) architecture featuring a fire module to perform accurate as well as fast segmentation of the brain on magnetic resonance imaging (MRI) scans. The proposed model utilizes uniform input patches, combined-connections, long skip connections, and squeeze–expand convolutional layers from the fire module to segment brain MRI data. The proposed SM-SegNet architecture involves a multi-scale deep network on the encoder side and deep supervision on the decoder side, which uses combined-connections (skip connections and pooling indices) from the encoder to the decoder layer. The multi-scale side input layers support the deep network layers’ extraction of discriminative feature information, and the decoder side provides deep supervision to reduce the gradient problem. By using combined-connections, extracted features can be transferred from the encoder to the decoder resulting in recovering spatial information, which makes the model converge faster. Long skip connections were used to stabilize the gradient updates in the network. Owing to the adoption of the fire module, the proposed model was significantly faster to train and offered a more efficient memory usage with 83% fewer parameters than previously developed methods, owing to the adoption of the fire module. The proposed method was evaluated using the open-access series of imaging studies (OASIS) and the internet brain segmentation registry (IBSR) datasets. The experimental results demonstrate that the proposed SM-SegNet architecture achieves segmentation accuracies of 95% for cerebrospinal fluid, 95% for gray matter, and 96% for white matter, which outperforms the existing methods in both subjective and objective metrics in brain MRI segmentation.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…As shown in Figure 2 , we create uniform patch sizes

slices are extracted from the S slices in a constant interval of 3.…”

Section: Proposed Methodologymentioning

confidence: 99%

See 1 more Smart Citation

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

Yamanakkanavar

Choi

Lee

2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Most of the previous studies [8,11,34] use only a certain number of slices. In [11,34], the slices were selected alternately or only one slice was selected from a few slices.…”

Section: A Analysis and Comparison With Single Slice And Multiple Sli...mentioning

confidence: 99%

“…Most of the previous studies [8,11,34] use only a certain number of slices. In [11,34], the slices were selected alternately or only one slice was selected from a few slices. The purpose of predicting and training only a selected number of slices is to avoid repeating information from the neighboring slices since the 2D slices are similar to each other.…”

Section: A Analysis and Comparison With Single Slice And Multiple Sli...mentioning

confidence: 99%

SIP-UNet: Sequential Inputs Parallel UNet Architecture for segmentation of Brain Tissues from Magnetic Resonance Images

Prajapati¹

2022

Preprint

View full text Add to dashboard Cite

Our work introduces a novel architecture for extracting information from neighboring slices in the image segmentation. The Proposed architecture consists of parallel UNets for each slice/image. These UNets are fused using Residual Network for late fusion. We passed features from central slice only in the residual network so that the features from the image to be segmented will not be lost. We performed segmentation using this architecture on the brain Magnetic Resonance Images (MRI). The processed data is obtained from the Open Access Series of Imaging Studies (OASIS) dataset. Data of each subject is in 3D. We extracted 2D slices/images from each subject and train/test for each view (axial, coronal, sagittal). As the 3D data has neighboring slices, that are similar to each other, we hypothesize and considered before and after slices as neighboring slice for segmentation of central slice.

show abstract

Performance analysis of segmentation models to detect leaf diseases in tomato plant

Harnal

Gautam

Singh

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

A novel M-SegNet with global attention CNN architecture for automatic segmentation of brain MRI

Cited by 31 publications

References 33 publications

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

SIP-UNet: Sequential Inputs Parallel UNet Architecture for segmentation of Brain Tissues from Magnetic Resonance Images

Performance analysis of segmentation models to detect leaf diseases in tomato plant

Contact Info

Product

Resources

About