SCANeXt: Enhancing 3D medical image segmentation with dual attention network and depth-wise convolution

Liu, Yajun; Zhang, Zenghui; Yue, Jiang; Guo, Weiwei

doi:10.1016/j.heliyon.2024.e26775

Cited by 2 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 , inspired by the dual attention mechanism presented in Refs. [ 31 , 33 ], the conventional channel attention has been extended into a more sophisticated Layer-Channel Attention. Specifically, the input feature maps, denoted as

, are sequentially passed through Channel Attention and Layer Attention, processing the features along the channel and layer dimensions.…”

Section: Methodsmentioning

confidence: 99%

“…(b) In MRIs, tumors occupy a small spatial proportion, and the networks, while extracting large amounts of irrelevant background information, might overshadow critical semantic features of tumors, affecting the ability to differentiate details between tumors and normal tissues. In such cases, attention mechanisms that target specific regions become the key to addressing this issue [ 30 , 31 ].…”

Section: Introductionmentioning

confidence: 99%

“…This design significantly expands the model's receptive field, enabling it to adapt to variations in tumor shape and size within slices and volumetric spaces, and enhances its ability to identify and process blurred boundaries. Thirdly, leveraging the concept of the dual attention mechanism [ 31 , 33 ], the Layer-Channel Attention module is proposed to focus on slices and channels that are closely related to tumors, while effectively suppressing background noise and interfering signals from lesion-free tissues, thus enhancing the detailed differentiation between tumors and normal tissues. The contributions of this study are as follows.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel LVPA-UNet network for target volume automatic delineation: An MRI case study of nasopharyngeal carcinoma

Zhang,

Xu,

Wen

et al. 2024

Heliyon

View full text Add to dashboard Cite

, are sequentially passed through Channel Attention and Layer Attention, processing the features along the channel and layer dimensions.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel LVPA-UNet network for target volume automatic delineation: An MRI case study of nasopharyngeal carcinoma

Zhang,

Xu,

Wen

et al. 2024

Heliyon

View full text Add to dashboard Cite

MFHARFNet: multi-branch feature hybrid and adaptive receptive field network for image segmentation

Li,

Yun,

Jiang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Accurate segmentation of medical images is crucial for disease diagnosis and understanding disease changes. Deep learning methods, utilizing encoder-decoder structures, have demonstrated cutting-edge performance in various medical image segmentation tasks. However, the pooling operation in the encoding stage results in feature loss, which makes the network lack the ability to fuse multi-scale information at different levels, hinders its effective perception of multi-scale information, and leads to poor segmentation performance. Drawing inspiration from the U-shaped network, this study introduces a multi-branch feature hybrid attention and adaptive receptive field network (MFHARFNet) for medical image segmentation. Building upon the encoder-decoder framework, we initially devise a multi-branch feature hybrid attention module (MFHAM) to seamlessly integrate feature maps of varying scales, capturing both fine-grained features and coarse-grained semantics across the entire scale. Furthermore, we redesign the skip connection to amalgamate feature information from different branches in the encoder stage and efficiently transmit it to the decoder, providing the decoder with global context feature maps at different levels. Finally, the adaptive receptive field (ARF) module is introduced in the decoder feature reconstruction stage to adapt and focus on related fields, ensuring the model's adaptation to different segmentation target features, and achieving different weights for the output of different convolution kernels to improve segmentation performance. We comprehensively evaluate our method on medical image segmentation tasks, by using four public datasets across CT and MRI. Remarkably, MFHARFNet method consistently outperforms other state-of-the-art methods, exceeding UNet by 2.1%, 0.9%, 6.6% and 1.0% on Dice on ATLAS, LiTs, BraTs2019 and Spine and intervertebral disc datasets, respectively. In addition, MFHARFNet minimizes network parameters and computational complexity as much as possible. The source codes are in https://github.com/OneHundred99/MFHARFNet.

show abstract

SCANeXt: Enhancing 3D medical image segmentation with dual attention network and depth-wise convolution

Cited by 2 publications

References 56 publications

A novel LVPA-UNet network for target volume automatic delineation: An MRI case study of nasopharyngeal carcinoma

A novel LVPA-UNet network for target volume automatic delineation: An MRI case study of nasopharyngeal carcinoma

MFHARFNet: multi-branch feature hybrid and adaptive receptive field network for image segmentation

Contact Info

Product

Resources

About