MLKCA-Unet: Multiscale large-kernel convolution and attention in Unet for spine MRI segmentation

Wang, Biao; Qin, Juan; Lv, Lianrong; Cheng, Mengdan; Li, Lei; Xia, Dan; Wang, Shike

doi:10.1016/j.ijleo.2022.170277

Cited by 13 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An attention module enhances important features and suppresses unimportant features to improve the representational ability of the network [27,28,40,41]. In order to effectively combine the global features extracted by Transformer with the local features extracted by the U-Net encoder, we design an attention mechanism to fuse the features of the two branches.…”

Section: Attention Branching Fusion Modulementioning

confidence: 99%

UTAC-Net: A Semantic Segmentation Model for Computer-Aided Diagnosis for Ischemic Region Based on Nuclear Medicine Cerebral Perfusion Imaging

Li,

Zhang

2024

Electronics

View full text Add to dashboard Cite

Cerebral ischemia has a high morbidity and disability rate. Clinical diagnosis is mainly made by radiologists manually reviewing cerebral perfusion images to determine whether cerebral ischemia is present. The number of patients with cerebral ischemia has risen dramatically in recent years, which has brought a huge workload for radiologists. In order to improve the efficiency of diagnosis, we develop a neural network for segmenting cerebral ischemia regions in perfusion images. Combining deep learning with medical imaging technology, we propose a segmentation network, UTAC-Net, based on U-Net and Transformer, which includes a contour-aware module and an attention branching fusion module, to achieve accurate segmentation of cerebral ischemic regions and correct identification of ischemic locations. Cerebral ischemia datasets are scarce, so we built a relevant dataset. The results on the self-built dataset show that UTAC-Net is superior to other networks, with the mDice of UTAC-Net increasing by 9.16% and mIoU increasing by 14.06% compared with U-Net. The output results meet the needs of aided diagnosis as judged by radiologists. Experiments have demonstrated that our algorithm has higher segmentation accuracy than other algorithms and better assists radiologists in the initial diagnosis, thereby reducing radiologists’ workload and improving diagnostic efficiency.

show abstract

Section: Attention Branching Fusion Modulementioning

confidence: 99%

UTAC-Net: A Semantic Segmentation Model for Computer-Aided Diagnosis for Ischemic Region Based on Nuclear Medicine Cerebral Perfusion Imaging

Li,

Zhang

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…For coarse blood vessels, the distance between target pixels is remote due to their large size. To acquire long-range contextual information with lower computational overhead, group convolution (GConv) with a large kernel [44] is used in the coarse branch. However, for fine vessels, using a large convolution kernel may introduce unnecessary background information and noise, resulting in the loss of capillary details.…”

Section: Coarse and Fine Feature Aggregationmentioning

confidence: 99%

CMP-UNet: A Retinal Vessel Segmentation Network Based on Multi-Scale Feature Fusion

Gu,

Cao,

Wang

et al. 2023

Electronics

View full text Add to dashboard Cite

Retinal vessel segmentation plays a critical role in the diagnosis and treatment of various ophthalmic diseases. However, due to poor image contrast, intricate vascular structures, and limited datasets, retinal vessel segmentation remains a long-term challenge. In this paper, based on an encoder–decoder framework, a novel retinal vessel segmentation model called CMP-UNet is proposed. Firstly, the Coarse and Fine Feature Aggregation module decouples and aggregates coarse and fine vessel features using two parallel branches, thus enhancing the model’s ability to extract features for vessels of various sizes. Then, the Multi-Scale Channel Adaptive Fusion module is embedded in the decoder to realize the efficient fusion of cascade features by mining the multi-scale context information from these features. Finally, to obtain more discriminative vascular features and enhance the connectivity of vascular structures, the Pyramid Feature Fusion module is proposed to effectively utilize the complementary information of multi-level features. To validate the effectiveness of the proposed model, it is evaluated on three publicly available retinal vessel segmentation datasets: CHASE_DB1, DRIVE, and STARE. The proposed model, CMP-UNet, reaches F1-scores of 82.84%, 82.55%, and 84.14% on these three datasets, with improvements of 0.76%, 0.31%, and 1.49%, respectively, compared with the baseline. The results show that the proposed model achieves higher segmentation accuracy and more robust generalization capability than state-of-the-art methods.

show abstract

“…However, given that the extracted multimodal features vary in importance, it is necessary to consider the weight effect, so many scholars have introduced an attention mechanism in the part of the jump connection to emphasize the key features and weaken the redundant features [20,21], to improve the validity and reliability of the model. Wang et al [22] proposed a multi-scale convolutional kernel UNet network for pattern recognition by adding a CBAM attention mechanism to the jump connection section. Dhiraj et al [23] proposed an attention ResUNet to automatically segment critical images by adding attention gates to the jump connection part and filtering redundant features.…”

Section: Introductionmentioning

confidence: 99%

Intelligent fault diagnosis of rolling bearings under small samples based on lightweight UNet with attention-fused residual block

Sun,

Ding,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In rotating machinery, rolling bearings are crucial, and their failure can lead to severe acci-dents and economic losses. Therefore, fault diagnosis of bearings is necessary to maintain the safe and stable operation of modern machinery and equipment. Currently, data-driven intelligent diagnosis methods are mainstream; however, in practical applications, problems such as insuffi-cient fault samples and strong interference signals often exist. At the same time, a large number of edge-end and mobile devices put higher requirements for the size of the diagnostic model. This study addresses these issues by proposing a lightweight UNet (LWUNet) model, which integrates wavelet packet decomposition (WPD) and attention-fused residual block (AFRB) for fault diag-nosis in rolling bearings under varying operating conditions, particularly for small sample sizes. Firstly, WPD is used to decompose and reconstruct the fault signal to achieve effective denoising. Secondly, a lightweight UNet network (LW-UNet) is constructed for pixel-level feature learning to reduce the number of parameters and improve the accuracy rate. Thereafter, to further enhance the model feature extraction capability, the attention-fused residual block is proposed and em-bedded into the LWUNet to develop the AFRB-LWUNet model. Finally, the reconstructed signals are input to the proposed model for training, and the model performance is examined using a test set. The proposed method is compared with other fault diagnosis models using small sample data of rolling bearings from the Case Western Reserve University (CWRU), USA and the University of Paderborn, Germany. The results confirm the higher recognition accuracy, stronger generaliza-tion ability, and robustness of the proposed method for small samples under various working conditions and intense noise.

show abstract

MLKCA-Unet: Multiscale large-kernel convolution and attention in Unet for spine MRI segmentation

Cited by 13 publications

References 22 publications

UTAC-Net: A Semantic Segmentation Model for Computer-Aided Diagnosis for Ischemic Region Based on Nuclear Medicine Cerebral Perfusion Imaging

UTAC-Net: A Semantic Segmentation Model for Computer-Aided Diagnosis for Ischemic Region Based on Nuclear Medicine Cerebral Perfusion Imaging

CMP-UNet: A Retinal Vessel Segmentation Network Based on Multi-Scale Feature Fusion

Intelligent fault diagnosis of rolling bearings under small samples based on lightweight UNet with attention-fused residual block

Contact Info

Product

Resources

About