Multiscale attention guided U-Net architecture for cardiac segmentation in short-axis MRI images

Cui, Hengfei; Chang, Yu-Hern; Jiang, Lei; Xia, Yong; Zhang, Yanning

doi:10.1016/j.cmpb.2021.106142

Cited by 45 publications

(26 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…erefore, the next step is to try to improve the model by using unsupervised learning method while ensuring high precision segmentation effect. [23][24][25].…”

Section: Discussionmentioning

confidence: 99%

Research on Segmentation Method of Greening Landscape of Urban Community Based on Improved U-Net Network

Sui

2022

Security and Communication Networks

View full text Add to dashboard Cite

Aiming at the problem of low segmentation accuracy of greening landscape of urban community, a segmentation method of greening landscape of urban community based on improved U-Net network is proposed by adding an encoder on U-Net network. In addition, simulation is carried out on the remote sensing image data collected by GPRS network, and the effectiveness of the method is verified. The simulation results show that the result of proposed method is close to that of manual annotation. Compared with the traditional segmentation algorithm SVM and SegNet method, as well as the U-Net network before improvement, the proposed method has higher segmentation accuracy. The segmentation accuracy can reach up to 91%, the intersection ratio can reach 76%, and the mean pixel accuracy and mean intersection ratio can reach 89% and 74%, which indicates that the proposed method has certain validity and practicability.

show abstract

“…erefore, the next step is to try to improve the model by using unsupervised learning method while ensuring high precision segmentation effect. [23][24][25].…”

Section: Discussionmentioning

confidence: 99%

Research on Segmentation Method of Greening Landscape of Urban Community Based on Improved U-Net Network

Sui

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…The quantitative comparison of the LV segmentation results between the proposed model and other advanced methods is depicted in Table 7 . These methods include the attention U-Net architecture [ 32 ], convolutional neural network regression (CNR) method [ 50 ], FCN method [ 51 ], multi-scale FCN DenseNet [ 8 ], and a dynamic pixel-wise weighting-based FCN [ 15 ]. The detailed datasets and data preparation steps for these models are presented under the related work sections in Table 1 .…”

Section: Resultsmentioning

confidence: 99%

“…Several FCN-based models have been used to improve LV segmentation performance [ 29 , 30 , 31 ]. The network proposed by Cui et al [ 32 ] was an attention U-Net model based on an FCN structure for cardiac short-axis MRI segmentation. U-Net [ 24 ] has been commonly applied in medical image segmentation, particularly in the segmentation of cardiac images [ 25 , 33 , 34 ].…”

Section: Related Workmentioning

confidence: 99%

“…Pixel imbalance between the target class and the background class has a significant effect on segmentation performance, which requires an effective solution. Hence, various methods have been proposed to deal with this issue; for example, the focal Tversky loss function (FTL) was introduced by Cui et al [ 32 ], Dong et al [ 27 ] applied cross-entropy loss function instead of the dice loss function, and Wang et al [ 15 ] used dynamic pixel-wise (PW) weighting. In addition, the authors normalized the pixel intensity of the input images to improve the learning ability of the models.…”

Section: Related Workmentioning

confidence: 99%

“…In addition, the authors normalized the pixel intensity of the input images to improve the learning ability of the models. Cui et al [ 32 ] used mean–variance normalization (MVN) to normalize the pixel intensity on an input image by subtracting the difference from its average value and dividing by its standard deviation, and Wang et al [ 15 ] used min-max normalization. Based on the above literature, in this study we created a 2D FCN technique with fewer parameters for accurately segmenting the LV and myocardium from short-axis MRI images.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Left Ventricle Segmentation from Short-Axis Cardiac MRI Images Based on Fully Convolutional Neural Network

et al. 2022

View full text Add to dashboard Cite

Background: Left ventricle (LV) segmentation using a cardiac magnetic resonance imaging (MRI) dataset is critical for evaluating global and regional cardiac functions and diagnosing cardiovascular diseases. LV clinical metrics such as LV volume, LV mass and ejection fraction (EF) are frequently extracted based on the LV segmentation from short-axis MRI images. Manual segmentation to assess such functions is tedious and time-consuming for medical experts to diagnose cardiac pathologies. Therefore, a fully automated LV segmentation technique is required to assist medical experts in working more efficiently. Method: This paper proposes a fully convolutional network (FCN) architecture for automatic LV segmentation from short-axis MRI images. Several experiments were conducted in the training phase to compare the performance of the network and the U-Net model with various hyper-parameters, including optimization algorithms, epochs, learning rate, and mini-batch size. In addition, a class weighting method was introduced to avoid having a high imbalance of pixels in the classes of image’s labels since the number of background pixels was significantly higher than the number of LV and myocardium pixels. Furthermore, effective image conversion with pixel normalization was applied to obtain exact features representing target organs (LV and myocardium). The segmentation models were trained and tested on a public dataset, namely the evaluation of myocardial infarction from the delayed-enhancement cardiac MRI (EMIDEC) dataset. Results: The dice metric, Jaccard index, sensitivity, and specificity were used to evaluate the network’s performance, with values of 0.93, 0.87, 0.98, and 0.94, respectively. Based on the experimental results, the proposed network outperforms the standard U-Net model and is an advanced fully automated method in terms of segmentation performance. Conclusion: This proposed method is applicable in clinical practice for doctors to diagnose cardiac diseases from short-axis MRI images.

show abstract

NVTrans‐UNet: Neighborhood vision transformer based U‐Net for multi‐modal cardiac MR image segmentation

Zhao

2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

With the rapid development of artificial intelligence and image processing technology, medical imaging technology has turned into a critical tool for clinical diagnosis and disease treatment. The extraction and segmentation of the regions of interest in cardiac images are crucial to the diagnosis of cardiovascular diseases. Due to the erratically diastolic and systolic cardiac, the boundaries of Magnetic Resonance (MR) images are quite fuzzy. Moreover, it is hard to provide complete information using a single modality due to the complex structure of the cardiac image. Furthermore, conventional CNN-based segmentation methods are weak in feature extraction. To overcome these challenges, we propose a multi-modal method for cardiac image segmentation, called NVTrans-UNet. Firstly, we employ the Neighborhood Vision Transformer (NVT) module, which takes advantage of Neighborhood Attention (NA) and inductive biases. It can better extract the local information of the cardiac image as well as reduce the computational cost. Secondly, we introduce a Multi-modal Gated Fusion (MGF) network, which can automatically adjust the contributions of different modal feature maps and make full use of multi-modal information. Thirdly, the bottleneck layer with Atrous Spatial Pyramid Pooling (ASPP) is proposed to expand the feature receptive field. Finally, the mixed loss is added to the cardiac image to focus the fuzzy boundary and realize accurate segmentation. We evaluated our model on MyoPS 2020 dataset. The Dice score of myocardial infarction (MI) was 0.642 ± 0.171, and the Dice score of myocardial infarction + edema (MI + ME) was 0.574 ± 0.110. Compared with the baseline, the MI increases by 11.2%, and the MI + ME increases by 12.5%. The results show the effectiveness of the proposed NVTrans-UNet in the segmentation of MI and ME.

show abstract

Multiscale attention guided U-Net architecture for cardiac segmentation in short-axis MRI images

Cited by 45 publications

References 27 publications

Research on Segmentation Method of Greening Landscape of Urban Community Based on Improved U-Net Network

Research on Segmentation Method of Greening Landscape of Urban Community Based on Improved U-Net Network

Automatic Left Ventricle Segmentation from Short-Axis Cardiac MRI Images Based on Fully Convolutional Neural Network

NVTrans‐UNet: Neighborhood vision transformer based U‐Net for multi‐modal cardiac MR image segmentation

Contact Info

Product

Resources

About