KEYWORDS: Image segmentation, Tumors, Brain, Semantics, Data modeling, Convolution, Magnetic resonance imaging, Medical imaging, Deep learning, Performance modeling
This paper designs a more efficient CNN (Convolutional Neural Network) architecture to extract more spatial features to solve this problem. A Double Channel Convolution(DCC) is designed using two multiple convolution modules to capture more spatial features and a residual module to prevent network performance degradation. The skip connection employs spatial and channel attention mechanisms for dual capturing of associations among global and local features between space and channel to enhance the correlation of features from modalities to modalities as well as the correlation judgment of Region of Interests (ROIs) and boundary information. The effectiveness of the network is verified by the experimental results with open access available dataset BraTS21, which shows that the Dice similarity coefficient (DSC) in the segmented brain tumors in the Enhance Tumor(ET),Tumor Core(TC) and the Whole Tumor(WT) were 0.832, 0.873 and 0.915, which are 1.2%, 1.16% and 2.2% higher than the DSC, JSC and Sensitivity of the U-Net model, respectively. The model size is reduced by 7.6 M. The experimental results show that the ALU-Net model proposed in this paper can achieve better performance and more computational efficient. The model showed good performance in automatic brain tumor segmentation.
During fault diagnosis of rolling bearings of rotating machinery in nuclear power plant, there are different data processing methods for original vibration signals, and different data processing methods have different diagnostic accuracy under the same diagnosis model. [Purpose] When the performance of the model is limited, in order to improve the diagnostic accuracy of the model, it is necessary to study the data processing method. [Methods] Therefore, the original vibration signal is processed into five ways: time-domain diagram(TD), time grayscale diagram(TGS), fast Fourier transform frequency-domain diagram(FFT), short-time Fourier transform time-frequency diagram(STFT) and continuous wavelet transform time-frequency diagram(CWT) for the initial feature extraction of the original vibration signal, and the five methods are compared and analyzed in the original data, data with added noise and data with less sample size. [Result] The experimental results show that the FFT data processing methods has a more obvious test accuracy under the noisy data and small sample size, and its accuracy is 1.9% and 6.7%(data under 50 sample size) higher than the suboptimal methods in both cases. [Conclusions] Therefore, in the case of noisy data and small sample size, the diagnostic performance of the model can be further improved by adopting the FFT data processing.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.