With the development of deep neural networks (DNN), building visual decoding models based on functional magnetic resonance imaging (fMRI) to simulate the visual system of the human brain and studying visual mechanisms have become a research hotspot. Although existing visual decoding models built using DNNs have achieved a certain accuracy, most models ignore the differences between different voxels. Among them, the BRNN-based category decoding model uses the bidirectional long short term memory (LSTM) network to simulate the visual bidirectional information flow, which improves the decoding accuracy, but it uses the voxels of each brain area as an overall input model. Therefore, we embed the channel attention module, the Squeeze-and-Excitation Networks (SENet), into the LSTM network to construct an LSTM-SENet vision that introduces an attention mechanism The decoding model allows the model to learn by itself and assign different weights to each voxel, focusing on important voxels, thereby improving the classification accuracy of natural images. The experimental results show that our method improves the accuracy of (three-level) category decoding than other methods, and the results further verify the effectiveness of building a visual decoding model based on the visual mechanism.
Limited-angle computed tomography (CT) image reconstruction is a challenging reconstruction problem in the fields of CT. With the development of deep learning, the generative adversarial network (GAN) perform well in image restoration by approximating the distribution of training sample data. In this paper, we proposed an effective GAN-based inpainting method to restore the missing sinogram data for limited-angle scanning. To estimate the missing data, we design the generator and discriminator of the patch-GAN and train the network to learn the data distribution of the sinogram. We obtain the reconstructed image from the restored sinogram by filtered back projection and simultaneous algebraic reconstruction technique with total variation. Experimental results show that serious artifacts caused by missing projection data can be reduced by the proposed method, and it is hopeful to solve the reconstruction problem of 60° limited scanning angle.
The improvement of computed tomography (CT) image resolution is beneficial to the subsequent medical diagnosis, but it is usually limited by the scanning devices and great expense. Convolutional neural network (CNN)- based methods have achieved promising ability in super-resolution. However, existing methods mainly focus on the super-resolution of reconstructed image and do not fully explored the approach of super-resolution from projectiondomain. In this paper, we studied the characteristic of projection and proposed a CNN-based super-resolution method to establish the mapping relationship of low- and high-resolution projection. The network label is high-resolution projection and the input is its corresponding interpolation data after down sampling. FDK algorithm is utilized for three-dimensional image reconstruction and one slice of reconstruction image is taken as an example to evaluate the performance of the proposed method. Qualitative and quantitative results show that the proposed method is potential to improve the resolution of projection and enables the reconstructed image with higher quality.
With the development of technology, the traditional X-ray CT can’t meet the modern medical and industry needs for component distinguish and identification. This is due to the inconsistency of X-ray imaging system and reconstruction algorithm. In the current CT systems, X-ray spectrum produced by X-ray source is continuous in energy range determined by tube voltage and energy filter, and the attenuation coefficient of object is varied with the X-ray energy. So the distribution of X-ray energy spectrum plays an important role for beam-hardening correction, dual energy CT image reconstruction or dose calculation. However, due to high ill-condition and ill-posed feature of system equations of transmission measurement data, statistical fluctuations of X ray quantum and noise pollution, it is very hard to get stable and accurate spectrum estimation using existing methods. In this paper, a model-based X-ray energy spectrum estimation method from CT scanning data with energy spectrum filter is proposed. First, transmission measurement data were accurately acquired by CT scan and measurement using phantoms with different energy spectrum filter. Second, a physical meaningful X-ray tube spectrum model was established with weighted gaussian functions and priori information such as continuity of bremsstrahlung and specificity of characteristic emission and estimation information of average attenuation coefficient. The parameter in model was optimized to get the best estimation result for filtered spectrum. Finally, the original energy spectrum was reconstructed from filtered spectrum estimation with filter priori information. Experimental results demonstrate that the stability and accuracy of X ray energy spectrum estimation using the proposed method are improved significantly.
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.