摘要 :
The kaolinite-mullite reaction series of eight kaolin samples have been studied with XRD, IR, DTA and MAS NMR spectra. The acquired results clearly show that the evolution of 29Si and " Al spectra of the various samples may differ...
展开
The kaolinite-mullite reaction series of eight kaolin samples have been studied with XRD, IR, DTA and MAS NMR spectra. The acquired results clearly show that the evolution of 29Si and " Al spectra of the various samples may differ from each other significantly. In the metakaolinite studied, the Al is universally present and it appears as a sign of the variation of the structure and some properties of the metakaoliuites. It can be suggested from many experimental results that the high-temperatural phase occurring after the exothermal peak should be y -AI2O3 rather than Al-Si spinel, and the mullite-formation path in the studied samples involve two steps: first, the primary mullite farmed directly from the metakaolinite around 850 °C; Second step, the secondary mullite developped extensively by reaction between segregated SiO2 and y -AI2O3 at about 1200-1300 "C and the composition or/and structure of secondary mullite may be visibly different depending on the content of the impurity mica minerals.
收起
摘要 :
Deep neural network methods have led to impressive breakthroughs in the medical image field. Most of them focus on single-modal data, while diagnoses in clinical practice are usually determined based on multi-modal data, especiall...
展开
Deep neural network methods have led to impressive breakthroughs in the medical image field. Most of them focus on single-modal data, while diagnoses in clinical practice are usually determined based on multi-modal data, especially for tumor diseases. In this paper, we intend to find a way to effectively fuse radiology images and pathology images for the diagnosis of gliomas. To this end, we propose a collaborative attention network (CA-Net), which consists of three attention-based feature fusion modules, multi-instance attention, cross attention, and attention fusion. We first take an individual network for each modality to extract the original features. Multi-instance attention combines different informative patches in the pathology image to form a holistic pathology feature. Cross attention interacts between the two modalities and enhances single modality features by exploring complementary information from the other modality. The cross attention matrixes imply the feature reliability, so they are further utilized to obtain a coefficient for each modality to linearly fuse the enhanced features as the final representation in the attention fusion module. The three attention modules are collaborative to discover a comprehensive representation. Our result on the CPM-RadPath outperforms other fusion methods by a large margin, which demonstrates the effectiveness of the proposed method.
收起
摘要 :
The principal-agent relationship between enterprise as the permanent organization and project as the temporary organization is the fundamental obstacle of knowledge management in construction enterprises. To deal with it, proper i...
展开
The principal-agent relationship between enterprise as the permanent organization and project as the temporary organization is the fundamental obstacle of knowledge management in construction enterprises. To deal with it, proper information and communication systems should be constructed and an agreement on knowledge management activities be reached. The project management office (PMO) is set up to release the contradiction between the enterprise organization and the project organization. Gradual revolution on organization structure of construction enterprise should make to reach the demand of knowledge management. Firstly, the structure should keep knowledge communication and share open. Secondly, knowledge management activities can be carried out conveniently under the structure. Lastly, knowledge characteristics should be integrated into structure reform.
收起
摘要 :
The principal-agent relationship between enterprise as the permanent organization and project as the temporary organization is the fundamental obstacle of knowledge management in construction enterprises. To deal with it, proper i...
展开
The principal-agent relationship between enterprise as the permanent organization and project as the temporary organization is the fundamental obstacle of knowledge management in construction enterprises. To deal with it, proper information and communication systems should be constructed and an agreement on knowledge management activities be reached. The project management office (PMO) is set up to release the contradiction between the enterprise organization and the project organization. Gradual revolution on organization structure of construction enterprise should make to reach the demand of knowledge management. Firstly, the structure should keep knowledge communication and share open. Secondly, knowledge management activities can be carried out conveniently under the structure. Lastly, knowledge characteristics should be integrated into structure reform.
收起
摘要 :
Gliomas are the most common and severe malignant tumors of the brain. The diagnosis and grading of gliomas are typically based on MRI images and pathology images. To improve the diagnosis accuracy and efficiency, we intend todesig...
展开
Gliomas are the most common and severe malignant tumors of the brain. The diagnosis and grading of gliomas are typically based on MRI images and pathology images. To improve the diagnosis accuracy and efficiency, we intend todesign a framework for computer-aided diagnosis combining the two modalities. Without loss of generality, we first take an individual network for each modality to get the features and fuse them to predict the subtype of gliomas. For MRI images, we directly take a 3D-CNN to extract features, supervised by a cross-entropy loss function. There are too many normal regions in abnormal whole slide pathology images (WSI), which affect the training of pathology features. We call these normal regions as noise regions and propose two ideas to reduce them. Firstly, we introduce a nucleus segmentation model trained on some public datasets. The regions that has a small number of nuclei are excluded in the subsequent training of tumor classification. Secondly, we take a noise-rank module to further suppress the noise regions. After the noise reduction, we train a gliomas classification model based on the rest regions and obtain the features of pathology images. Finally, we fuse the features of the two modalities by a linear weighted module. We evaluate the proposed framework on CPM-RadPath2020 and achieve the first rank on the validation set.
收起
摘要 :
Gliomas are the most common and severe malignant tumors of the brain. The diagnosis and grading of gliomas are typically based on MRI images and pathology images. To improve the diagnosis accuracy and efficiency, we intend todesig...
展开
Gliomas are the most common and severe malignant tumors of the brain. The diagnosis and grading of gliomas are typically based on MRI images and pathology images. To improve the diagnosis accuracy and efficiency, we intend todesign a framework for computer-aided diagnosis combining the two modalities. Without loss of generality, we first take an individual network for each modality to get the features and fuse them to predict the subtype of gliomas. For MRI images, we directly take a 3D-CNN to extract features, supervised by a cross-entropy loss function. There are too many normal regions in abnormal whole slide pathology images (WSI), which affect the training of pathology features. We call these normal regions as noise regions and propose two ideas to reduce them. Firstly, we introduce a nucleus segmentation model trained on some public datasets. The regions that has a small number of nuclei are excluded in the subsequent training of tumor classification. Secondly, we take a noise-rank module to further suppress the noise regions. After the noise reduction, we train a gliomas classification model based on the rest regions and obtain the features of pathology images. Finally, we fuse the features of the two modalities by a linear weighted module. We evaluate the proposed framework on CPM-RadPath2020 and achieve the first rank on the validation set.
收起
摘要 :
Faced with the enhanced resource and environmental constraints increasingly, the relationship between the public projects and ecological environment should be focused to achieve the sustainable development of public projects. Firs...
展开
Faced with the enhanced resource and environmental constraints increasingly, the relationship between the public projects and ecological environment should be focused to achieve the sustainable development of public projects. Firstly, the concept of public projects ecosystem is explained from the perspective of ecology, then the composition, structure and characteristics of the public projects ecosystem are analyzed. Furthermore, the co-evolution of public projects ecosystem is defined and analyzed, and the co-evolution mechanism between the public projects and ecological environment is clarified. Finally, the co-evolution model of the public project ecosystem is determined on the basis of the strength degree of the interaction between public projects and ecology environment.
收起
摘要 :
Faced with the enhanced resource and environmental constraints increasingly, the relationship between the public projects and ecological environment should be focused to achieve the sustainable development of public projects. Firs...
展开
Faced with the enhanced resource and environmental constraints increasingly, the relationship between the public projects and ecological environment should be focused to achieve the sustainable development of public projects. Firstly, the concept of public projects ecosystem is explained from the perspective of ecology, then the composition, structure and characteristics of the public projects ecosystem are analyzed. Furthermore, the co-evolution of public projects ecosystem is defined and analyzed, and the co-evolution mechanism between the public projects and ecological environment is clarified. Finally, the co-evolution model of the public project ecosystem is determined on the basis of the strength degree of the interaction between public projects and ecology environment.
收起
摘要 :
The state-of-the-art methods of Magnetic Resonance Imaging (MRI) denoising technologies have improved significantly in t,he past, decade, particularly those based in deep learning. However, the major issues in deep learning based ...
展开
The state-of-the-art methods of Magnetic Resonance Imaging (MRI) denoising technologies have improved significantly in t,he past, decade, particularly those based in deep learning. However, the major issues in deep learning based denoising algorithms is both that the model architectures are not built for the complex noise distributions inherent in MRI, and that the data given to these algorithms is typically synthetic, and thus, they fail to generalize to spatially variant noise distributions. The noise varies greatly dependent upon such factors as pulse sequence of the MRI sequence, reconstruction method, coil configuration, physiological activities, etc. To overcome these issues, we have created HydraNet, a multi-branch deep neural network architecture that learns to denoise MR images at a multitude of noise levels, and which has critically been trained using only real image pairs of high and low signal-to-noise ratio (SNR) images. We prove the superiority of HydraNet at denoising complex noise distributions in comparison to the leading deep learning method in our experimentation, in addition to non-local collaborative filtering-based methods, quantitatively in both Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM), and qualitatively upon inspection of denoised MRI samples.
收起
摘要 :
The state-of-the-art methods of Magnetic Resonance Imaging (MRI) denoising technologies have improved significantly in t,he past, decade, particularly those based in deep learning. However, the major issues in deep learning based ...
展开
The state-of-the-art methods of Magnetic Resonance Imaging (MRI) denoising technologies have improved significantly in t,he past, decade, particularly those based in deep learning. However, the major issues in deep learning based denoising algorithms is both that the model architectures are not built for the complex noise distributions inherent in MRI, and that the data given to these algorithms is typically synthetic, and thus, they fail to generalize to spatially variant noise distributions. The noise varies greatly dependent upon such factors as pulse sequence of the MRI sequence, reconstruction method, coil configuration, physiological activities, etc. To overcome these issues, we have created HydraNet, a multi-branch deep neural network architecture that learns to denoise MR images at a multitude of noise levels, and which has critically been trained using only real image pairs of high and low signal-to-noise ratio (SNR) images. We prove the superiority of HydraNet at denoising complex noise distributions in comparison to the leading deep learning method in our experimentation, in addition to non-local collaborative filtering-based methods, quantitatively in both Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM), and qualitatively upon inspection of denoised MRI samples.
收起