DEM super resolution is proposed in our previous publication to improve the resolution for a DEM on basis of some learning examples. Meanwhile, the nonlocal algorithm is introduced to deal with it and lots of experiments show that the strategy is feasible. In our publication, the learning examples are defined as the partial original DEM and their related high measurements due to this way can avoid the incompatibility between the data to be processed and the learning examples. To further extent the applications of this new strategy, the learning examples should be diverse and easy to obtain. Yet, it may cause the problem of incompatibility and unrobustness. To overcome it, we intend to investigate a convolutional neural network based method. The input of the convolutional neural network is a low resolution DEM and the output is expected to be its high resolution one. A three layers model will be adopted. The first layer is used to detect some features from the input, the second integrates the detected features to some compressed ones and the final step transforms the compressed features as a new DEM. According to this designed structure, some learning DEMs will be taken to train it. Specifically, the designed network will be optimized by minimizing the error of the output and its expected high resolution DEM. In practical applications, a testing DEM will be input to the convolutional neural network and a super resolution will be obtained. Many experiments show that the CNN based method can obtain better reconstructions than many classic interpolation methods.

Aim: To study the effect of pharmacological inhibition of epidermal growth factor receptor (EGFR) on intracranial aneurysm (IA) initiation.Methods: Human IA samples were analyzed for the expression of p‐EGFR and alpha smooth muscle actin (α‐SMA) by immunofluorescence (IF). Rat models of IA were established to evaluate the ability of the EGFR inhibitor, erlotinib, to attenuate the incidence of IA. We analyzed anterior cerebral artery tissues by pathological and proteomic detection for the expression of p‐EGFR and relevant proteins, and vessel casting was used to evaluate the incidence of aneurysms in each group. Rat vascular smooth muscle cells (VSMCs) and endothelial cells were extracted and used to establish an in vitro co‐culture model in a flow chamber with or without erlotinib treatment. We determined p‐EGFR and relevant protein expression in VSMCs by immunoblotting analysis.Results: Epidermal growth factor receptor activation was found in human IA vessel walls and rat anterior cerebral artery walls. Treatment with erlotinib markedly attenuated the incidence of IA by inhibiting vascular remodeling and pro‐inflammatory transformation of VSMC in rat IA vessel walls. Activation of EGFR in rat VSMCs and phenotypic modulation of rat VSMCs were correlated with the strength of shear stress in vitro, and treatment with erlotinib reduced phenotypic modulation of rat VSMCs. In vitro experiments also revealed that EGFR activation could be induced by TNF‐α in human brain VSMCs.Conclusions: These results suggest that EGFR plays a critical role in the initiation of IA and that the EGFR inhibitor erlotinib protects rats from IA initiation by regulating phenotypic modulation of VSMCs.

The quality of ultrasound image is a key information in medical related application. It is also an important index in evaluating the performance of ultrasonic imaging equipment and image processing algorithms. Yet, there is still no recognized quantitative standard about medical image quality assessment (IQA) due to the fact that IQA is traditionally regarded as a subjective issue, especially in case of the ultrasound medical images. As such, the medical ultrasound IQA on basis of convolutional neural network (CNN) is quantitatively studied in this paper. Firstly, a dataset with 1063 ultrasound images is established through degenerating a certain number of original high‐quality images. Subsequently, some operations are performed for the dataset including scoring and abnormal value screening. Then, 478 ultrasonic images are selected as the training and testing examples. The label of each example is obtained by averaging the scores of different doctors. Afterwards, a deep CNN network and a residuals network are taken to establish the IQA models. Meanwhile, the transfer learning strategy is introduced here to accelerate the training and improve the robustness of the model considering the fact that the ultrasound image samples are not abundant. At last, some tests are taken to evaluate the IQA models. They show that the CNN‐based IQA is feasible and effective.

Optical coherence tomography (OCT) images are usually degraded by significant speckle noise, which will strongly hamper their quantitative analysis. However, speckle noise reduction in OCT images is particularly challenging because of the difficulty in differentiating between noise and the information components of the speckle pattern. To address this problem, the spiking cortical model (SCM)-based nonlocal means method is presented. The proposed method explores self-similarities of OCT images based on rotation-invariant features of image patches extracted by SCM and then restores the speckled images by averaging the similar patches. This method can provide sufficient speckle reduction while preserving image details very well due to its effectiveness in finding reliable similar patches under high speckle noise contamination. When applied to the retinal OCT image, this method provides signal-to-noise ratio improvements of $>16dB$ with a small 5.4% loss of similarity.

How to automatically detect intracranial aneurysms from Three-Dimension Time of Flight Magnetic Resonance Angiography (3D TOF MRA) images is a typical 3D image classification problem. Currently, the commonly used method is the Maximum Intensity Projection- (MIP-) based way. It transfers 3D classification into 2D case by projecting the 3D patch into 2D planes along different directions on the basis of voxel’s intensity. After then, the 2D Convolutional Neural Network (CNN) is established to do classification. It has been shown that the MIP-based method can reduce the demands for the samples and increase the computation efficiency. Meanwhile, the accuracy is comparable with that of 3D image classification. Inspired by the strategy of MIP, we want to further reduce the demands for samples and accelerate the training by transferring the 2D image classification into 1D case, i.e., we want to generate the 1D vectors from the MIP images and then establish a 1D CNN to do intracranial aneurysm detection and classification for 3D TOF MRA image. Specifically, our method first extracts a series of patches as the Region of Interests (ROIs) along the blood vessels from the original 3D TOF MRA 3D image. The corresponding MIP images of each ROI will be obtained through maximum intensity projecting. Then, we generate a series of 1D vectors by accumulating each MIP image along different directions. Meanwhile, a 1D CNN is established to detect aneurysms, in which, the input is the obtained 1D vectors and the output is the binary classification result denoting whether there are intracranial aneurysms in the considered patch. Generally, compared with 2D- and 3D-CNN, the 1D CNN-based way greatly accelerates the training and shows stronger robustness in the case of fewer samples. The efficiency of the proposed method outperforms the 2D CNN about 10 times in CPU training. Yet, their accuracies are close.