Timely and accurate auxiliary diagnosis of intracranial aneurysm can help radiologist make treatment plans quickly, saving lives and cutting costs at the same time. At present Digital Subtraction Angiography (DSA) is the gold standard for the diagnosis of intracranial aneurysm, but as radiologists interpret those imaging sequences frame by frame, misdiagnosis might occur. The utilization of computer-assisted diagnosis (CAD) can ease the burdens of radiologists and improve the detection accuracy of aneurysms. In this paper, a deep learning method is applied to detect the intracranial aneurysm in 3D Rotational Angiography (3D-RA) based on a spatial information fusion (SIF) method, and in stead of 3D vascular model, 2D image sequences are used. Given the intracranial aneurysm and vascular overlap having similar feature in the most time, rather than focusing on distinguishing them in one frame, the morphological differences between frames are considered as major feature. In the training data, consecutive frames of every imaging time series are extracted and concatenated in a specific way, so that the spatial contextual information could be embedded into a single twodimensional image. This method enables the time series with obvious correlation between frames be directly trained on 2D convolutional neural network (CNN), instead of 3D-CNN with huge computational cost. Finally, we got an accuracy of 98.89%, with sensitivity and specificity of 99.38% and 98.19% respectively, which proves the feasibility and availability of the SIF feature.

Purpose.: To explore the regulation of inducible nitric oxide synthase (iNOS) expression by nuclear factor kappa B (NF-κB) in human lens epithelial cells (LECs) treated with high levels of glucose, and to elucidate the impact of this in the pathogenesis of cataracts associated with diabetes. Methods.: LECs (SRA01/04) were cultured in vitro. NF-κB nuclear translocation and iNOS expression were measured at different glucose concentrations and at various time points, and the optimal concentration for detecting changes in the patterns of NF-κB nuclear translocation and iNOS expression was chosen. As a specific NF-κB inhibitor, pyrrolidine dithiocarbamate (PDTC) was used to assess the effect of inhibiting NF-κB. Western blotting and inverted fluorescence microscopy were used to monitor the nuclear translocation of NF-κB. PCR and Western blotting were used to measure iNOS expression. Using the University of California, Santa Cruz database and the TFSEARCH program, we searched the DNA sequence upstream of iNOS for the core binding sequence for NF-κB. Chromatin immunoprecipitation (ChIP) was used to measure the binding of NF-κB. Results.: The nuclear translocation of NF-κB was measured upon glucose treatment, and the concentration of NF-κB in the nucleus was found to peak at 25 to 30 minutes of treatment with 25 mM glucose. iNOS mRNA and protein levels also increased significantly in a time- and concentration-dependent manner and iNOS mRNA and protein reached their peak values after 8 hours of treatment with 25 mM glucose. The binding of NF-κB to the promoter of the iNOS gene was enhanced in the 25 mM glucose group compared with the 5.5 mM glucose group or the 25 mM glucose + 100 μL PDTC group, and this difference was statistically significant (P < 0.05). Conclusions.: NF-κB regulates iNOS expression in a time- and concentration-dependent manner. Under high glucose conditions, NF-κB is activated and rapidly translocates to the nucleus, leading to increased binding to the iNOS promoter and a consequent increase in iNOS expression. The findings of this study provide important experimental evidence that clarifies the pathogenesis of cataracts associated with diabetes and contributes to the search for therapeutic targets of these cataracts.