Among numerous medical imaging modalities, diffusion weighted imaging (DWI) is extremely sensitive to acute ischemic stroke lesions, especially small infarcts. However, magnetic resonance imaging is time-consuming and expensive, and it is also prone to interference from metal implants. Therefore, the aim of this study is to design a medical image synthesis method based on generative adversarial network, Stroke-p2pHD, for synthesizing DWI images from computed tomography (CT). Stroke-p2pHD consisted of a generator that effectively fused local image features and global context information (Global_to_Local) and a multi-scale discriminator (M ²Dis). Specifically, in the Global_to_Local generator, a fully convolutional Transformer (FCT) and a local attention module (LAM) were integrated to achieve the synthesis of detailed information such as textures and lesions in DWI images. In the M ²Dis discriminator, a multi-scale convolutional network was adopted to perform the discrimination function of the input images. Meanwhile, an optimization balance with the Global_to_Local generator was ensured and the consistency of features in each layer of the M ²Dis discriminator was constrained. In this study, the public Acute Ischemic Stroke Dataset (AISD) and the acute cerebral infarction dataset from Yantaishan Hospital were used to verify the performance of the Stroke-p2pHD model in synthesizing DWI based on CT. Compared with other methods, the Stroke-p2pHD model showed excellent quantitative results (mean-square error = 0.008, peak signal-to-noise ratio = 23.766, structural similarity = 0.743). At the same time, relevant experimental analyses such as computational efficiency verify that the Stroke-p2pHD model has great potential for clinical applications.
Humans ; Tomography, X-Ray Computed/methods* ; Diffusion Magnetic Resonance Imaging/methods* ; Cerebral Infarction/diagnostic imaging* ; Stroke/diagnostic imaging* ; Neural Networks, Computer ; Image Processing, Computer-Assisted/methods* ; Algorithms

Objective To investigate the clinical characteristics and angiographic findings of cardiogenic shock(CS)following acute myocardial infarction(AMI) in elderly patients.Methods Between January 2015 and April 2016,we carried out a retrospective observational analysis of consecutive elderly patients in Tianjin Chest Hospital,who suffered CS-complicating AMI.Emergency angiography and percutaneous coronary intervention(PCI) were performed after admission.All selected patients were divided into CS and non-CS groups according to whether CS occurred.Electrocardiograph (ECG),cardiac enzyme testing,and ultrasound cardiography were performed after admission to monitor the occurrence of CS.Results The incidence of CS-complicating AMI was 8.33％ (34/408) in elderly patients.Among all CS patients enrolled,the aged patients accounted for 91.89 ％ (3 4/3 7).In-hospital mortality rate was 2 9.41 ％ (10/3 4).There were significant differences between two groups in WBC,H s-CRP,blood glucose,CR and ALT (t =2.403,4.596,6.778,6.109,each P＜0.05).The NT-Pro BNP level,the time of FMC,the frequency of left main and multivessel disease were higher in the CS group than in the non-CS group (each P ＜ 0.05).Conclusions Elderly patients are bearing high risk of CS following AMI.Prolonged FMC time and the presence of left main and/or multivessel lesion are independent risk factors for the development of CS.The optimal revascularisation strategy can improve the clinical outcome of patients with CS.