Objective To evaluate the accuracy of a novel echocardiographic three-dimensional automated software for the assessment of the aortic root in candidates for transcatheter aortic valve replacement(TAVR).Methods Four patterns(Lax,Lax-Res,Sax,Sax-Res) of 3D-TEE imaging of aortic root were gotten preoperatively in 18 patients with severe tricuspid aortic stenosis who were referred to our center for TAVR.The specialized 3D-TEE reconstruction software,eSie Valves,then automatically configured a geometric model of the aortic root from the images obtained by 3D-TEE and performed a quantitative analysis of these structures:the minimal diameter(Dmin),maximal diameter(Dmax),area and perimeter(Peri) of aortic annulus,height of the ostia of the left/right coronary artery above the aortic annulus(LOH/ROH).The echo dimensions were compared with the MDCT measurements.Results No statistically significant difference were found in above parameters between the ZOOM pattern (Sax-Res and Lax-Res) and CT measurements(all P>0.05).Lax-Res pattern measurements had good correlation with MDCT,with r valves of 0.81,0.77,0.89,0.84 for Lax-Res-Dmin,Lax-Res-Dmax,Lax-Res-Area,Lax-Res-Peri,respectively(all P<0.05).3D-TEE LOH/ROH had poor correlation with MDCT LOH/ROH (all r<0.7).Conclusions The new automatic 3D-TEE software allows modelling and quantifying the aortic annulus dimensions from 3D-TEE data in patients with tricuspid aortic valves,and Lax-Res pattern is recommended.Quantified assessment of LOH/ROH is not ideal and needs to be improved.

Objective:To evaluate the efficiency of ResNet50-OC model based on deep learning for multiple classification of color fundus photographs.Methods:The proprietary dataset (PD) collected in July 2018 in BenQ Hospital of Nanjing Medical University and EyePACS dataset were included.The included images were classified into five types of high quality, underexposure, overexposure, blurred edges and lens flare according to clinical ophthalmologists.There were 1 000 images (800 from EyePACS and 200 from PD) for each type in the training dataset and 500 images (400 from EyePACS and 100 from PD) for each type in the testing dataset.There were 5 000 images in the training dataset and 2 500 images in the testing dataset.All images were normalized and augmented.The transfer learning method was used to initialize the parameters of the network model, on the basis of which the current mainstream deep learning classification networks (VGG, Inception-resnet-v2, ResNet, DenseNet) were compared.The optimal network ResNet50 with best accuracy and Micro F1 value was selected as the main network of the classification model in this study.In the training process, the One-Cycle strategy was introduced to accelerate the model convergence speed to obtain the optimal model ResNet50-OC.ResNet50-OC was applied to multi-class classification of fundus image quality.The accuracy and Micro F1 value of multi-classification of color fundus photographs by ResNet50 and ResNet50-OC were evaluated.Results:The multi-classification accuracy and Micro F1 values of color fundus photographs of ResNet50 were significantly higher than those of VGG, Inception-resnet-v2, ResNet34 and DenseNet.The accuracy of multi-classification of fundus photographs in the ResNet50-OC model was 98.77% after 15 rounds of training, which was higher than 98.76% of the ResNet50 model after 50 rounds of training.The Micro F1 value of multi-classification of retinal images in ResNet50-OC model was 98.78% after 15 rounds of training, which was the same as that of ResNet50 model after 50 rounds of training.Conclusions:The proposed ResNet50-OC model can be accurate and effective in the multi-classification of color fundus photograph quality.One-Cycle strategy can reduce the frequency of training and improve the classification efficiency.

Aortic Valve Insufficiency ; Heart Valve Prosthesis ; Heart Valve Prosthesis Implantation ; Humans ; Transcatheter Aortic Valve Replacement

Objective:To propose and evaluate the cycle-constraint adversarial network (CycleGAN) for enhancing the low-quality fundus images such as the blurred, underexposed and overexposed etc.Methods:A dataset including 700 high-quality and 700 low-quality fundus images selected from the EyePACS dataset was used to train the image enhancement network in this study.The selected images were cropped and uniformly scaled to 512×512 pixels.Two generative models and two discriminative models were used to establish CycleGAN.The generative model generated matching high/low-quality images according to the input low/high-quality fundus images, and the discriminative model determined whether the image was original or generated.The algorithm proposed in this study was compared with three image enhancement algorithms of contrast limited adaptive histogram equalization (CLAHE), dynamic histogram equalization (DHE), and multi-scale retinex with color restoration (MSRCR) to perform qualitative visual assessment with clarity, BRISQUE, hue and saturation as quantitative indicators.The original and enhanced images were applied to the diabetic retinopathy (DR) diagnostic network to diagnose, and the accuracy and specificity were compared.Results:CycleGAN achieved the optimal results on enhancing the three types of low-quality fundus images including the blurred, underexposed and overexposed.The enhanced fundus images were of high contrast, rich colors, and with clear optic disc and blood vessel structures.The clarity of the images enhanced by CycleGAN was second only to the CLAHE algorithm.The BRISQUE quality score of the images enhanced by CycleGAN was 0.571, which was 10.2%, 7.3%, and 10.0% higher than that of CLAHE, DHE and MSRCR algorithms, respectively.CycleGAN achieved 103.03 in hue and 123.24 in saturation, both higher than those of the other three algorithms.CycleGAN took only 35 seconds to enhance 100 images, only slower than CLAHE.The images enhanced by CycleGAN achieved accuracy of 96.75% and specificity of 99.60% in DR diagnosis, which were higher than those of oringinal images.Conclusions:CycleGAN can effectively enhance low-quality blurry, underexposed and overexposed fundus images and improve the accuracy of computer-aided DR diagnostic network.The enhanced fundus image is helpful for doctors to carry out pathological analysis and may have great application value in clinical diagnosis of ophthalmology.

Objective To evaluate the value of preoperative assessment on transcatheter aortic valve implantation(TAVI) procedure with high-pitch dual-source computed tomography angiography (CTA).Methods Seventeen consecutive patients with severe symptomatic aortic stenosis underwent TAVI in our department from December 2012 to December 2013 were examined by 128-slice prospective ECG-triggered high-pitch spiral CTA and the clinical data were analyzed.Aortic annulus,sinus of Valsalva,sinotubular junction,ascending aorta and native leaflet to coronary ostium length were measured.Peripheral vascular access was evaluated.Then the patients were assessed on the suitability for TAVI procedure and prosthetic valve sizes.Results Mean diameter of the aortic annulus was (25.7 ± 2.0) mm,perimeter mean diameter was (26.4 ± 2.0) mm,area mean diameter was (25.4 ± 1.9) mm.Mean diameter of sinus of Valsalva was (34.0 ± 3.8) mm.Mean diameter of sinotubular junction was (30.5 ± 3.2) mm.Mean diameter of ascending aorta was(37.8 ± 2.8)mm.The length from native leaflet to left coronary ostium was (14.0 ± 2.0)mm,and the length from native leaflet to right coronary ostium was (15.9 ± 3.6)mm.Mean diameter of left iliac arteries was (7.5 ± 1.4) mm.Mean diameter of right iliac arteries was (7.4 ± 1.2) mm.Mean diameter of left femoral arteries was (7.4 ± 1.2) mm.Mean diameter of right femoral arteries was (7.3 ± 1.3) mm.One patient was considered ineligible for TAVI because of large aortic annulus diameter.Three patients died prior to TAVI.Two patients refused to undergo TAVI.Eleven patients underwent TAVI,26# prosthetic valve was implanted in 1 patient,29# prosthetic valve implanted in 6 patients,31 # prosthetic valve implanted in 4 patients.Prosthetic valve implantation was successful in 9 patients and only mild or trace perivalvular leakage was observed in these patients.Moderate perivalvular leakage were observed in 2 patients because of the location of implantation was too low,and perivalvular leakage was significantly reduced after re-implantation with same size prosthetic valve at a higher location.Conclusions CTA can be used to evaluate the aortic root anatomy and vascular access,and help to choose the right size of prosthetic valve.CTA has an important practical value in preoperative screening of TAVI procedure.

OBJECTIVETo assess the diagnostic value of dual energy CT for lymph node metastasis in patients with non-small cell lung cancer (NSCLC).

METHODSForty NSCLC patients, including 15 cases of squamous cell carcinoma and 25 cases of adenocarcinoma, underwent dual energy CT examination in pre-contrast and venous phase contrast scans, then the CT attenuation value of the lung cancer lesions and 85 mediastinal enlarged lymph nodes (the short diameter ≥ 5 mm, 53 metastatic and 32 non-metastatic) were measured at different energy levels (40-190 keV, spacing 10 keV) in venous phase contrast. CT spectral curves of the lung cancer lesions, hilus pulmonis and mediastinal enlarged lymph nodes were produced automatically, through comparing their CT spectral curves slope to judge whether or not the lymph nodes were metastatic. Receiver operating characteristic (ROC) curve was used to evaluate the efficiency of CT spectral curve in diagnosis of lymph node metastasis.

RESULTSThe CT spectral curves slopes of the lung cancer, metastatic lymph nodes and non-metastatic lymph nodes were 1.10±0.11, 1.08±0.07 and 1.54±0.17, respectively. There was no significant difference in curve slope between metastatic lymph nodes and lung cancer (=-1.32,>0.05); while there was significant difference between non-metastatic lymph nodes and lung cancer (=-2.58,<0.05). The CT spectral curve slope ratios of metastatic and non-metastatic lymph nodes to lung cancer were 0.98±0.05 and 1.40±0.12, respectively (=-2.86,<0.05). ROC curve showed that taking CT spectral curve slope ratio of 1.15 as cut-off value for the diagnosis of metastatic lymph nodes, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy were 81.1%, 87.5%, 91.5%, 73.7% and 83.5%, respectively.

CONCLUSIONSDual energy CT is of value in improving the diagnostic accuracy of lymph node metastasis in NSCLC patients before treatment.

The research on clinical high-risk for psychosis is a hotspot in recent years, which is helpful to the early identification and early intervention of psychosis. White matter fibers are the important structural basis of complex information transmission function among brain regions. The existing literatures show that there are abnormal white matter microstructures in individuals at clinical high-risk for psychosis, which is related to their clinical symptoms and social function. Diffusion tensor imaging is the only non-invasive technique to study the microstructure of brain white matter. This paper reviews the existing evidences of microstructural abnormalities of white matter at clinical high-risk for psychosis by diffusion tensor imaging, in order to comprehensively analyze the potential neurobiomarkers in the early stage of the disease and the pathological evolution characteristics in the development of the disease.