Membranous nephropathy is one of the most prevalent conditions responsible for nephrotic syndrome in adults. It is clinically nonspecific and mainly diagnosed by kidney biopsy pathology, with three prevalent techniques: light microscopy, electron microscopy, and immunofluorescence microscopy. Manual observation of glomeruli one by one under the microscope is very time-consuming, and there are certain differences in the observation results between physicians. This study makes use of whole-slide images scanned by a light microscope as well as immunofluorescence images to classify patients with membranous nephropathy. The framework mainly includes a glomerular segmentation module, a confidence coefficient extraction module, and a multi-modal fusion module. This framework first identifies and segments the glomerulus from whole-slide images and immunofluorescence images, and then a glomerular classifier is trained to extract the features of each glomerulus. The results are then combined to produce the final diagnosis. The results of the experiments show that the F1-score of image classification results obtained by combining two kinds of features, which can reach 97.32%, is higher than those obtained by using only light-microscopy-observed images or immunofluorescent images, which reach 92.76% and 93.20%, respectively. Experiments demonstrate that considering both WSIs and immunofluorescence images is effective in improving the diagnosis of membranous nephropathy.

Background and Objective: Detecting urine red blood cells (U-RBCs) is an important operation in diagnosing nephropathy. Existing U-RBC detection methods usually employ single-focus images to implement such tasks, which inevitably results in false positives and missed detections due to the abundance of defocused U-RBCs in the single-focus images. Meanwhile, the current diabetic nephropathy diagnosis methods heavily rely on artificially setting a threshold to detect the U-RBC proportion, whose accuracy and robustness are still supposed to be improved. Methods: To overcome these limitations, a novel multi-focus video dataset in which the typical shape of all U-RBCs can be captured in one frame is constructed, and an accurate U-RBC detection method based on multi-focus video fusion (D-MVF) is presented. The proposed D-MVF method consists of multi-focus video fusion and detection stages. In the fusion stage, D-MVF first uses the frame-difference data of multi-focus video to separate the U-RBCs from the background. Then, a new key frame extraction method based on the three metrics of information entropy, edge gradient, and intensity contrast is proposed. This method is responsible for extracting the typical shapes of U-RBCs and fusing them into a single image. In the detection stage, D-MVF utilizes the high-performance deep learning model YOLOv4 to rapidly and accurately detect U-RBCs based on the fused image. In addition, based on U-RBC detection results from D-MVF, this paper applies the K-nearest neighbor (KNN) method to replace artificial threshold setting for achieving more accurate diabetic nephropathy diagnosis. Results: A series of controlled experiments are conducted on the self-constructed dataset containing 887 multi-focus videos, and the experimental results show that the proposed D-MVF obtains a satisfactory mean average precision (mAP) of 0.915, which is significantly higher than that of the existing method based on single-focus images (0.700). Meanwhile, the diabetic nephropathy diagnosis accuracy and specificity of KNN reach 0.781 and 0.793, respectively, which significantly exceed the traditional threshold method (0.719 and 0.759). Conclusions: The research in this paper intelligently assists microscopists to complete U-RBC detection and diabetic nephropathy diagnosis. Therefore, the work load of microscopists can be effectively relieved, and the urine test demands of nephrotic patients can be met.

Object discrimination is one of the applications of visual intelligence technology. The shape and size of an object can be roughly judged by its contour. View-dependent contour can be shown by a discrete closed curve. In this paper, we proposed a discrimination method for two-dimensional discrete closed curves, using both curvature features and shape features. Firstly, the curvature of each point on the discrete closed curve is calculated using the micro-central difference algorithm. Then four statistical indexes, that are curvature mean, standard deviation of curvature, curvature skewness and curvature kurtosis, are estimated. Based on the sigma criterion, the curvature sharpness is obtained. The shape features are calculated and standardized. Finally, the support vector machine is employed to classify and recognize the discrete closed curve. The experimental results show that the proposed method works well for classifying those closed curves.

This study developed a method to detect sarafloxacin in goldfish (Carassius auratus) plasma and tissues using reverse phase high performance liquid chromatography (RP2HPLC).Plasma,muscle,skin,hepatopancreas,kidney and ovary were sampled at different intervals after oral administration of sarafloxacin hydrochloride at single dose of 20mg/kg under 21±2 ℃.Joining danofloxacin mesylate as inner standard , the medicine was extracted by dichloromethane from plasma and tissues,and the extracts were evaporated to dryness with N2 flow in water bath of 60℃then dissolved in mobile phase . The fat of the solute was degreased by hexane.Sarafloxacin hydrochloride and danofloxacin mesylate analyses were performed by RP2HPLC.The mobile phase was acetonitrile and 0.12mol/L phosphate buffer (pH714) (including 015 % tetrabutyl ammonium bromide)(10/90,V/ V) adjusted to pH 310 with phosphoric acid.Sarafloxacin hydrochloride and danofloxacin mesylate were quantitated by using ZORAX SB2C18 column and ultraviolet detector was set at 280nm.The mean recoveries were all higher than 82.97% for samples and inter-day CV for plasma and tissues were all under 8.41%,The lowest limit of detection was 010125μg/g for muscle.Both limit of detection (LOD) and limit of quantitation (LOQ) met the requirement of the residual detection.The results showed that the elimination rate was markedly different in plasma and five tissues of healthy female goldfish. The drug was slowly eliminated in plasma,the concentration of sarafloxacin hydrochloride in kidney and hepatopancreas was higher than other tissues and skin showed the slowest depletion among five tissues.Kidney was the main reservoir of sarafloxacin hy- drochloride in goldfish.Withdrawl time was 14d when the maximum residue is 30μg/kg for edible tissues after single oral administration of sarafloxacin hydrochloride in healthy female goldfish.