Peripheral Blood Leukocyte Detection Based on an Improved Detection Transformer Algorithm.

The combination of a blood cell analyzer and artificial microscopy to detect white blood cells is used in hospitals. Blood cell analyzers not only have large throughput, but they also cannot detect cell morphology; although artificial microscopy has high accuracy, it is inefficient and prone to missed detections. In view of the above problems, a method based on Fourier ptychographic microscopy (FPM) and deep learning to detect peripheral blood leukocytes is proposed in this paper. Firstly, high-resolution and wide-field microscopic images of human peripheral blood cells are obtained using the FPM system, and the cell image data are enhanced with DCGANs (deep convolution generative adversarial networks) to construct datasets for performance evaluation. Then, an improved DETR (detection transformer) algorithm is proposed to improve the detection accuracy of small white blood cell targets; that is, the residual module Conv Block in the feature extraction part of the DETR network is improved to reduce the problem of information loss caused by downsampling. Finally, CIOU (complete intersection over union) is introduced as the bounding box loss function, which avoids the problem that GIOU (generalized intersection over union) is difficult to optimize when the two boxes are far away and the convergence speed is faster. The experimental results show that the mAP of the improved DETR algorithm in the detection of human peripheral white blood cells is 0.936. In addition, this algorithm is compared with other convolutional neural networks in terms of average accuracy, parameters, and number of inference frames per second, which verifies the feasibility of this method in microscopic medical image detection.

Catalytic hydrolysis of cellulose by phosphotungstic acid-supported functionalized metal-organic frameworks with different electronegative groups.

It is found that strong electronegative groups can selectively adsorb cellulose by hydrogen bonds. Grafting strong negatively charged groups onto catalysts to achieve the functionalization of the catalyst can give it the ability to selectively adsorb cellulose without affecting its catalysis, which is of great significance for the hydrolysis of cellulose. In this study, PTA@MIL-101-X (X = -Br, -NH2, -Cl, -NO2) materials were synthesized to investigate the effect of grafting different electronegative groups on carriers to the directional hydrolysis of cellulose. The synthesized catalysts used phosphotungstic acid as the catalytic center while treated MIL-101 structure as the carrier. The grafting of different electronegative groups changed the crystal structure of the metal organic framework without affecting its stability during the reaction. The strong negative functional groups can selectively adsorb cellulose by forming hydrogen bonds with cellulose hydroxyl groups and weaken the hydrogen bonds within cellulose molecules. This hydrogen bond can reduce the side reaction of glucose, lighten the difficulty of cellulose hydrolysis, and improve the efficiency of cellulose conversion at the same time. The hydrolysis rate of cellulose increased with the electronegativity enhancement of the grafted functional groups, and the grafted -NO2 catalyst PTA@MIL-101-NO2 obtained the highest glucose yield of 16.2% in the cellulose-directed hydrolysis. The -NH2 can form a chemical linkage with PTA through electrostatic interaction to get the highest immobilization stability and exhibit excellent stability in the recycling of catalysts. Graphical abstract.