ABSTRACT
The count and recognition of white blood cells in blood smear images play an important role in the diagnosis of blood diseases including leukemia. Traditional manual test results are easily disturbed by many factors. It is necessary to develop an automatic leukocyte analysis system to provide doctors with auxiliary diagnosis, and blood leukocyte segmentation is the basis of automatic analysis. In this paper, we improved the U-Net model and proposed a segmentation algorithm of leukocyte image based on dual path and atrous spatial pyramid pooling. Firstly, the dual path network was introduced into the feature encoder to extract multi-scale leukocyte features, and the atrous spatial pyramid pooling was used to enhance the feature extraction ability of the network. Then the feature decoder composed of convolution and deconvolution was used to restore the segmented target to the original image size to realize the pixel level segmentation of blood leukocytes. Finally, qualitative and quantitative experiments were carried out on three leukocyte data sets to verify the effectiveness of the algorithm. The results showed that compared with other representative algorithms, the proposed blood leukocyte segmentation algorithm had better segmentation results, and the mIoU value could reach more than 0.97. It is hoped that the method could be conducive to the automatic auxiliary diagnosis of blood diseases in the future.
Subject(s)
Algorithms , LeukocytesABSTRACT
Objective:To investigate the diagnostic valuation of multilayer spiral CT pulmonary angiography in pulmonary embolism. Methods:A retrospective analysis 22 cases of pulmonary embolism were performed by 16 slice spiral CT diagnosis, The volume data of all cases were reconstructed for image post-processing with multi-plane reconstruction, maximum intensity projection and volume rendering. Results: Pulmonary embolism in patients with 22 cases, pulmonary artery and its branches remobilization of 22 cases were demonstrated well by MSCTA. Conclusion:The 16 slice spiral CT in the diagnosis of pulmonary embolism in a safe, rapid, high sensitivity, reliable diagnosis advantages, has been used as first choice of imaging diagnosis of pulmonary embolism diagnosis methods. It is worthy of wide clinical application.
ABSTRACT
Objective To evaluate whether the protein SP70 could be used as a serum biomarker for the diagnosis of non-small cell lung cancer (NSCLC).Methods Polyclonal antibody was prepared by immunizing New Zealand rabbit with SPC-A1 cells.Sandwich ELISA was carried out by using newly-prepared polyclonal antibody(PcMb) coating assay plates,monoclonal antibody (McAb) NJ001 and HRP goat antimouse antibody as primary antibody and labeling antibody respectively.After optimizing the experiment conditions,serum from 175 lung cancer patients [ 80 NSCLC adenocarcinoma,70 NSCLC squamous carcinoma and 25 small cell lung cancer ( SCLC) ],25 benign lung disease ( BLD) patients and 300 healthy controls (HC) were examined.CEA,NSE,CYFRA21-1 were measured by ECLIA for comparison.Results Positive rates of NSCLC adenocarcinoma,NSCLC squamous carcinoma,SCLC and BLD were 68.8％,51.4％,16.0％ and 12.0％ respectively,obviously higher than that of HC (7.3％).NSCLC (adenocarcinoma,Squamous carcinoma) had significantly higher positive rate than SCLC (60.7％ υs 16.0％,x2 =17.23,P＜0.05)and BLD(60.7％ υs 12.0％,x2 =20.41,P ＜0.05).Among 68 NSCLC patients who had definite staging,positive rates at early stage ( Ⅰ/Ⅱ,n=30) reached up to 76.7％.Meanwhile,positive rates of CEA,NSE and CYFRA21-1 (32.7％,18.0％ and 37.3％) were significantly lower than the targeting antigen to McAb NJ001 in NSCLC(60.7％ υs 32.7％,x2 =23.63,P ＜0.05;60.7％υs18.0％,x2 =57.22,P＜0.05;60.7％ υs37.3％,x2=16.34,P＜0.05).Conclusions It showed high positive rates of SP70 in the serum of NSCLC patients,which suggested thai SP70 might be a potential valuable biomarker for the diagnosis of NSCLC.