ObjectiveTo summarize the advancement of precise diagnosis and treatment for spastic cerebral palsy in recent years.MethodsThe literature and own experiences were reviewed, and the surgical method, precise diagnosis, and personalized treatment of spastic cerebral palsy based on the classification of spastic cerebral palsy were summarized and analyzed.ResultsThe common classification of spastic cerebral palsy are gross motor function classification system (GMFCS) and manual ability classification system (MACS). The surgical methods of spastic cerebral palsy can be divided into soft tissue surgery, nerve surgery, and bone and joint surgery. The precise diagnosis of spastic cerebral palsy includes qualitative diagnosis, localization diagnosis, and quantitative diagnosis. Based on precise diagnosis and classification, one or more corresponding surgical methods are selected for treatment.ConclusionThe manifestations of spastic cerebral palsy are so diverse that it is necessary to select rational surgeries based on precise diagnosis to achieve individualized treatment.
Objective To investigate the diagnostic efficacy of silkworm larvae plasma (SLP) colorimetry in the accurate diagnosis of periprosthetic joint infection (PJI). Methods Ninety healthy male New Zealand white rabbits were used for knee arthroplasty with Swanson prosthesis. Then they were randomly divided into 3 groups according to different pathogenic bacteria: group A (Staphylococcus aureus group), group B (Staphylococcus epidermidis group) and group C (Escherichia coli group), with 30 rats in each group. The PJI model was prepared by knee injection with 1 mL of pathogenic bacteria of different concentrations. Samples were taken before inoculation and at 7, 14, and 21 days after inoculation, and based on the 2018 PJI Philadelphia International Consensus diagnostic criteria, the success rate of modeling among 3 groups of experimental animals was determined. The sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic efficiency of SLP colorimetry were calculated. Results At 21 days after inoculation, 26, 18, and 23 rabbits in groups A, B, and C were diagnosed as infection, respectively. The success rates of modeling were 86.7%, 60.0%, and 76.7%, respectively, showing no significant difference among the 3 groups (χ2=5.724, P=0.073). The results of PJI colorimetry showed that 1 false-positive animal (specificity 75.0%) appeared in group A at 7 days, and the specificity of SLP increased to 100.0% over time (on 14 and 21 days); on 14 and 21 days, another animal appeared false-negative results (sensitivity decreased from 100.0% to 96.2%). One false-positive animal appeared in group B at 7 days (specificity 91.7%), the specificity returned to 100.0% over time; 1 and 4 false-negative animals appeared at 14 and 21 days, respectively (sensitivity 94.4% and 83.3%, respectively). In group C, two false-positive animals (specificity 71.4%) were found at 7 days, and then returned to 100.0%. The diagnostic efficiency of groups A and C was very high at 21 days (96.7% and 100.0%), even for the low virulence Staphylococcus epidermidis in group B, the diagnostic efficiency could be maintained at 90.0% (21 days), and the overall diagnostic efficiency was very good (95.6%). Conclusion SLP colorimetry has high sensitivity, specificity, and diagnostic efficiency in the diagnosis of PJI, which is a potential diagnostic method.
Melanocytic lesions occur on the surface of the skin, in which the malignant type is melanoma with a high fatality rate, seriously endangering human health. The histopathological analysis is the gold standard for diagnosis of melanocytic lesions. In this study, a fully automated intelligent diagnosis method based on deep learning was proposed to classify the pathological whole slide images (WSI) of melanocytic lesions. Firstly, the color normalization based on CycleGAN neural network was performed on multi-center pathological WSI; Secondly, ResNet-152 neural network-based deep convolutional network prediction model was built using 745 WSI; Then, a decision fusion model was cascaded, which calculates the average prediction probability of each WSI; Finally, the diagnostic performance of the proposed method was verified by internal and external test sets containing 182 and 54 WSI, respectively. Experimental results showed that the overall diagnostic accuracy of the proposed method reached 94.12% in the internal test set and exceeded 90% in the external test set. Furthermore, the color normalization method adopted was superior to the traditional color statistics-based and staining separation-based methods in terms of structure preservation and artifact suppression. The results demonstrate that the proposed method can achieve high precision and strong robustness in pathological WSI classification of melanocytic lesions, which has the potential in promoting the clinical application of computer-aided pathological diagnosis.