RESUMO
Objective:To observe the diagnostic value of six classification intelligent auxiliary diagnosis lightweight model for common fundus diseases based on fundus color photography.Methods:A applied research. A dataset of 2 400 color fundus images from Nanjing Medical University Eye Hospital and Zhejiang Mathematical Medical Society Smart Eye Database was collected, which was desensitized and labeled by a fundus specialist. Of these, 400 each were for diabetic retinopathy, glaucoma, retinal vein occlusion, high myopia, age-related macular degeneration, and normal fundus. The parameters obtained from the classical classification models VGGNet16, ResNet50, DenseNet121 and lightweight classification models MobileNet3, ShuffleNet2, GhostNet trained on the ImageNet dataset were migrated to the six-classified common fundus disease intelligent aid diagnostic model using a migration learning approach during training as initialization parameters for training to obtain the latest model. 1 315 color fundus images of clinical patients were used as the test set. Evaluation metrics included sensitivity, specificity, accuracy, F1-Score and agreement of diagnostic tests (Kappa value); comparison of subject working characteristic curves as well as area under the curve values for different models.Result:Compared with the classical classification model, the storage size and number of parameters of the three lightweight classification models were significantly reduced, with ShuffleNetV2 having an average recognition time per sheet 438.08 ms faster than the classical classification model VGGNet16. All 3 lightweight classification models had Accuracy > 80.0%; Kappa values > 70.0% with significant agreement; sensitivity, specificity, and F1-Score for the diagnosis of normal fundus images were ≥ 98.0%; Macro-F1 was 78.2%, 79.4%, and 81.5%, respectively.Conclusion:The intelligent assisted diagnosis of common fundus diseases based on fundus color photography is a lightweight model with high recognition accuracy and speed; the storage size and number of parameters are significantly reduced compared with the classical classification model.
RESUMO
AIM:To establish a kind of simple and efficient method for cell-free fetal DNA ( cff-DNA) enrich-ment and to investigate its range of applications and the advantages and disadvantages.METHODS:(1) The single nucleo-tide polymorphisms( SNPs) , which linked to paternalβ-thalassemia mutations, were screened.We analyzed the contact be-tween the SNPs inβ-thalassemia gene ( HBB gene) and haploid type by the Haploview software, and then selected these close SNPs which have higher heterozygosity with the HBB gene.(2) We selected 4 cases of different β-thalassemia muta-tions with their husband, and then we used TT-FAST-COLD-PCR to enrich the IVS-II-654 mutations in maternal plasma.If the IVS-II-654 mutation was not detected, we detected the SNP which linked to the IVS-II-654 mutation.Similarly, we used TT-FULL-COLD-PCR to enrich the CD41-42 mutations in the maternal plasma.At the same time, we used the conventional PCR to enrich CD41-42 mutation and IVS-II-654 mutation in the maternal plasma.RESULTS:(1) Nine cases of the SNP ( rs7480526) linked to the mutation at IVS-II-654 in HBB gene, and 11 cases of the SNP ( rs10768683) linked to the muta-tion at CD41-42 in HBB gene were detected.( 2 ) We detected 1 case who inherited the paternal β-thalassemia mutation (IVS-II-654).We did not directly detect patermal IVS-II-654 mutation in maternal plasma, but detected the SNP linked to the IVS-II-654 mutation in the other case and had 100%detection, and 2 cases inherited the paternal β-thalassemia muta-tions (CD41-42) in the maternal plasma by TT-FULL-COLD-PCR and had 100%detection.However, we detected nothing by conventional PCR.CONCLUSION:TT-COLD-PCR is applicable to enrich cell-free fetal DNA in maternal plasma and is a method in the field of noninvasive prenatal diagnosis.