ObjectiveTo study the characteristics of the genotype and phenotypic in a family with X-linked retinoschisis (XLRS) due to RS1 mutation. MethodsA retrospective clinical study. An XLRS family of 4 generations of 26 people were included in the study. Among them, 8 participants were males and 7 participants were females. Routine ophthalmologic examination was performed on 3 patients in the family including the proband and 12 patients with normal phenotype. Optical coherence tomography was performed in 2 of the 3 patients. Peripheral venous blood was extracted from all participants, whole-genome DNA was extracted, and potential pathogenic genes were screened by Panel sequencing. Conservative analysis, pathogenicity analysis and protein structure prediction were carried out by software tools. The pathogenicity of gene mutations was analyzed according to the American Society of Medical Genetics and Genomics (ACMG) guidelines. ResultsThe proband was 3 years old. Optical coherence tomography (OCT) examination showed that the retinal core layer in the macular area of both eyes had a cystic change, which was segmented by vertical or oblique bridging tissue. The proband's uncle was 32 years old. OCT examination showed atrophy in the macular area of the left eye. The macular area of the right eye was cystoid, segmented by vertical or oblique bridging tissue. No abnormality was found in the fundus examination of the proband's parents and 10 members of his family. Panel sequencing showed that c.361C>T/ p.Q121X hemizygous mutation was found in the fifth exon of RS1 gene in the proband (Ⅳ3) and 2 patients (Ⅱ1, Ⅲ8). The mother was a heterozygous mutation carrier of the gene, while the father had no mutation. The mutant gene causes premature termination of RS1, a truncated protein encoding 224 amino acids to 120 amino acids. Of the 10 patients with normal fundus examination, 6 participants were normal. The mutation was carried by four people, which were women. Homology analysis of the protein sequence showed that the mutant site was highly conserved in 12 mammals. Three-dimensional structural analysis of RS1 protein showed that the c-terminal amino acid sequence of the mutant protein was more than 50% missing. Analysis of ACMG guidelines indicated that the mutation was pathogenic. ConclusionThe RS1 mutation site c.361C>T/p.Q121X is a new mutation site of XLRS.
ObjectiveTo observe the diagnostic value of six classification intelligent auxiliary diagnosis lightweight model for common fundus diseases based on fundus color photography. MethodsA 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. ResultCompared 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. ConclusionThe 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.