Objective:To develop a deep learning-based automated analysis system for precise segmentation of the optic cup and disc in fundus images and automatic measurement of the vertical cup-to-disc ratio (CDR) for early risk assessment and screening of chronic glaucoma.Methods:The proposed automated system comprised three modules: a dual coding-attention U-net (DCoAtUNet) segmentation network for optic cup and disc segmentation, a conditional random field (CRF) post-processing module, and a CDR measurement and glaucoma screening module based on the segmentation results.The system was designed to enhance boundary detection accuracy and measurement stability and its performance was evaluated on the publicly available Drishti-GS dataset.The dataset was divided into a training set and a test set in a 1∶1 ratio.Dice coefficient and intersection over union (IoU) were used to quantify segmentation accuracy and regional consistency, while accaracy, precision, recall, and F1-score were employed to assess glaucoma screening performance.Results:The DCoAtUNet combined with CRF post-processing achieved Dice coefficients of 0.976 0 for the optic disc and 0.908 1 for the optic cup, with corresponding IoU values of 0.953 4 and 0.837 9, demonstrating high segmentation precision and stability in boundary identification and region overlap.In glaucoma screening, the system achieved an accuracy of 0.843 1, precision of 0.840 9, recall of 0.973 7, and F1-score of 0.902 4, indicating good diagnostic sensitivity and accuracy.Conclusions:By integrating high-precision segmentation and automated measurement strategies, the DCoAtUNet+ CRF model significantly improves the accuracy and stability of CDR evaluation.It effectively assists in identifying high-risk individuals during early glaucoma screening and shows strong potential for clinical application in computer-aided diagnosis workflows.

Objective:To develop a deep learning-based automated analysis system for precise segmentation of the optic cup and disc in fundus images and automatic measurement of the vertical cup-to-disc ratio (CDR) for early risk assessment and screening of chronic glaucoma.Methods:The proposed automated system comprised three modules: a dual coding-attention U-net (DCoAtUNet) segmentation network for optic cup and disc segmentation, a conditional random field (CRF) post-processing module, and a CDR measurement and glaucoma screening module based on the segmentation results.The system was designed to enhance boundary detection accuracy and measurement stability and its performance was evaluated on the publicly available Drishti-GS dataset.The dataset was divided into a training set and a test set in a 1∶1 ratio.Dice coefficient and intersection over union (IoU) were used to quantify segmentation accuracy and regional consistency, while accaracy, precision, recall, and F1-score were employed to assess glaucoma screening performance.Results:The DCoAtUNet combined with CRF post-processing achieved Dice coefficients of 0.976 0 for the optic disc and 0.908 1 for the optic cup, with corresponding IoU values of 0.953 4 and 0.837 9, demonstrating high segmentation precision and stability in boundary identification and region overlap.In glaucoma screening, the system achieved an accuracy of 0.843 1, precision of 0.840 9, recall of 0.973 7, and F1-score of 0.902 4, indicating good diagnostic sensitivity and accuracy.Conclusions:By integrating high-precision segmentation and automated measurement strategies, the DCoAtUNet+ CRF model significantly improves the accuracy and stability of CDR evaluation.It effectively assists in identifying high-risk individuals during early glaucoma screening and shows strong potential for clinical application in computer-aided diagnosis workflows.

Objective To investigate the effects of silencing the gene of single-stranded DNA-binding protein 1 (SSB1) on proliferation and DNA repair of rat submandibular gland (SMG) cells after irradiation, and explore the relationship between SSB1 and DNA damage repair. Methods Primary rat SMG cells were obtained by mechanical-enzyme digestion and identified by immunohistochemistry. The cells were divided into three groups, including blank control, negative control and shRNA transfection group. The shRNA was transfected into cells by recombinant adenovirus vector. Real-time quantitative PCR ( qRT-PCR) was used to detect the expression of SSB1 after silencing. The cell viability was detected by CCK-8 assay. Immunofluorescence analysis was performed to observe the dynamic formation of γ-H2AX foci. Results The SMG cells were positively stained for both Pan CK and α-Amylase. The efficiency of shRNA transfection was about 90%at 72 h post-transfection. Compared with the blank control group, the expression of SSB1 was significantly decreased in the cells transfected with shRNA (t=16. 24, P<0. 05). The cell viability of shRNA transfection group without irradiation was decreased indistinctively and became lower than the blank control group significantly until 120 h(t=3. 29, P<0. 05). After radiation with 5 Gy of γ-rays, the cell viability of shRNA transfection group was lower than that of the control groups significantly (F=10. 19-30. 13, P<0. 05). Silencing the expression of SSB1 could increase the number ofγ-H2AX foci in SMG cells at different time of radiation. Conclusions After silencing of the expression of SSB1, the SMG cells could be more radiosensitive, which indicats that SSB1 may play an important role in DNA damage repair after radiation.

OBJECTIVETo assess the feasibility of chromosomal microarray analysis(CMA) for studying the correlation between birth defects and chromosomal aberrations.

METHODSA total of 2000 patients with birth defects were recruited for the CMA testing.

RESULTSFive hundred twenty two patients (26.1%) were found to have chromosomal abnormalities. These included 24 cases with numerical abnormalities, 11 with mosaicisms, and 11 with uniparental disomies. The remaining 476 cases were of well-known microdeletion or microduplication syndromes. The advantage of CMA over conventional karyotyping was demonstrated in many cases.

CONCLUSIONAs a powerful tool for patients with birth defects, CMA can produce a higher diagnostic yield compared with conventional karyotyping.

Adolescent ; Adult ; Child ; Child, Preschool ; Chromosome Disorders ; genetics ; Chromosomes, Human ; genetics ; Female ; Gene Dosage ; Humans ; Infant ; Infant, Newborn ; Karyotyping ; Male ; Oligonucleotide Array Sequence Analysis