Glaucoma is one of blind causing diseases. The cup-to-disc ratio is the main basis for glaucoma screening. Therefore, it is of great significance to precisely segment the optic cup and disc. In this article, an optic cup and disc segmentation model based on the linear attention and dual attention is proposed. Firstly, the region of interest is located and cropped according to the characteristics of the optic disc. Secondly, linear attention residual network-34 (ResNet-34) is introduced as a feature extraction network. Finally, channel and spatial dual attention weights are generated by the linear attention output features, which are used to calibrate feature map in the decoder to obtain the optic cup and disc segmentation image. Experimental results show that the intersection over union of the optic disc and cup in Retinal Image Dataset for Optic Nerve Head Segmentation (DRISHTI-GS) dataset are 0.962 3 and 0.856 4, respectively, and the intersection over union of the optic disc and cup in retinal image database for optic nerve evaluation (RIM-ONE-V3) are 0.956 3 and 0.784 4, respectively. The proposed model is better than the comparison algorithm and has certain medical value in the early screening of glaucoma. In addition, this article uses knowledge distillation technology to generate two smaller models, which is beneficial to apply the models to embedded device.
Humans ; Optic Disk/diagnostic imaging* ; Glaucoma/diagnosis* ; Algorithms ; Diagnostic Techniques, Ophthalmological ; Databases, Factual

OBJECTIVE To determ ine the contents of main active constituents in Gynura divaricata leaf with different drying methods and at different harvesting time ，so as to confirm the best drying method and harvesting time. METHODS G. divaricata leaf with different drying methods [drying in the shade ，drying in the sun ，oven drying （60℃，70℃，80℃），microwave drying and freeze drying] and different harvesting time （March to October ）were prepared. The content of water-soluble extract was determined by hot dip method. The contents of total flavonoids and polysaccharides were determined by ultraviolet-visible spectrophotometry. The content of astragalin was determined by HPLC. Analytic hierarchy process was used for comprehensive analysis. RESULTS The time of drying in the shade ，drying in the sun ，drying at 60 ℃，drying at 70 ℃，drying at 80 ℃， microwave drying and freeze drying were 7 d，5 d，8 h，5 h，3.5 h，6 min and 1 d respectively. The average contents of water-soluble extract in G. divaricata leaf were 55.98％，60.78％，52.33％，49.54％，46.87％，59.70％ and 58.24％；those of total flavonoids were 3.27％，3.22％，1.99％，1.70％，1.31％，3.92％ and 2.28％；those of polysaccharides were 4.70％，6.09％， 6.48％，5.45％，5.74％，5.76％ and 7.15％；those of astragalin were 0.48％，0.46％，0.24％，0.23％，0.20％，0.48％，0.29％. The comprehensive score of microwave drying was the highest ，being 0.996 3. The average contents of water-soluble extract from March to October were 41.50％，40.57％，39.16％，40.65％，40.68％，43.30％，45.19％ and 40.12％；those of total flavonoids were 2.24％，2.81％，3.87％，3.92％，3.82％，3.93％，3.66％ and 3.25％；those of polysaccharides were 4.41％，4.61％， 4.98％，5.26％，5.75％，5.94％，5.32％ and 4.47％；those of astragalin were 0.20％，0.21％，0.25％，0.26％，0.25％，0.24％， 0.25％ and 0.21％，respectively. The comprehensive scores of samples collected from May to September exceeded 0.92，and the comprehensive score in August was the highest （0.988 6）. CONCLUSIONS Microwave-dried Gynura divaricata leaf has the best quality ，and the best harvesting time is from May to September.