AIM: To quantitatively evaluate the clinical characteristics of haze after transepithelial photorefractive keratectomy(TPRK)for astigmatism using corneal densitometry.METHODS:In this retrospective clinical study, a total of 74 patients(106 eyes)with astigmatism ≥1.25 D who underwent TPRK in our hospital from October 2022 to December 2024 were continuously collected. All of the study subjects were divided into transparent group(65 eyes)and haze group(41 eyes)based on whether haze occurred after surgery. Pentacam examination was performed before and after surgery, and corneal densitometry was recorded at the time points of preoperation, 1 mo postoperation in the transparent group and the most severe haze degree in the haze group. The collected corneal densitometry included the average densitometry of the entire corneal layer in the central 2 mm, 2-6 mm, and 6-10 mm areas, as well as the average densitometry of the entire layer of the corneal section in the center 6 mm of the astigmatism axis(astigmatism expressed in negative cylindrical form)and orthogonal axis(the axis perpendicular to the astigmatism axis), and the average densitometry of the entire layer of the corneal section in the nasal and temporal 2-6 mm areas of the astigmatism axis in the haze group of patients with regular astigmatism. The change in corneal densitometry after surgery compared with that before surgery was calculated.RESULTS:There was no statistically significant difference in baseline data such as gender, age, and spherical equivalent between the transparent group and the haze group(all P>0.05). The change in corneal densitometry in the 2-6 mm area of the haze group was greater than that in the transparent group(Z=-2.226, P=0.026), while there was no significant difference in the change of corneal densitometry in the central 2 mm and 6-10 mm areas between the two groups(both P>0.05). There was no significant difference in the change of corneal densitometry between the transparent group and haze group along the orthogonal axis(all P>0.05), while the change of corneal densitometry in the haze group along the astigmatism axis was greater than that in the transparent group(Z=-2.371, P=0.018). The temporal corneal densitometry of patients with regular astigmatism in the haze group after surgery was higher than that of the nasal side, and the change in corneal densitometry was also greater than that of the nasal side(Z=-4.288, P<0.001; Z=-4.043, P<0.001).CONCLUSION:Unlike spherical correction for myopia and hyperopia, haze after TPRK for astigmatism was mainly manifested in the peripheral cutting area of the astigmatism axis, and patients with regular astigmatism had a higher probability or severity of haze on the temporal side of the astigmatism axis than on the nasal side.

Objective To investigate the diagnostic accuracy and clinical applicability of the Linknet-VGG16 deep learning algorithm for measuring the effective optical zone(EOZ)after corneal refractive surgery.Methods This single-center retrospective cohort study included 69 patients(69 eyes)who underwent femtosecond laser-assisted in situ kerato-mileusis(FS-LASIK)(34 eyes)or small incision lenticule extraction(SMILE)(35 eyes)at the Refractive Surgery Center of Affiliated Zhengzhou Aier Eye Hospital of Henan University from June 2023 to June 2024.Data from the right eyes of all patients were selected for statistical analysis.During the surgery,patients in the FS-LASIK group adopted the VisuMax fem-tosecond laser system combined with the Amaris 750S excimer laser system,while those in the SMILE group only used the VisuMax femtosecond laser system.A total of 276 Pentacam images were re-examined postoperatively.A Linknet segmenta-tion model based on the VGG16 encoder was constructed,and image normalization techniques were applied to accelerate model convergence.Model performance was assessed using accuracy,intersection over union(IoU),and the Dice coeffi-cient.The traditional EOZ measurement method based on corneal tangential curvature served as the reference standard.Bland-Altman analysis was conducted to evaluate consistency across all images and within each group,and the time effi-ciency of both methods was compared.Results Six representative medical image segmentation architectures(U-Net,U-Net++,DeepLabv3-ResNet50,DeepLabv3+-ResNet50,Unet-Densenet169,and Linknet-VGG16)were systematically evaluated.The Linknet-VGG16 model demonstrated superior performance over the other 5 models in pixel-level accuracy,IoU and Dice coefficient,which were 99.83％,99.48％and 99.74％,respectively.Although there was no significant differ-ence in accuracy and Dice coefficient between Linknet-VGG16 and U-Net models(whose accuracy was 99.82％and Dice coefficient was 99.72％),the inference speed of the U-Net model(62.46 ms)was 31.76％slower than that of the Linknet-VGG16 model(42.62 ms).The evaluation results of a clinically applicable comprehensive scoring model(weights:accura-cy 20％,IoU 20％,Dice coefficient 20％,speed 25％,model size 15％)showed that the Linknet-VGG16 model achieved a score of 88.01,surpassing other architectures(U-Net:86.29;DeepLabv3+-ResNet50:80.41;DeepLabv3-ResNet50:73.82;U-Net++:73.22;Unet-Densenet169:66.66).Bland-Altman analysis revealed that the mean difference of the 136 images in the FS-LASIK group was 0.01 mm[95％limits of agreement(LoA):-0.36 to 0.35 mm],with 96.3％of data points falling within the LoA.The mean difference of the 140 images in the SMILE group was-0.01 mm(95％LoA:-0.36 to 0.33 mum),with 95.7％of data points falling within the LoA.The mean difference of all 276 images was 0.00 mm(95％LoA:-0.36 to 0.34 mm),with 96.4％of data points falling within the LoA.These results indicated excellent consistency.The average measurement time per image using the traditional EOZ measurement method was 13.00 minutes,whereas the deep learning model required only 3.22 seconds.Conclusion The traditional EOZ measurement method based on corne-al tangential curvature exhibits good consistency with the fully automatic EOZ measurement method based on deep learning algorithms,achieving high image recognition accuracy.Additionally,the deep learning algorithm significantly reduces measurement time,compared with the traditional method based on corneal tangential curvature.

Objective To investigate the diagnostic accuracy and clinical applicability of the Linknet-VGG16 deep learning algorithm for measuring the effective optical zone(EOZ)after corneal refractive surgery.Methods This single-center retrospective cohort study included 69 patients(69 eyes)who underwent femtosecond laser-assisted in situ kerato-mileusis(FS-LASIK)(34 eyes)or small incision lenticule extraction(SMILE)(35 eyes)at the Refractive Surgery Center of Affiliated Zhengzhou Aier Eye Hospital of Henan University from June 2023 to June 2024.Data from the right eyes of all patients were selected for statistical analysis.During the surgery,patients in the FS-LASIK group adopted the VisuMax fem-tosecond laser system combined with the Amaris 750S excimer laser system,while those in the SMILE group only used the VisuMax femtosecond laser system.A total of 276 Pentacam images were re-examined postoperatively.A Linknet segmenta-tion model based on the VGG16 encoder was constructed,and image normalization techniques were applied to accelerate model convergence.Model performance was assessed using accuracy,intersection over union(IoU),and the Dice coeffi-cient.The traditional EOZ measurement method based on corneal tangential curvature served as the reference standard.Bland-Altman analysis was conducted to evaluate consistency across all images and within each group,and the time effi-ciency of both methods was compared.Results Six representative medical image segmentation architectures(U-Net,U-Net++,DeepLabv3-ResNet50,DeepLabv3+-ResNet50,Unet-Densenet169,and Linknet-VGG16)were systematically evaluated.The Linknet-VGG16 model demonstrated superior performance over the other 5 models in pixel-level accuracy,IoU and Dice coefficient,which were 99.83％,99.48％and 99.74％,respectively.Although there was no significant differ-ence in accuracy and Dice coefficient between Linknet-VGG16 and U-Net models(whose accuracy was 99.82％and Dice coefficient was 99.72％),the inference speed of the U-Net model(62.46 ms)was 31.76％slower than that of the Linknet-VGG16 model(42.62 ms).The evaluation results of a clinically applicable comprehensive scoring model(weights:accura-cy 20％,IoU 20％,Dice coefficient 20％,speed 25％,model size 15％)showed that the Linknet-VGG16 model achieved a score of 88.01,surpassing other architectures(U-Net:86.29;DeepLabv3+-ResNet50:80.41;DeepLabv3-ResNet50:73.82;U-Net++:73.22;Unet-Densenet169:66.66).Bland-Altman analysis revealed that the mean difference of the 136 images in the FS-LASIK group was 0.01 mm[95％limits of agreement(LoA):-0.36 to 0.35 mm],with 96.3％of data points falling within the LoA.The mean difference of the 140 images in the SMILE group was-0.01 mm(95％LoA:-0.36 to 0.33 mum),with 95.7％of data points falling within the LoA.The mean difference of all 276 images was 0.00 mm(95％LoA:-0.36 to 0.34 mm),with 96.4％of data points falling within the LoA.These results indicated excellent consistency.The average measurement time per image using the traditional EOZ measurement method was 13.00 minutes,whereas the deep learning model required only 3.22 seconds.Conclusion The traditional EOZ measurement method based on corne-al tangential curvature exhibits good consistency with the fully automatic EOZ measurement method based on deep learning algorithms,achieving high image recognition accuracy.Additionally,the deep learning algorithm significantly reduces measurement time,compared with the traditional method based on corneal tangential curvature.