ABSTRACT
Purpose: Cataract is one of the leading causes of blindness worldwide, accounting for >50% of cases of blindness in low- and middle-income countries. In this study, two artificial intelligence (AI) diagnosis platforms are proposed for cortical cataract staging to achieve a precise diagnosis. Methods: A total of 647 high quality anterior segment images, which included the four stages of cataracts, were collected into the dataset. They were divided randomly into a training set and a test set using a stratified random-allocation technique at a ratio of 8:2. Then, after automatic or manual segmentation of the lens area of the cataract, the deep transform-learning (DTL) features extraction, PCA dimensionality reduction, multi-features fusion, fusion features selection, and classification models establishment, the automatic and manual segmentation DTL platforms were developed. Finally, the accuracy, confusion matrix, and area under the receiver operating characteristic (ROC) curve (AUC) were used to evaluate the performance of the two platforms. Results: In the automatic segmentation DTL platform, the accuracy of the model in the training and test sets was 94.59 and 84.50%, respectively. In the manual segmentation DTL platform, the accuracy of the model in the training and test sets was 97.48 and 90.00%, respectively. In the test set, the micro and macro average AUCs of the two platforms reached >95% and the AUC for each classification was >90%. The results of a confusion matrix showed that all stages, except for mature, had a high recognition rate. Conclusion: Two AI diagnosis platforms were proposed for cortical cataract staging. The resulting automatic segmentation platform can stage cataracts more quickly, whereas the resulting manual segmentation platform can stage cataracts more accurately.
ABSTRACT
OBJECTIVE: To evaluate the long-term efficacy and safety of laser in situ keratomileusis (LASIK) for extremely high myopia (with a preoperative refraction more than -10.00 diopters). METHODS: 173 eyes of 99 patients with a mean spherical equivalent (SE) of (-13.70 +/- 3.60) D (range -10.00 approximately 23.50 D), including 41 eyes with more than -15.00 D, were treated with LASIK and followed up for more than 18 months. The examinations included slitlamp microscopy, fundus examination, Orbscan II corneal topography system, tonometry, pachymetry, cycloplegic and subjective refraction. RESULTS: At 18 months postoperatively, the uncorrected visual acuity (UCVA) was 0.5 or better in 148 eyes (85.6%), and the best spectacle-corrected visual acuity (BSCVA) remained the same or increased in 147 eyes (84.4%). No eye lost more than two lines of BSCVA. 109 eyes (63.0%) were within +/- 1.00 D of emmetropia. The percentage was 73.5% and 29.3% in eyes with a preoperative SE of less than -14.75 D and more than -15.00 D, respectively. Postoperatively, the posterior corneal surface bulge was detected in all eyes. The mean elevation of the posterior corneal surface against the best-fit sphere was (0.029 +/- 0.010) mm preoperatively, (0.069 +/- 0.031) mm at 3 months, (0.065 +/- 0.025) mm at 18 months. At final follow-up, corneal flap folds were found in 2 eyes, and 6 patients (10 eyes) complained of glare or decreased scotopic vision. CONCLUSION: LASIK appeared to be an effective and safe treatment for correction of extremely high myopia. Meanwhile the candidates should be carefully screened.