Introduction: Infectious keratitis is a vision threatening disease. Bacterial and fungal keratitis are often confused in the early stages, so right diagnosis and optimized treatment for causative organisms is crucial. Antibacterial and antifungal medications are completely different, and the prognosis for fungal keratitis is even much worse. Since the identification of microorganisms takes a long time, empirical treatment must be started according to the appearance of the lesion before an accurate diagnosis. Thus, we developed an automated deep learning (DL) based diagnostic system of bacterial and fungal keratitis based on the anterior segment photographs using two proposed modules, Lesion Guiding Module (LGM) and Mask Adjusting Module (MAM).Methods: We used 684 anterior segment photographs from 107 patients confirmed as bacterial or fungal keratitis by corneal scraping culture. Both broad- and slit-beam images were included in the analysis. We set baseline classifier as ResNet-50. The LGM was designed to learn the location information of lesions annotated by ophthalmologists and the slit-beam MAM was applied to extract the correct feature points from two different images (broad- and slit-beam) during the training phase. Our algorithm was then externally validated using 98 images from Google image search and ophthalmology textbooks.Results: A total of 594 images from 88 patients were used for training, and 90 images from 19 patients were used for test. Compared to the diagnostic accuracy of baseline network ResNet-50, the proposed method with LGM and MAM showed significantly higher accuracy (81.1 vs. 87.8%). We further observed that the model achieved significant improvement on diagnostic performance using open-source dataset (64.2 vs. 71.4%). LGM and MAM module showed positive effect on an ablation study.Discussion: This study demonstrated that the potential of a novel DL based diagnostic algorithm for bacterial and fungal keratitis using two types of anterior segment photographs. The proposed network containing LGM and slit-beam MAM is robust in improving the diagnostic accuracy and overcoming the limitations of small training data and multi type of images.

Background: To compare the visual outcomes and optical quality of patients who underwent bilateral implantation of EDOF (AcrySof^® IQ Vivity IOL, DFT015) for mini-monovision, trifocal (AcrySof^® IQ PanOptix, TNFT00), or monofocal (AcrySof^® IQ IOL, SN60WF) IOL. Methods: The monocular-corrected and uncorrected distance visual acuities (CDVA and UDVA, respectively) were evaluated postoperatively at 1 and 3 months. The binocular visual acuity by distance, the binocular defocus curve, contrast sensitivity, and patient satisfaction were examined 3 months postoperatively. All patients were asked to complete questionnaires regarding their satisfaction, visual symptoms, and spectacle dependency. Results: This study included 178 eyes from 89 patients. The postoperative binocular UDVA did not differ significantly among the three groups. In the defocus curve, the Vivity group showed better visual acuity over a range of far and intermediate (60 cm) than the other two IOLs groups. In near-vision, the PanOptix group showed the best near-vision, and the Vivity group showed significantly better vision than the IQ group. The Vivity group showed contrast sensitivity and optical quality comparable to the IQ group. Conclusions: The bilateral implantation of AcrySof^® IQ Vivity IOL with the mini-monovision approach provided excellent distance and intermediate visual acuity with good near-vision, resulting in high satisfaction.

To develop three novel Vision Transformer (ViT) frameworks for the specific diagnosis of bacterial and fungal keratitis using different types of anterior segment images and compare their performances. Retrospective study. A ViT was used to classify bacterial and fungal keratitis. We integrated one or more ViTs by adding a vector or by using self-attention to combine different types of anterior segment images (broad-beam, slit-beam, and blue-light). We compared the area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) of the models. Cross-validation was performed thrice, and there was no overlap between the validation sets. The training/validation set was divided in an 8:2 ratio based on the number of individuals. A total of 283 broad-beam, 610 slit-beam, and 342 blue-light images were obtained from 79 patients. 62 (78 %) patients were assigned for training and 17 (22 %) for validation. The AUROC of ViT with broad-beam images was 0.72. The top AUROC score (0.93) was attained by combining the outputs from two ViT models utilizing self-attention, incorporating both broad-beam and slit-beam images. Similarly, the highest AUPRC score (0.93) was reached by fusing the outputs from three ViTs with self-attention, involving broad-beam, slit-beam, and blue-light images. Despite the limited dataset, we validated ViT with self-attention to learn different types of images to improve recognition accuracy in diagnosing bacterial and fungal keratitis. ViT with self-attention has a meaningful effect on enhancing the diagnostic performance of bacterial and fungal keratitis by combining two or more types of anterior segment images.

Background: We aimed to study the bilateral choroidal thickness (CT) symmetry and difference in uncomplicated pachychoroid subjects using wide-field swept-source optical coherence tomography (SS-OCT). Methods: All subjects underwent a wide-field 16-mm one-line scan using SS-OCT. Bilateral CT was measured at, and compared among, the following 12 points: three points at 900-µm intervals from the nasal optic disc margin (nasal peripapillary area), one point at the subfovea, six points at 900-µm intervals from the fovea to the nasal and temporal areas (macular area), and two peripheral points 5400 and 8100 µm from the fovea (peripheral area). Results: There were no statistically significant differences in CT between the right and left eyes in any area (all p > 0.05); they all showed significant positive correlations (all p < 0.01). However, the correlation coefficients (ρ) were smaller for the nasal peripapillary and peripheral areas compared to the macular area. Conclusions: The CTs in each region were bilaterally symmetrical in subjects with uncomplicated pachychoroid. However, interocular difference in CT increased from the center to the periphery, indicating that the anatomical variation of the nasal peripapillary and peripheral choroid was greater than that of the macula.

Background: To evaluate the clinical outcomes and patient satisfaction after implantation of an enhanced monofocal intraocular lens (TECNIS Eyhance ICB00) in patients with idiopathic epiretinal membrane (ERM) who underwent cataract surgery with pars plana vitrectomy (PPV). Methods: This is a single-center, retrospective, comparative study. In total, 61 eyes of 61 patients with idiopathic ERM and cataracts were included. We measured the uncorrected near and intermediate visual acuity (UNVA and UIVA), uncorrected and corrected distance visual acuity (UDVA and CDVA), central macular thickness, defocus curves, and contrast sensitivity 3–6 months after the surgery. Overall patient satisfaction was assessed using a questionnaire at the 1-month follow-up visit. Results: The ICB00 group showed better near and intermediate visual acuity than the monofocal group (TECNIS ZCB00); however, no statistically significant differences were found between the groups. The ICB00 group exhibited wider defocus curves at near to far distances (−3.0 to +2.0 D) than the ZCB00 group. There were no significant differences in the results of the contrast sensitivity test, dysphotopsia, spectacle dependence, or patient satisfaction between the two groups. Conclusions: In combined PPV and cataract surgery for ERM patients, ICB00 resulted in good visual acuity with a smoother defocus curve compared to the ZCB00 group.

This study aimed to evaluate the spherical aberration (SA) in different corneal areas before and after femtosecond laser-assisted in situ keratomileusis (fLASIK) and transepithelial photorefractive keratectomy (tPRK), with the goal of identifying the limitations of and potential improvements in using SA within a 6 mm area. The study included 62 patients who underwent fLASIK and tPRK. Complete eye examinations including keratometry, corneal epithelial thickness, central corneal thickness, and topography were performed preoperatively and postoperatively. Anterior, posterior, and total corneal aberrations were measured preoperatively and three months postoperatively, with pupil diameters ranging from 2 to 8 mm. In the fLASIK group, compared to the preoperative SA, the anterior and total SA increased postoperatively in the 6 and 7 mm areas. In the tPRK group, meanwhile, the anterior and total SA of the 5 mm or larger areas increased postoperatively. An area of 6 mm or larger showed an increase in correlation with the changes in Q value and refractive correction. As the corneal SA and asphericity in the 6 mm zone cannot specifically demonstrate the status of areas smaller than 6 mm or changes in the optical zone after laser refractive surgery, comparison with normal values in various areas of the cornea is necessary.