TRAMADOL-ASSOCIATED BILATERAL CYSTOID MACULAR EDEMA.

PURPOSE: To describe a case of bilateral cystoid macular edema in a patient with long-standing tramadol hydrochloride use. METHODS: Observational case report. RESULTS: A 73-year-old female patient was referred for progressive, bilateral decreased visual acuity. The patient was phakic with a best-corrected visual acuity at presentation was 20/50 on the right eye and 20/64 on the left eye. The patient had a history of low back pain and had been on tramadol hydrochloride 200 mg/day for 16 years. Bilateral cystoid macular edema was confirmed by means of multimodal imaging, including optical coherence tomography angiography. Tramadol intake was progressively reduced over one month and then completely interrupted. At 3 months follow-up, the cystoid macular edema had completely resolved and the best-corrected visual acuity improved in both eyes. CONCLUSION: Cystoid macular edema may be associated with longstanding treatment with tramadol hydrochloride. Tramadol hydrochloride-associated cystoid macular edema is described and its resolution on tramadol cessation.

FOCAL CHOROIDAL THICKNESS HEMODYNAMICS AS a SIGN OF MACULAR NEOVASCULARIZATION ACTIVITY IN PATHOLOGIC MYOPIA.

PURPOSE: To analyze the relationship between a focal increase of choroidal thickness (ChT) and exudative activity of macular neovascularization (MNV) secondary to pathologic myopia. METHODS: Retrospective analysis including eyes with pathologic myopia presenting with a focally increased ChT underneath active MNV. All patients included were treated, and ChT was measured before and after each intravitreal injection by two experienced ophthalmologists. RESULTS: Fifty-two eyes of 52 patients with myopic MNV (19 men and 33 women) were included in this analysis. ChT at T-1 averaged 51.09 ± 33.56 µ m, whereas at the time of MNV activation (T0), ChT was significantly thicker: 85.11 ± 43.99 µ m ( P < 0.001). After a single intravitreal injection, the ChT significantly decreased to 53.23 ± 34.15 µ m ( P < 0.001). CONCLUSION: This study showed that focal ChT variations may be considered an interesting corollary sign of MNV in high myopic patients, indicating the activity of myopic neovascularization.

Deep Learning to Distinguish ABCA4-Related Stargardt Disease from PRPH2-Related Pseudo-Stargardt Pattern Dystrophy.

(1) Background: Recessive Stargardt disease (STGD1) and multifocal pattern dystrophy simulating Stargardt disease ("pseudo-Stargardt pattern dystrophy", PSPD) share phenotypic similitudes, leading to a difficult clinical diagnosis. Our aim was to assess whether a deep learning classifier pretrained on fundus autofluorescence (FAF) images can assist in distinguishing ABCA4-related STGD1 from the PRPH2/RDS-related PSPD and to compare the performance with that of retinal specialists. (2) Methods: We trained a convolutional neural network (CNN) using 729 FAF images from normal patients or patients with inherited retinal diseases (IRDs). Transfer learning was then used to update the weights of a ResNet50V2 used to classify the 370 FAF images into STGD1 and PSPD. Retina specialists evaluated the same dataset. The performance of the CNN and that of retina specialists were compared in terms of accuracy, sensitivity, and precision. (3) Results: The CNN accuracy on the test dataset of 111 images was 0.882. The AUROC was 0.890, the precision was 0.883 and the sensitivity was 0.883. The accuracy for retina experts averaged 0.816, whereas for retina fellows it averaged 0.724. (4) Conclusions: This proof-of-concept study demonstrates that, even with small databases, a pretrained CNN is able to distinguish between STGD1 and PSPD with good accuracy.

Deep learning-based classification of retinal atrophy using fundus autofluorescence imaging.

PURPOSE: To automatically classify retinal atrophy according to its etiology, using fundus autofluorescence (FAF) images, using a deep learning model. METHODS: In this study, FAF images of patients with advanced dry age-related macular degeneration (AMD), also called geographic atrophy (GA), and genetically confirmed inherited retinal diseases (IRDs) in late atrophic stages [Stargardt disease (STGD1) and Pseudo-Stargardt Pattern Dystrophy (PSPD)] were included. The FAF images were used to train a multi-layer deep convolutional neural network (CNN) to differentiate on FAF between atrophy in the context of AMD (GA) and atrophy secondary to IRDs. Three-hundred fourteen FAF images were included, of which 110 images were of GA eyes and 204 were eyes with genetically confirmed STGD1 or PSPD. In the first approach, the CNN was trained and validated with 251 FAF images. Established augmentation techniques were used and an Adam optimizer was used for training. For the subsequent testing, the built classifiers were then tested with 63 untrained FAF images. The visualization method was integrated gradient visualization. In the second approach, 10-fold cross-validation was used to determine the model's performance. RESULTS: In the first approach, the best performance of the model was obtained using 10 epochs, with an accuracy of 0.92 and an area under the curve for Receiver Operating Characteristic (AUC-ROC) of 0.981. Mean accuracy was 87.30 ± 2.96. In the second approach, a mean accuracy of 0.79 ± 0.06 was obtained. CONCLUSION: This study describes the use of a deep learning-based algorithm to automatically classify atrophy on FAF imaging according to its etiology. Accurate differential diagnosis between GA and late-onset IRDs masquerading as GA on FAF can be performed with good accuracy and AUC-ROC values.

Pre-operative conjunctival flora in patients with local and/or systemic risk factors for post cataract surgery infection in Northern Italy.

PURPOSE: To investigate the pre-operative conjunctival flora in patients undergoing cataract surgery with major local and/or systemic risk factors for developing post-operative infection. METHODS: A total of 83 patients underwent bacterial culture and sensitivity testing of conjunctival swabs obtained from both eyes because of local risk factors at the pre-operative visit (i.e. chronic blepharitis, conjunctivitis, or lacrimal system disease), and/or systemic risk factors (i.e. autoimmune or skin disorders) for developing post-operative infection. If the swab was found positive, an antimicrobial susceptibility test was performed, and a specific antibiotic therapy was administered. Surgery was performed when a repeat conjunctival swab (after antibiotic treatment) showed negative cultures. RESULTS: Cultures were found positive in 25.3% of patients. Staphylococcus aureus (18%) and Staphylococcus epidermidis (15%) were the most frequently isolated microorganisms. Gram-negative bacteria, including Pseudomonas aeruginosa, were present in nine cases (8%). CONCLUSION: Present results showed a low rate of swab positivity compared to previous published data, and slightly different microbial flora. The differences observed may be caused by geographical factors and/or to the specific characteristics of the subgroup of studied patients. Considering that the surface microbial flora is one of the major causes of endophthalmitis, this information may be useful in selecting antibacterial regimens to prevent serious ocular infections, and restrain the increasing problem of antibiotic resistance.

Deep Learning-Based Classification of Inherited Retinal Diseases Using Fundus Autofluorescence.

Background. In recent years, deep learning has been increasingly applied to a vast array of ophthalmological diseases. Inherited retinal diseases (IRD) are rare genetic conditions with a distinctive phenotype on fundus autofluorescence imaging (FAF). Our purpose was to automatically classify different IRDs by means of FAF images using a deep learning algorithm. Methods. In this study, FAF images of patients with retinitis pigmentosa (RP), Best disease (BD), Stargardt disease (STGD), as well as a healthy comparable group were used to train a multilayer deep convolutional neural network (CNN) to differentiate FAF images between each type of IRD and normal FAF. The CNN was trained and validated with 389 FAF images. Established augmentation techniques were used. An Adam optimizer was used for training. For subsequent testing, the built classifiers were then tested with 94 untrained FAF images. Results. For the inherited retinal disease classifiers, global accuracy was 0.95. The precision-recall area under the curve (PRC-AUC) averaged 0.988 for BD, 0.999 for RP, 0.996 for STGD, and 0.989 for healthy controls. Conclusions. This study describes the use of a deep learning-based algorithm to automatically detect and classify inherited retinal disease in FAF. Hereby, the created classifiers showed excellent results. With further developments, this model may be a diagnostic tool and may give relevant information for future therapeutic approaches.