Deep learning based joint segmentation and characterization of multi-class retinal fluid lesions on OCT scans for clinical use in anti-VEGF therapy.

BACKGROUND: In anti-vascular endothelial growth factor (anti-VEGF) therapy, an accurate estimation of multi-class retinal fluid (MRF) is required for the activity prescription and intravitreal dose. This study proposes an end-to-end deep learning-based retinal fluids segmentation network (RFS-Net) to segment and recognize three MRF lesion manifestations, namely, intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelial detachment (PED), from multi-vendor optical coherence tomography (OCT) imagery. The proposed image analysis tool will optimize anti-VEGF therapy and contribute to reducing the inter- and intra-observer variability. METHOD: The proposed RFS-Net architecture integrates the atrous spatial pyramid pooling (ASPP), residual, and inception modules in the encoder path to learn better features and conserve more global information for precise segmentation and characterization of MRF lesions. The RFS-Net model is trained and validated using OCT scans from multiple vendors (Topcon, Cirrus, Spectralis), collected from three publicly available datasets. The first dataset consisted of OCT volumes obtained from 112 subjects (a total of 11,334 B-scans) is used for both training and evaluation purposes. Moreover, the remaining two datasets are only used for evaluation purposes to check the trained RFS-Net's generalizability on unseen OCT scans. The two evaluation datasets contain a total of 1572 OCT B-scans from 1255 subjects. The performance of the proposed RFS-Net model is assessed through various evaluation metrics. RESULTS: The proposed RFS-Net model achieved the mean F1 scores of 0.762, 0.796, and 0.805 for segmenting IRF, SRF, and PED. Moreover, with the automated segmentation of the three retinal manifestations, the RFS-Net brings a considerable gain in efficiency compared to the tedious and demanding manual segmentation procedure of the MRF. CONCLUSIONS: Our proposed RFS-Net is a potential diagnostic tool for the automatic segmentation of MRF (IRF, SRF, and PED) lesions. It is expected to strengthen the inter-observer agreement, and standardization of dosimetry is envisaged as a result.

Anterior migration of intravitreal fluocinolone acetonide (Iluvien®) implant in a pseudophakic eye with intact posterior capsule.

PURPOSE: To describe a case of spontaneous anterior migration of intravitreal fluocinolone acetonide (Iluvien®) implant in a pseudophakic eye with intact posterior capsule. OBSERVATION: A 60-year old woman with proliferative diabetic retinopathy underwent uneventful pars plana vitrectomy and phacoemulsification with posterior chamber intraocular lens (PCIOL) implants in both eyes. She developed diabetic macular edema (DME) in her right eye which failed to respond to repeated intravitreal injections of Aflibercept 2mg/0.05ml (Eylea®). The patient received an intravitreal Iluvien® implant to treat the recalcitrant DME after she showed a favorable temporary response to dexamethasone intravitreal implant (Ozurdex™).Six months later she presented with pain in the right eye due to elevated intraocular pressure (IOP). The Iluvien® implant was found to be dislodged into the anterior chamber (AC) in the presence of an intact posterior capsule and stable PCIOL implant. The migrated Iluvien implant was removed and IOP was controlled with a glaucoma drainage valve as it failed to respond to maximum anti-glaucoma medication. CONCLUSIONS AND IMPORTANCE: Intravitreal Iluvien® implant could migrate into the AC in a previously vitrectomized eyes in the presence of an intact posterior capsule.

Asthenopia as the presenting symptom in advance allergic fungal sinusitis.

A 14-year-old male presented to the ophthalmology clinic with a history of asthenopia. Laboratory, radiological and histopathological studies confirmed the diagnosis of allergic fungal sinusitis resulting in lateral displacement of the medial rectus muscles. Symptoms improved and near point of convergence recovered after surgical endoscopic decompression of the ethmoidal and maxillary sinuses.

The relationship between stress and acute anterior uveitis.

PURPOSE: To examine the relationship between stress and anterior uveitis using the General Health Questionnaire (GHQ) and the Social Readjustment Rating Questionnaire (SRRQ). METHODS: Patients attending eye casualty with acute anterior uveitis (AAU) and suitable controls were asked to complete the GHQ and the SRRQ. A follow-up postal survey, using the same questionnaires, was repeated at least 3 months later amongst AAU patients only. Scores for the GHQ and SRRQ at initial presentation and at follow-up were compared for different groups. RESULTS: Over 12 months, 42 patients and 25 controls participated in the first stage of this study. Patients with AAU had higher GHQ scores than controls (mean 6.8 versus 3.2, p = 0.01). A total of 25 patients responded to the follow-up postal survey. At follow-up, 13 had experienced resolution and 12 had recurrence. In the group with resolution, there was a significant fall in GHQ scores (mean 6.1 versus 1.5, p = 0.0044). Patients with recurrence had higher GHQ scores than those with resolution (mean 6.8 versus 1.5, p = 0.02). CONCLUSIONS: Using the GHQ reveals a clear relationship between stress and the recurrence of AAU in susceptible individuals.

Capsular phimosis following phacotrabeculectomy.

Three cases of severe capsular phimosis following augmented phacotrabeculectomy complicated by intense postoperative fibrinous uveitis are described. The marked inflammation was possibly related to the combined procedure itself, the excessive intraoperative manipulation to stretch the pupil, and the compromised blood-aqueous barrier after prolonged use of pilocarpine. The combination of fibrinous uveitis and the small size of capsulorhexis attained through a stretched pupil are possible risk factors for developing severe capsular phimosis in the absence of zonular weakness or preoperative uveitis. For patients with similar risk factors, two separate surgical procedures should be considered. Alternatively, a larger capsulorhexis or radial relieving incisions should be attempted during phacotrabeculectomy to prevent this complication, which could jeopardize the outcome of otherwise successful surgery.

Iris prolapse in small incision cataract surgery.

Iris prolapse is a rare complication after small incision cataract surgery. We looked at the possible operative and perioperative factors that might have contributed to this complication in 2 of our patients and in another 10 patients identified through a national questionnaire survey. The details of 12 cases of iris prolapse following small incision cataract surgery are presented. Since iris prolapse may occur in small incision cataract surgery, notably in the presence of certain predisposing factors, extra diligence is required in wound construction and closure in high-risk patients.

Sensitivity and specificity of frequency-doubling technology, tendency-oriented perimetry, and Humphrey Swedish interactive threshold algorithm-fast perimetry in a glaucoma practice.

PURPOSE: To evaluate the sensitivity and specificity of the screening mode of the Humphrey-Welch Allyn frequency-doubling technology (FDT), Octopus tendency-oriented perimetry (TOP), and the Humphrey Swedish Interactive Threshold Algorithm (SITA)-fast (HSF) in patients with glaucoma. DESIGN: A comparative consecutive case series. METHODS: This was a prospective study which took place in the glaucoma unit of an academic department of ophthalmology. One eye of 70 consecutive glaucoma patients and 28 age-matched normal subjects was studied. Eyes were examined with the program C-20 of FDT, G1-TOP, and 24-2 HSF in one visit and in random order. The gold standard for glaucoma was presence of a typical glaucomatous optic disk appearance on stereoscopic examination, which was judged by a glaucoma expert. The sensitivity and specificity, positive and negative predictive value, and receiver operating characteristic (ROC) curves of two algorithms for the FDT screening test, two algorithms for TOP, and three algorithms for HSF, as defined before the start of this study, were evaluated. The time required for each test was also analyzed. RESULTS: Values for area under the ROC curve ranged from 82.5%-93.9%. The largest area (93.9%) under the ROC curve was obtained with the FDT criteria, defining abnormality as presence of at least one abnormal location. Mean test time was 1.08 +/- 0.28 minutes, 2.31 +/- 0.28 minutes, and 4.14 +/- 0.57 minutes for the FDT, TOP, and HSF, respectively. The difference in testing time was statistically significant (P <.0001). CONCLUSIONS: The C-20 FDT, G1-TOP, and 24-2 HSF appear to be useful tools to diagnose glaucoma. The test C-20 FDT and G1-TOP take approximately 1/4 and 1/2 of the time taken by 24 to 2 HSF.

Foreign body reaction with delayed extrusion of ganciclovir implant in a patient with immune recovery vitritis syndrome.

PURPOSE: To report a case of delayed extrusion of primary ganciclovir implants in a patient with immune recovery vitritis syndrome. METHOD: Interventional case report. A 54-year-old HIV positive male patient with immune recovery vitritis syndrome had spontaneous extrusion of bilateral ganciclovir devices 4 years after primary implantation. RESULT: The extruded ganciclovir implants were removed from both eyes, and removal was complicated by vitreous hemorrhage in one eye. Histopathological examination of the extruded implant, LE, showed marked inflammation and evidence of foreign body reaction. CONCLUSION: Excess inflammation in eyes with immune recovery vitritis syndrome may trigger a foreign body reaction that results in a delayed extrusion of primary ganciclovir implants. The site of ganciclovir implants in patients with immune recovery vitritis syndrome should be regularly inspected for eroding struts to prevent secondary endophthalmitis.