Glaucoma is an eye disease that occurs without the onset of symptoms at initial, and late diagnosis results in irreversible degeneration of retinal ganglion cells. Standard automated perimetry is the gold standard for assessing glaucoma; however, the examination is subjective, where responses can fluctuate each time the test is performed, significantly confounding the test's interpretation. In this study, we present our approach that aims to provide a rapid point-of-care diagnostics for glaucoma patients by eliminating the cognitive aspect in existing visual field assessment. Unlike existing methods that mostly report the foveal target detection's accuracy, we employed a multi-task learning architecture that efficiently captures signals simultaneously from the fovea and the neighboring targets in the peripheral vision, generating a visual response map. Furthermore, we designed a multi-task learning module that learns multiple tasks in parallel efficiently. We evaluated our model classification on a 40-classes dataset, with yields 92% and 95% in accuracy and F1 score respectively. Our model is able to perform on a calibration-free user-independent scenario, which is desirable for clinical diagnostics. Our proposed approach could be a stepping stone for an objective assessment of glaucoma patients' visual field.
To evaluate the outcome and complications of transscleral suture-fixated posterior chamber intraocular lens (PCIOL) implantation combined with Ahmed glaucoma valve (AGV) surgery in Asian eyes.This was a retrospective study that included 22 eyes from 22 participants. The surgeries were performed at Singapore's National University Hospital. Participants underwent an Ahmed tube surgery, together with transscleral suture-fixated posterior chamber intraocular lens.Complete success was defined as 6 ≤ intraocular pressure (IOP) ≤ 21 mmHg without medications at the last follow-up visit, with no reoperation required and no progression to no perception of light (NPL).At the last follow-up, there was a significant reduction in mean IOP (22.4 ± 6.5 mmHg versus 13.9 ± 3.9 mmHg; p < 0.001) and mean number of intraocular pressure-lowering medications (2.45 ± 1.30 versus 0.05 ± 0.21; p < 0.001). There was no significant change in visual acuity [1.43 ± 1.21 (LogMAR) versus 1.09 ± 1.31 (p = 0.204)]. Sixteen eyes (72.7%) achieved complete success. The 3 commonest complications were bullous keratopathy, choroidal detachment, and displacement of intraocular lens.This technique showed good success for intraocular pressure control and vision preservation. Postoperative complications were relatively common although most were self-limiting. Patients at increased risk of trabeculectomy failure may be suitable for this procedure.
Anterior chamber depth (ACD) is a major risk factor of angle closure disease, and has been used in angle closure screening in various populations. However, ACD is measured from ocular biometer or anterior segment optical coherence tomography (AS-OCT), which are costly and may not be readily available in primary care and community settings. Thus, this proof-of-concept study aims to predict ACD from low-cost anterior segment photographs (ASPs) using deep-learning (DL). We included 2,311 pairs of ASPs and ACD measurements for algorithm development and validation, and 380 pairs for algorithm testing. We captured ASPs with a digital camera mounted on a slit-lamp biomicroscope. Anterior chamber depth was measured with ocular biometer (IOLMaster700 or Lenstar LS9000) in data used for algorithm development and validation, and with AS-OCT (Visante) in data used for testing. The DL algorithm was modified from the ResNet-50 architecture, and assessed using mean absolute error (MAE), coefficient-of-determination (R 2 ), Bland-Altman plot and intraclass correlation coefficients (ICC). In validation, our algorithm predicted ACD with a MAE (standard deviation) of 0.18 (0.14) mm; R 2 = 0.63. The MAE of predicted ACD was 0.18 (0.14) mm in eyes with open angles and 0.19 (0.14) mm in eyes with angle closure. The ICC between actual and predicted ACD measurements was 0.81 (95% CI 0.77, 0.84). In testing, our algorithm predicted ACD with a MAE of 0.23 (0.18) mm; R 2 = 0.37. Saliency maps highlighted the pupil and its margin as the main structures used in ACD prediction. This study demonstrates the possibility of predicting ACD from ASPs via DL. This algorithm mimics an ocular biometer in making its prediction, and provides a foundation to predict other quantitative measurements that are relevant to angle closure screening.
'/%3e%3cuse xlink:href='%23a' transform='translate(288.889 -214.211)'/%3e%3cuse xlink:href='%23a' transform='translate(108 342.749)'/%3e%3cuse xlink:href='%23a' transform='translate(469.189 342.749)'/%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
