Delivery of photocoagulation treatment for diabetic retinopathy at a large Australian ophthalmic hospital: comparisons with national clinical practice guidelines

Automatic detection of non-perfusion areas in diabetic macular edema from fundus fluorescein angiography for decision making using deep learning

Vision loss caused by diabetic macular edema (DME) can be prevented by early detection and laser photocoagulation. As there is no comprehensive detection technique to recognize NPA, we proposed an automatic detection method of NPA on fundus fluorescein angiography (FFA) in DME. The study included 3,014 FFA images of 221 patients with DME. We use 3 convolutional neural networks (CNNs), including DenseNet, ResNet50, and VGG16, to identify non-perfusion regions (NP), microaneurysms, and leakages in FFA images. The NPA was segmented using attention U-net. To validate its performance, we applied our detection algorithm on 249 FFA images in which the NPA areas were manually delineated by 3 ophthalmologists. For DR lesion classification, area under the curve is 0.8855 for NP regions, 0.9782 for microaneurysms, and 0.9765 for leakage classifier. The average precision of NP region overlap ratio is 0.643. NP regions of DME in FFA images are identified based a new automated deep learning algorithm. This study is an in-depth study from computer-aided diagnosis to treatment, and will be the theoretical basis for the application of intelligent guided laser.

NAVILAS Laser System Focal Laser Treatment for Diabetic Macular Edema - One Year Results of a Case Series

Purpose:

To report one year outcomes of focal Navigated Retina Laser Therapy (NAVILAS) for diabetic macular edema (DME).

Methods:

Retrospective cohort series of 7 diabetic patients treated with NAVILAS focal laser. Statistical analysis included descriptive and continuous variables (Best-corrected logMAR Visual Acuity and time-domain optical coherence tomography (OCT) parameters) which were compared using a non-parametric procedure, the Friedman tests for repeated measures. A p-value of less than 0.05 was considered to denote statistical significance.

Results:

diabetic patients (4 male; 3 female) with an average age of 60.8 years (range 48-85 years) were included. All treated eyes were phakic; patients had an average hemoglobin A1C of 9.1 (range 7.8-11.7) at baseline and 8.0 (range 7.4-8.4) at 12 months. Six of the 7 patients had intravitreal bevacizumab injections prior to focal laser treatment with 1 patient having had more than 1 prior injection (total 3). At 12 months, median logMAR improved from 0.695 (± interquartile range 0.574) to 0.477 (± 0.573, p <0.001). OCT median central foveal thickness decreased from 248 (± 112) to 220 µm (± 41, p <0.001); total macular volume decreased from 7.84 (± 0.8) to 7.44 mm3 (± 0.7, p = 0.117); and largest macular subfield thickness decreased from 354 (± 116) to 289 µm (± 42, p <0.001). All patients were treated without complications.

Conclusions:

Focal NAVILAS showed to be safe and effective in treating DME with improvement in visual acuity and macular edema on OCT over 12 months in this case series. In clinical practice, combined treatment with focal laser including NAVILAS and anti-vascular endothelial growth factor may provide long-term improvement in DME.

Clinical outcomes following laser photocoagulation treatment for diabetic retinopathy at a large Australian ophthalmic hospital

OBJECTIVE

To evaluate clinical outcomes of diabetic retinopathy laser treatment at a large Australian ophthalmic hospital.

METHODS

A retrospective medical record review of all patients who had initial laser treatment for diabetic retinopathy at the Royal Victorian Eye and Ear Hospital from January 1997 to December 1998.

RESULTS

The study included 322 eyes from 203 patients. The mean age was 65.8 years (range 18-89) and the mean follow up was 18 months (range 2-33). Focal photocoagulation treatment alone was performed in 238 eyes. Clinically significant macular oedema (CSME) resolved in 218 (91.6%) eyes. Vision was improved or maintained in 137 (57.6%) eyes. Moderate visual loss occurred in 49 (20.6%) eyes. Panretinal photocoagulation (PRP) was performed in 84 eyes, including 37 eyes with PRP alone and 47 eyes with PRP and focal together. Neovascularization regressed in 55 (65.5%) eyes. Vision was improved or maintained in 52 (61.9%) eyes. Moderate visual loss was observed in 20 (23.8%) eyes and severe visual loss was observed in 4 (4.8%) eyes.

CONCLUSIONS

The clinical outcomes reported here are similar to those reported in other studies.