[Navigated focal retinal laser therapy using the NAVILAS® system for diabetic macula edema]

Development of a Computer System for Automatically Generating a Laser Photocoagulation Plan to Improve the Retinal Coagulation Quality in the Treatment of Diabetic Retinopathy

In this article, the development of a computer system for high-tech medical uses in ophthalmology is proposed. An overview of the main methods and algorithms that formed the basis of the coagulation plan planning system is presented. The system provides the formation of a more effective plan for laser coagulation in comparison with the use of existing coagulation techniques. An analysis of monopulse- and pattern-based laser coagulation techniques in the treatment of diabetic retinopathy has shown that modern treatment methods do not provide the required efficacy of medical laser coagulation procedures, as the laser energy is nonuniformly distributed across the pigment epithelium and may exert an excessive effect on parts of the retina and anatomical elements. The analysis has shown that the efficacy of retinal laser coagulation for the treatment of diabetic retinopathy is determined by the relative position of coagulates and parameters of laser exposure. In the course of the development of the computer system proposed herein, main stages of processing diagnostic data were identified. They are as follows: the allocation of the laser exposure zone, the evaluation of laser pulse parameters that would be safe for the fundus, mapping a coagulation plan in the laser exposure zone, followed by the analysis of the generated plan for predicting the therapeutic effect. In the course of the study, it was found that the developed algorithms for placing coagulates in the area of laser exposure provide a more uniform distribution of laser energy across the pigment epithelium when compared to monopulse- and pattern-based laser coagulation techniques.

Application of Artificial Intelligence in Ophthalmology for the Diagnosis and Treatment of Eye Diseases

In this paper, we present the main aspects of artificial intelligence application in ophthalmology for the diagnosis and treatment of eye diseases on the example of developing a computer system for personalizing retinal laser photocoagulation. Approaches to the automation of eye disease prediction and treatment based on fundus images are described. Four problems of applying the neural network approach are highlighted. Decision support information technology for personalizing laser treatment of diabetic macular edema and identifying prognostic factors of surgical outcome using methods of intellectual analysis of large unstructured data is described. The system allows the doctor to form a plan of optimal coagulation arrangement for retinal laser coagulation for each case, to predict the quality of laser coagulation depending on the initial data on the localization and severity of edema and to improve his skills by comparing the result of coagulation performed and the coagulation plan proposed by the system.

Automatic detection of leakage point in central serous chorioretinopathy of fundus fluorescein angiography based on time sequence deep learning

PURPOSE

To detect the leakage points of central serous chorioretinopathy (CSC) automatically from dynamic images of fundus fluorescein angiography (FFA) using a deep learning algorithm (DLA).

METHODS

The study included 2104 FFA images from 291 FFA sequences of 291 eyes (137 right eyes and 154 left eyes) from 262 patients. The leakage points were segmented with an attention gated network (AGN). The optic disk (OD) and macula region were segmented simultaneously using a U-net. To reduce the number of false positives based on time sequence, the leakage points were matched according to their positions in relation to the OD and macula.

RESULTS

With the AGN alone, the number of cases whose detection results perfectly matched the ground truth was only 37 out of 61 cases (60.7%) in the test set. The dice on the lesion level were 0.811. Using an elimination procedure to remove false positives, the number of accurate detection cases increased to 57 (93.4%). The dice on the lesion level also improved to 0.949.

CONCLUSIONS

Using DLA, the CSC leakage points in FFA can be identified reproducibly and accurately with a good match to the ground truth. This novel finding may pave the way for potential application of artificial intelligence to guide laser therapy.

Clinical efficacy of navigated panretinal photocoagulation in proliferative diabetic retinopathy

PURPOSE

To compare the clinical efficacy of navigated pattern and conventional slit-lamp pattern panretinal photocoagulation (PRP).

DESIGN

Randomized clinical trial.

METHODS

Seventy-four eyes with proliferative diabetic retinopathy (PDR) in need of PRP were randomly assigned to 1 of 4 groups: PRP conventional pattern 30 ms, 100 ms, navigated pattern 30 ms, 100 ms pulse. Navigated laser is a fundus camera-based photocoagulator with retinal eye tracking. Outcome variables included stability of visual acuity, regression or development of neovascularization and need for retreatment sessions and surgical intervention, pain perception, and procedure time.

RESULTS

There was no change in visual acuity between pre- and post-treatment measurements among the study groups. Short pulse groups in total required 22 procedures compared to 12 procedures in long pulse groups (P < .05). A trend toward worse outcome using 30 ms pulse duration treatments is expressed by slightly increased relative risk of 1.3 compared to 100 ms groups. Only 2 eyes required vitreoretinal surgery for nonclearing vitreous hemorrhage, 1 in each 30 ms group; insignificantly different between study groups (P = .98). The pain score was lower with navigated laser as compared to conventional laser in both 30 ms groups (P = .1) and 100 ms groups, where it reached statistical significance (P = .02). Pain experience was significant (P < .001) between navigated 100 ms pattern and conventional single-spot 100 ms treatments.

CONCLUSIONS

This study demonstrates better clinical efficacy of 100 ms compared to 30 ms treatments using both conventional and navigated pattern lasers. The ability to use long-pulse-duration navigated pattern treatments broadens therapeutic options for PRP in proliferative diabetic retinopathy.

Navigated Laser Therapy for Diabetic Macular Oedema

Navigated laser therapy introduces computerised assistance systems to retinal laser photocoagulation treatment. Some of the main benefits the Navilas system offers over conventional laser include high precision and safety and provides additional advantages in terms of standardisation of planning, execution, documentation, quality assurance and better overall treatment comfort for the patient. Navigated laser therapy is being used with good success in the treatment of diabetic macular oedema (DMO), retinal vein occlusions (RVO) and fastpattern navigated panretinal photocoagulation in proliferative diabetic retinopathy (PDR). In centre-involving DMO, a combination of anti-vascular endothelial growth factor (VEGF) and macular laser may provide advantages over anti-VEGF monotherapy. In terms of navigated laser therapy, recent study data from our clinic and other institutions indicate that combined initial anti-VEGF and navigated macular laser therapy allows treatment success to be achieved and maintained with a significantly reduced number of interventions.

Time required for navigated macular laser photocoagulation treatment with the Navilas

BACKGROUND

Navilas laser is a novel technology combining photocoagulation with imaging, including fluorescein angiographic (FA) images which are annotated and aligned to a live fundus view. We determine the time necessary for planning and treatment of macular edema utilizing the Navilas.

METHODS

The screen recordings during treatments were retrospectively analyzed for treatment type, number of laser shots, the duration of planning (measured from the time the planning image was selected to time of marking the last planned treatment spot), and total time of laser application.

RESULTS

A total of 93 treatments (30 grid, 30 focal and 33 combined treatments) by four physicians from three sites were included. An average of 125 spots were applied to each eye. The total time spent for each focal treatment - including the planning was 7 min 47 s (±3 min and 32 s).

CONCLUSIONS

Navilas is a novel device providing a time efficient platform for evaluating FA images and performing threshold macular laser photocoagulation.