The role of the disc damage likelihood scale in glaucoma detection by community optometrists

Changes to glaucoma surgery patterns during the coronavirus disease 2019 pandemic: a shift towards less invasive procedures

PURPOSE

The aim of the study was to compare the quantity, type of glaucoma surgeries, and the disease stage before and during the coronavirus disease 2019 (COVID-19) pandemic.

METHODS

This was a retrospective, single-centre consecutive case series that included medical records of patients who underwent glaucoma surgery at the University Hospital in Białystok between 4 September, 2018, and 3 March, 2020 (pre-pandemic group) and compared it with patients treated between 4 March, 2020, and 4 September, 2021 (pandemic group). Adult patients with primary or secondary open-angle or closed-angle glaucoma who underwent surgery were included in this study. Finally, 534 operated eyes (362 and 172 eyes operated on before and during the pandemic, respectively) were examined.

RESULTS

The number of glaucoma surgeries dropped by 50% during the pandemic compared to a similar pre-pandemic period, with a significant difference in the kind of procedure between the two groups (p < 0.001). The most common procedures in the pre-pandemic group were Ex-Press implantation (33.7%) and trabeculectomy (31.5%). Within the pandemic group, half of the eyes underwent trabeculectomy (50.0%), followed by Preserflo microshunt (11.6%), iStent (8.7%), and transscleral cyclophotocoagulation (TSCP) (8.7%). A significant difference in the average intraocular pressure was revealed among patients who qualified for surgery.

CONCLUSION

The COVID-19 pandemic is associated with a decrease in the number of extended antiglaucoma procedures and an increase in the number of short procedures performed, such as TSCP and minimally invasive glaucoma surgery.Key MessagesOur study has shown the negative impact of the COVID-19 pandemic in reducing the number of antiglaucoma procedures.The number of glaucoma surgeries dropped by 50% during the pandemic compared to those in a similar pre-pandemic period, and the type of performed procedures has changed.The COVID-19 pandemic is associated with a decrease in the number of combined antiglaucoma procedures, in opposite: the number of minimally invasive glaucoma surgeries increased due to safety reasons.

DDLSNet: A Novel Deep Learning-Based System for Grading Funduscopic Images for Glaucomatous Damage

Purpose

To report an image analysis pipeline, DDLSNet, consisting of a rim segmentation (RimNet) branch and a disc size classification (DiscNet) branch to automate estimation of the disc damage likelihood scale (DDLS).

Design

Retrospective observational.

Participants

RimNet and DiscNet were developed with 1208 and 11 536 optic disc photographs (ODPs), respectively. DDLSNet performance was evaluated on 120 ODPs from the RimNet test set, for which the DDLS scores were graded by clinicians. Reproducibility was evaluated on a group of 781 eyes, each with 2 ODPs taken within 4 years apart.

Methods

Disc damage likelihood scale calculation requires estimation of optic disc size, provided by DiscNet (VGG19 network), and the minimum rim-to-disc ratio (mRDR) or absent rim width (ARW), provided by RimNet (InceptionV3/LinkNet segmentation model). To build RimNet's dataset, glaucoma specialists marked optic disc rim and cup boundaries on ODPs. The "ground truth" mRDR or ARW was calculated. For DiscNet's dataset, corresponding OCT images provided "ground truth" disc size. Optic disc photographs were split into 80/10/10 for training, validation, and testing, respectively, for RimNet and DiscNet. DDLSNet estimation was tested against manual grading of DDLS by clinicians with the average score used as "ground truth." Reproducibility of DDLSNet grading was evaluated by repeating DDLS estimation on a dataset of nonprogressing paired ODPs taken at separate times.

Main Outcome Measures

The main outcome measure was a weighted kappa score between clinicians and the DDLSNet pipeline with agreement defined as ± 1 DDLS score difference.

Results

RimNet achieved an mRDR mean absolute error (MAE) of 0.04 (± 0.03) and an ARW MAE of 48.9 (± 35.9) degrees when compared to clinician segmentations. DiscNet achieved 73% (95% confidence interval [CI]: 70%, 75%) classification accuracy. DDLSNet achieved an average weighted kappa agreement of 0.54 (95% CI: 0.40, 0.68) compared to clinicians. Average interclinician agreement was 0.52 (95% CI: 0.49, 0.56). Reproducibility testing demonstrated that 96% of ODP pairs had a difference of ≤ 1 DDLS score.

Conclusions

DDLSNet achieved moderate agreement with clinicians for DDLS grading. This novel approach illustrates the feasibility of automated ODP grading for assessing glaucoma severity. Further improvements may be achieved by increasing the number of incomplete rims sample size, expanding the hyperparameter search, and increasing the agreement of clinicians grading ODPs.

RimNet: A Deep Neural Network Pipeline for Automated Identification of the Optic Disc Rim

Purpose

Accurate neural rim measurement based on optic disc imaging is important to glaucoma severity grading and often performed by trained glaucoma specialists. We aim to improve upon existing automated tools by building a fully automated system (RimNet) for direct rim identification in glaucomatous eyes and measurement of the minimum rim-to-disc ratio (mRDR) in intact rims, the angle of absent rim width (ARW) in incomplete rims, and the rim-to-disc-area ratio (RDAR) with the goal of optic disc damage grading.

Design

Retrospective cross sectional study.

Participants

One thousand and twenty-eight optic disc photographs with evidence of glaucomatous optic nerve damage from 1021 eyes of 903 patients with any form of primary glaucoma were included. The mean age was 63.7 (± 14.9) yrs. The average mean deviation of visual fields was -8.03 (± 8.59).

Methods

The images were required to be of adequate quality, have signs of glaucomatous damage, and be free of significant concurrent pathology as independently determined by glaucoma specialists. Rim and optic cup masks for each image were manually delineated by glaucoma specialists. The database was randomly split into 80/10/10 for training, validation, and testing, respectively. RimNet consists of a deep learning rim and cup segmentation model, a computer vision mRDR measurement tool for intact rims, and an ARW measurement tool for incomplete rims. The mRDR is calculated at the thinnest rim section while ARW is calculated in regions of total rim loss. The RDAR was also calculated. Evaluation on the Drishti-GS dataset provided external validation (Sivaswamy 2015).

Main Outcome Measures

Median Absolute Error (MAE) between glaucoma specialists and RimNet for mRDR and ARW.

Results

On the test set, RimNet achieved a mRDR MAE of 0.03 (0.05), ARW MAE of 31 (89)°, and an RDAR MAE of 0.09 (0.10). On the Drishti-GS dataset, an mRDR MAE of 0.03 (0.04) and an mRDAR MAE of 0.09 (0.10) was observed.

Conclusions

RimNet demonstrated acceptably accurate rim segmentation and mRDR and ARW measurements. The fully automated algorithm presented here would be a valuable component in an automated mRDR-based glaucoma grading system. Further improvements could be made by improving identification and segmentation performance on incomplete rims and expanding the number and variety of glaucomatous training images.

Referrals from community optometrists in England and their replies: A mixed methods study

PURPOSE

Community optometrists, through routine eye examinations, identify patients with disease or ocular abnormalities requiring referral to the Hospital Eye Service. In many cases no reply to the referral letter is received, resulting in some patients being re-referred unnecessarily, potentially increasing the number of other patients who lose sight whilst on hospital waiting lists. This study investigated, qualitatively and quantitatively, factors influencing optometric referrals and replies.

METHODS

The three-phase, sequential mixed methods study started with a literature review and qualitative phase, interviewing stakeholders to identify issues for exploration in subsequent phases. The second, quantitative phase, undertook documentary analysis of 349 patient referral records from three optometric practice modalities (domiciliary, independently owned, and corporate chain) in England. A final qualitative phase obtained views from stakeholders to explore unexplained findings from the first two phases.

RESULTS

Phase 1 identified communication, financial, professional and technological issues for further exploration. In Phase 2, the referral rate was 22.2% for domiciliary provider, 2.1% for independent practice and 2.5% for the corporate chain, with the variation most likely explained by patient age and associated ophthalmic disease, illness and disability. The referral reply rate was 5.7% for domiciliary provider, 25.0% for independent practice and 4.9% for the corporate chain. The community optometrist remained unaware of the outcome of their referral in 72.8% of cases. Qualitative analyses indicate the main factors influencing referral reply rates are technology, the General Medical Practitioner, community optometrists' utility to and utility of the National Health Service and patient mobilisation.

CONCLUSIONS

The low referral reply rate creates a break in the feedback loop required to raise the standard of referrals and avoid unnecessary re-referral. Of the factors identified that influence referral reply rates, technology is key in view of the increasing use of online referral platforms. Feedback to the referring optometrist should be embedded in such systems.

Spotlight on the Disc-Damage Likelihood Scale (DDLS)

The disc damage likelihood scale (DDLS) is a tool for classifying glaucomatous structural changes to the optic disc based on the radial width of the neuroretinal rim at its thinnest location, or if no rim is present, the extent of absence of the rim. Unlike cup disc ratio (CDR), the DDLS also considers disc size. Twenty years after its first description, the aim of this review was to critically appraise evidence for the DDLS and evaluate its role in current practice. A literature search by two independent authors identified 33 relevant articles for inclusion. Five studies evaluated reproducibility, 5 diagnostic performance, and 2 studies examined ability to detect progression. Eleven studies evaluated correlation between DDLS and other markers of glaucoma. Despite the widespread availability of imaging devices such as optical coherence tomography (OCT), clinical examination of the optic disc remains an essential component of glaucoma diagnosis and monitoring. The DDLS provides a reliable method for semi-quantitative clinical grading of the optic disc in glaucoma, with higher reproducibility than methods such as CDR.