Machine Learning-Guided Prediction of Central Anterior Chamber Depth Using Slit Lamp Images from a Portable Smartphone Device

Assessment of angle closure disease in the age of artificial intelligence: A review

Primary angle closure glaucoma is a visually debilitating disease that is under-detected worldwide. Many of the challenges in managing primary angle closure disease (PACD) are related to the lack of convenient and precise tools for clinic-based disease assessment and monitoring. Artificial intelligence (AI)- assisted tools to detect and assess PACD have proliferated in recent years with encouraging results. Machine learning (ML) algorithms that utilize clinical data have been developed to categorize angle closure eyes by disease mechanism. Other ML algorithms that utilize image data have demonstrated good performance in detecting angle closure. Nonetheless, deep learning (DL) algorithms trained directly on image data generally outperformed traditional ML algorithms in detecting PACD, were able to accurately differentiate between angle status (open, narrow, closed), and automated the measurement of quantitative parameters. However, more work is required to expand the capabilities of these AI algorithms and for deployment into real-world practice settings. This includes the need for real-world evaluation, establishing the use case for different algorithms, and evaluating the feasibility of deployment while considering other clinical, economic, social, and policy-related factors.

[Corneal endothelial cell photography: comparison of smartphones]

BACKGROUND

The documentation of ophthalmologic findings using smartphone photography can confirm diagnoses and enable follow-up assessments in outpatient care. Photographing corneal endothelial cells using a smartphone on a slit lamp is complex for both smartphone and examiner. Smartphone models differ in their ability to quickly and safely take images of the corneal endothelium.

AIM OF THIS WORK

In this paper different smartphone models are presented with respect to their applicability for corneal endothelial cell photography and success factors for good smartphone imaging are described.

MATERIAL AND METHODS

In a cross-sectional study, a selection of 16 different smartphone models were compared with respect to their use in corneal endothelial cell photography. The smartphones were attached to the slit lamp eyepiece using an adjustable adapter. It was tested whether high-quality endothelial cell images of healthy subjects could be obtained within 3 min using the standard photo app of the respective smartphone. In addition, the subjective difficulty of creating the image was recorded. Factors contributing to successful imaging of corneal endothelial cells were summarized in a figure.

RESULTS AND DISCUSSION

Distinct differences regarding feasibility and quality of endothelial cell photography were detected between the different smartphones. Not every smartphone is suitable for endothelial cell photography.

From 2 dimensions to 3rd dimension: Quantitative prediction of anterior chamber depth from anterior segment photographs via deep-learning

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 (R2), 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; R2 = 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; R2 = 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.

Assessing the subjective quality of smartphone anterior segment photography: a non-inferiority study

PURPOSE

To assess the subjective quality of anterior segment photos taken from a smartphone camera adapted to the slit lamp compared to a commercial inbuilt slit-lamp camera.

METHODS

Non-inferiority study. Five paired images of the anterior segment of normal eyes were taken using an iPhone 11 (Apple, Inc., Calif., USA) camera attached to a universal slit-lamp adaptor and a commercial inbuilt slit-lamp camera (Haag-Streit Diagnostics, Bern, Switzerland). Images were collated into a survey in which ophthalmology students, residents, registrars, and consultants participated to select the image taken from the inbuilt slit-lamp camera. If the image quality was subjectively indistinguishable, we expected a 50:50 split for each photograph that was presented. We selected a 10% non-inferiority margin, with the hypothesis that no less than 40% of images believed to be from the conventional camera were in fact from the smartphone camera.

RESULTS

There were 27 respondents in the survey: ophthalmology consultants (n = 7), registrars (n = 10), residents (n = 7), intern (n = 1) and students (n = 2). The mean correct identification across the respondents was 11.3 out of 25 (45.2%) images. Overall, the smartphone camera was non-inferior to the inbuilt slit-lamp camera (p < 0.001). The non-inferiority of the smartphone camera was significant for consultants (47.4%, p < 0.01), registrars (47.6%, p < 0.001) and residents (37.7%, p < 0.0001).

CONCLUSIONS

Anterior segment images obtained with a smartphone camera were non-inferior to the commercial inbuilt slit-lamp camera. Smartphone cameras may be a non-inferior tool for communication of anterior segment images having implications for the ease of access to quality telehealth consultations.

Smartphone-Acquired Anterior Segment Images for Deep Learning Prediction of Anterior Chamber Depth: A Proof-of-Concept Study

Purpose

To develop a deep learning (DL) algorithm for predicting anterior chamber depth (ACD) from smartphone-acquired anterior segment photographs.

Methods

For algorithm development, we included 4,157 eyes from 2,084 Chinese primary school students (aged 11–15 years) from Mojiang Myopia Progression Study (MMPS). All participants had with ACD measurement measured with Lenstar (LS 900) and anterior segment photographs acquired from a smartphone (iPhone Xs), which was mounted on slit lamp and under diffuses lighting. The anterior segment photographs were randomly selected by person into training (80%, no. of eyes = 3,326) and testing (20%, no. of eyes = 831) dataset. We excluded participants with intraocular surgery history or pronounced corneal haze. A convolutional neural network was developed to predict ACD based on these anterior segment photographs. To determine the accuracy of our algorithm, we measured the mean absolute error (MAE) and coefficient of determination (R²) were evaluated. Bland Altman plot was used to illustrate the agreement between DL-predicted and measured ACD values.

Results

In the test set of 831 eyes, the mean measured ACD was 3.06 ± 0.25 mm, and the mean DL-predicted ACD was 3.10 ± 0.20 mm. The MAE was 0.16 ± 0.13 mm, and R² was 0.40 between the predicted and measured ACD. The overall mean difference was −0.04 ± 0.20 mm, with 95% limits of agreement ranging between −0.43 and 0.34 mm. The generated saliency maps showed that the algorithm mainly utilized central corneal region (i.e., the site where ACD is clinically measured typically) in making its prediction, providing further plausibility to the algorithm's prediction.

Conclusions

We developed a DL algorithm to estimate ACD based on smartphone-acquired anterior segment photographs. Upon further validation, our algorithm may be further refined for use as a ACD screening tool in rural localities where means of assessing ocular biometry is not readily available. This is particularly important in China where the risk of primary angle closure disease is high and often undetected.

Applications of Artificial Intelligence in Myopia: Current and Future Directions

With the continuous development of computer technology, big data acquisition and imaging methods, the application of artificial intelligence (AI) in medical fields is expanding. The use of machine learning and deep learning in the diagnosis and treatment of ophthalmic diseases is becoming more widespread. As one of the main causes of visual impairment, myopia has a high global prevalence. Early screening or diagnosis of myopia, combined with other effective therapeutic interventions, is very important to maintain a patient's visual function and quality of life. Through the training of fundus photography, optical coherence tomography, and slit lamp images and through platforms provided by telemedicine, AI shows great application potential in the detection, diagnosis, progression prediction and treatment of myopia. In addition, AI models and wearable devices based on other forms of data also perform well in the behavioral intervention of myopia patients. Admittedly, there are still some challenges in the practical application of AI in myopia, such as the standardization of datasets; acceptance attitudes of users; and ethical, legal and regulatory issues. This paper reviews the clinical application status, potential challenges and future directions of AI in myopia and proposes that the establishment of an AI-integrated telemedicine platform will be a new direction for myopia management in the post-COVID-19 period.