Functional visual fields: a cross-sectional UK study to determine which visual field paradigms best reflect difficulty with mobility function

Predicting 60-4 visual field tests using 3D facial reconstruction

BACKGROUND

Despite, the potential clinical utility of 60-4 visual fields, they are not frequently used in clinical practice partly, due to the purported impact of facial contour on field defects. The purpose of this study was to design and test an artificial intelligence-driven platform to predict facial structure-dependent visual field defects on 60-4 visual field tests.

METHODS

Subjects with no ocular pathology were included. Participants were subject to optical coherence tomography, 60-4 Swedish interactive thresholding algorithm visual field tests and photography. The predicted visual field was compared with observed 60-4 visual field results in subjects. Average and point-specific sensitivity, specificity, precision, negative predictive value, accuracy, and F1-scores were primary outcome measures.

RESULTS

30 healthy were enrolled. Three-dimensional facial reconstruction using a convolution neural network (CNN) was able to predict facial contour-dependent 60-4 visual field defects in 30 subjects without ocular pathology. Overall model accuracy was 97%±3% and 96%±3% and the F1-score, dependent on precision and sensitivity, was 58%±19% and 55%±15% for the right eye and left eye, respectively. Spatial-dependent model performance was observed with increased sensitivity and precision within the far inferior nasal field reflected by an average F1-score of 76%±20% and 70%±29% for the right eye and left eye, respectively.

CONCLUSIONS

This pilot study reports the development of a CNN-enhanced platform capable of predicting 60-4 visual field defects in healthy controls based on facial contour. Further study with this platform may enhance understanding of the influence of facial contour on 60-4 visual field testing.

Topical Review: Assessment of Binocular Sensory Processes in Low Vision

SIGNIFICANCE

This article summarizes the evidence for a higher prevalence of binocular vision dysfunctions in individuals with vision impairment. Assessment for and identification of binocular vision dysfunctions can detect individuals experiencing difficulties in activities including reading, object placement tasks, and mobility.Comprehensive vision assessment in low vision populations is necessary to identify the extent of remaining vision and to enable directed rehabilitation efforts. In patients with vision impairment, little attention is typically paid to assessments of binocular vision, including ocular vergence, stereopsis, and binocular summation characteristics. In addition, binocular measurements of threshold automated visual fields are not routinely performed in clinical practice, leading to an incomplete understanding of individuals' binocular visual field and may affect rehabilitation outcomes.First, this review summarizes the prevalence of dysfunctions in ocular vergence, stereopsis, and binocular summation characteristics across a variety of ocular pathologies causing vision impairment. Second, this review examines the links between clinical measurements of binocular visual functions and outcome measures including quality of life and performance in functional tasks. There is an increased prevalence of dysfunctions in ocular alignment, stereopsis, and binocular summation across low vision cohorts compared with those with normal vision. The identification of binocular vision dysfunctions during routine low vision assessments is especially important in patients experiencing difficulties in activities of daily living, including but not limited to reading, object placement tasks, and mobility. However, further research is required to determine whether addressing the identified deficits in binocular vision in low vision rehabilitative efforts directly impacts patient outcomes.