The distribution of visual field scores in a normal population. In: Greve EL, Heijl A, editors. Seventh International Visual Field Symposium, Amsterdam, September 1986. Dordrecht: Springer Netherlands; 1987. pp. 109-15. [DOI: 10.1007/978-94-009-3325-5_17]

Visual field analysis using artificial neural networks

There have been several reports on the application of artificial neural networks (ANNs) to visual field classification. While these have demonstrated that neural networks can be used with good results they have not explored the effects that the training set can have upon network performance nor emphasized the unique value of ANNs in visual field analysis. This paper considers the problem of differentiating normal and glaucomatous visual fields and explores different training set characteristics using field data collected from a Henson CFS2000 perimeter. Training set properties including size, balance between normals and glaucomas, extent of field loss and the spatial location of glaucomatous defects are explored. A multilayer network with 132 input nodes, 20 hidden layer nodes and 2 output nodes in trained using an error backpropagation algorithm. Both sensitivity and specificity are measured during testing. The results demonstrate that large random sets are better than small random sets since sensitivity improves with size and specificity is not adversely affected. The variability in performance also reduces as training set size increases. In addition, sets that are biased towards glaucoma examples are more sensitive and less specific, while sets biased with normal examples are more specific and less sensitive than balanced sets. Thus large training sets with class balance are generally desirable for good sensitivities and specificities. The actual glaucoma examples contained in the set are also important. A training set deficient in examples has no detrimental effect on sensitivity or specificity. The spatial distribution of defects is also crucial. Spatially biased sets are unable to recognize defects that occur in locations where no previous defect has been presented while more balanced sets lead to better performance. In conclusion the 'ideal' training set should contain many examples of early defects that represent the full range of locations where these defects may occur.

Effectiveness of unsupervised oculokinetic perimetry for detecting glaucomatous visual field defects

Oculokinetic perimetry (OKP) is a simple, inexpensive technique which was introduced primarily to promote more widespread use of visual field screening for glaucoma. The effectiveness of unsupervised OKP screening was evaluated using 145 non-glaucomatous patients and 64 patients with previously undiagnosed primary open angle glaucoma. Glaucoma cases were validated by the extended 132 point program on the Henson CFS2000 instrument. Both sample populations were representative of patients presenting for primary vision care. The effectiveness of the 26 point OKP test was compared with the 26 point Henson screening program. The results suggest that, in contrast to the Henson screening test (sensitivity = 85.1%, specificity = 93.8%), unsupervised OKP screening (sensitivity = 25.0%, specificity = 93.6%) has limited effectiveness for detecting glaucomatous visual field defects.

A cluster and scotoma analysis based on empiric criteria

From a collection of 288 visual fields of glaucomatous or glaucoma suspects, 30 were selected at random and were analyzed by one expert interpreter. Visual field damage varied from nonexistent to severe. The interpreter defined clusters or scotomas subjectively according to adjacency criteria: adjacent test locations which exceeded a critical loss value were grouped as clusters or scotomas. A computer algorithm has been devised which simulates such evaluation methods. In general, a standard setting of several parameters produced a cluster display containing the same number of clusters as determined by the expert interpreter. Another display mode grouped clusters according to polygonal areas of a predetermined size (Voronoi diagram). Due to the broad selection of visual field defects, the specificity of the program with regard to various field decay patterns was small and it should thus be applicable to a broad spectrum of glaucomatous field damage.

Usefulness of the Henson Central Field Screener for the detection of visual field defects, especially in glaucoma

The Henson Central Field Screener is a recently marketed, relatively inexpensive campimeter with semi-automated registration of responses. The strategy used is suprathreshold, eccentricity-compensated, multiple stimulus static perimetry. The clinical usefulness of this apparatus was tested in a number of glaucoma patients, glaucoma suspects and normals, as well as in subjects with other ocular disorders, for whom stable visual fields as tested with other perimeters were available. The results obtained with the Henson Screener are generally in agreement with the known defects. The apparatus has some drawbacks, however.

A cluster analysis for threshold perimetry

Cluster analysis in perimetry is a technique used in the evaluation of localised visual field loss. It has previously been applied to suprathreshold data and, unlike the indices currently available to indicate localised loss, it is influenced by the relative positions of individual defects. This paper describes a cluster analysis for use with data from Program 31 of the Octopus perimeter. To demonstrate the technique, sensitivity values of normal 60-year-old subject were altered to simulate localised loss. Illustrative examples of clinical cases are given, showing differing degrees of localised loss that do not influence the corrected loss variance (CLV) but influence the computed cluster parameters. It is hoped that the value of this form of analysis will be demonstrated in clinical follow-up of glaucoma patients.

Cluster analysis in visual field quantification

The central visual fields of 2165 normal and 106 glaucoma eyes were measured using a threshold related suprathreshold strategy. The effects of altering the cluster radius in normals and glaucoma eyes sheds light on the nature of defects in these two groups. It is estimated that approximately 13% of normals have clusters; the great majority of these individuals have one cluster of two defects. Most clusters in normals are formed artefactually due to angioscotoma and/or physiological variations in the blind spot position. Clusters due to other factors occur rarely. Clusters are found with equal frequencies in the superior and inferior fields in normal eyes, but with a greater frequency in the superior field in glaucoma eyes. The use of clusters in quantification is both sensitive and specific. Using results from this large sample and looking at other visual field properties, it is possible to devise weighted probability indices to score visual fields.