Application of Pattern Recognition Analysis to Optimize Hemifield Asymmetry Patterns for Early Detection of Glaucoma

Purpose To assess the diagnostic utility of a new hemifield asymmetry analysis derived using pattern recognition contrast sensitivity isocontours (CSIs) within the Humphrey Field Analyzer (HFA) 24-2 visual field (VF) test grid. The performance of an optimal CSI-derived map was compared against a commercially available clustering method (Glaucoma Hemifield Test, GHT). Methods Five hundred VF results of 116 healthy subjects were used to determine normative distribution limits for comparisons. Pattern recognition analysis was applied to HFA 24-2 sensitivity data to determine CSI theme maps delineating clusters for hemifield comparisons. Then, 1019 VF results from 228 glaucoma patients were assessed using different clustering methods to determine the true-positive rate. We also assessed additional 354 VF results of 145 healthy subjects to determine the false-positive rate. Results The optimum clustering method was the CSI-derived seven-theme class map, which identified more glaucomatous VFs compared with the GHT map. The seven-class theme map also identified more cases compared with the five-, six-, and eight-class maps, suggesting no effect of number of clusters. Integrating information regarding the location of glaucomatous defects to the CSI clusters did not improve detection rate. Conclusions A clustering map derived using CSIs improved detection of glaucomatous VFs compared with the currently available GHT. An optimized CSI-derived map may serve as an additional means to aid earlier detection of glaucoma. Translational Relevance Pattern recognition–derived theme maps provide a means for guiding test point selection for asymmetry analysis in glaucoma assessment.

[1]  Teresa C. Chen,et al.  Assessment of visual function in glaucoma: a report by the American Academy of Ophthalmology. , 2011, Ophthalmology.

[2]  Ziyad Mahfoud,et al.  What Is an Intracluster Correlation Coefficient? Crucial Concepts for Primary Care Researchers , 2004, The Annals of Family Medicine.

[3]  C. Kee,et al.  Initial central scotomas vs peripheral scotomas in normal-tension glaucoma: clinical characteristics and progression rates , 2014, Eye.

[4]  B. Bengtsson,et al.  Evaluation of a new threshold visual field strategy, SITA, in normal subjects. Swedish Interactive Thresholding Algorithm. , 1998, Acta ophthalmologica Scandinavica.

[5]  M. Brusco,et al.  Evaluating mixture modeling for clustering: recommendations and cautions. , 2011, Psychological methods.

[6]  A. Zalta.  Lens rim artifact in automated threshold perimetry. , 1989, Ophthalmology.

[7]  Sieu K. Khuu,et al.  Equating spatial summation in visual field testing reveals greater loss in optic nerve disease , 2016, Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians.

[8]  Dong Myung Kim,et al.  Preperimetric normal tension glaucoma study: long‐term clinical course and effect of therapeutic lowering of intraocular pressure , 2014, Acta ophthalmologica.

[9]  Mounir Mesbah,et al.  Scoring of visual field measured through Humphrey perimetry: principal component varimax rotation followed by validated cluster analysis. , 2005, Investigative ophthalmology & visual science.

[10]  Shigeki Hashimoto,et al.  The interpretation of results of 10-2 visual fields should consider individual variability in the position of the optic disc and temporal raphe , 2017, British Journal of Ophthalmology.

[11]  Robert Ritch,et al.  The ISNT rule and differentiation of normal from glaucomatous eyes. , 2006, Archives of ophthalmology.

[12]  G. Holder,et al.  Relationship between electrophysiological, psychophysical, and anatomical measurements in glaucoma. , 2002, Investigative ophthalmology & visual science.

[13]  J. Jonas,et al.  The Proportion of Individuals Likely to Benefit from Customized Optic Nerve Head Structure-Function Mapping. , 2017, Ophthalmology.

[14]  A. Sommer,et al.  Repeatability of the Glaucoma Hemifield Test in automated perimetry. , 1995, Investigative ophthalmology & visual science.

[15]  M Araie,et al.  Sectorization of the central 30 degrees visual field in glaucoma. , 1993, Ophthalmology.

[16]  Dong Myung Kim,et al.  Long-term follow-up in preperimetric open-angle glaucoma: progression rates and associated factors. , 2015, American journal of ophthalmology.

[17]  D. Cicchetti.  Guidelines, Criteria, and Rules of Thumb for Evaluating Normed and Standardized Assessment Instruments in Psychology. , 1994 .

[18]  R E Marc,et al.  Pattern recognition of amino acid signatures in retinal neurons , 1995, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[19]  S. Takagi,et al.  Macular Retinal Ganglion Cell Complex Damage in the Apparently Normal Visual Field of Glaucomatous Eyes With Hemifield Defects , 2012, Journal of glaucoma.

[20]  Sieu K Khuu,et al.  Reducing Spatial Uncertainty Through Attentional Cueing Improves Contrast Sensitivity in Regions of the Visual Field With Glaucomatous Defects , 2018, Translational vision science & technology.

[21]  B J Lachenmayr,et al.  Points of a normal visual field are not statistically independent. , 1995, German journal of ophthalmology.

[22]  Robert Ritch,et al.  Modifying the Conventional Visual Field Test Pattern to Improve the Detection of Early Glaucomatous Defects in the Central 10° , 2014, Translational vision science & technology.

[23]  Sieu K. Khuu,et al.  How Many Subjects are Needed for a Visual Field Normative Database? A Comparison of Ground Truth and Bootstrapped Statistics , 2018, Translational vision science & technology.

[24]  Siamak Yousefi,et al.  Detection of Longitudinal Visual Field Progression in Glaucoma Using Machine Learning. , 2018, American journal of ophthalmology.

[25]  M. Kalloniatis,et al.  Metabolic profiling of the mouse retina using amino acid signatures: Insight into developmental cell dispersion patterns , 2013, Experimental Neurology.

[26]  M. C. Leske,et al.  Factors for glaucoma progression and the effect of treatment: the early manifest glaucoma trial. , 2003, Archives of ophthalmology.

[27]  Sieu K Khuu,et al.  Visual Psychophysics and Physiological Optics Standard Automated Perimetry : Determining Spatial Summation and Its Effect on Contrast Sensitivity Across the Visual Field , 2015 .

[28]  Sieu K. Khuu,et al.  A comparison of Goldmann III, V and spatially equated test stimuli in visual field testing: the importance of complete and partial spatial summation , 2017, Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians.

[29]  Sieu K. Khuu,et al.  Pattern Recognition Analysis of Age-Related Retinal Ganglion Cell Signatures in the Human Eye , 2017, Investigative Ophthalmology and Visual Science.

[30]  T Zeyen,et al.  An evaluation of clusters in the glaucomatous visual field. , 1993, American journal of ophthalmology.

[31]  R. Anderson,et al.  Sensitivity loss in early glaucoma can be mapped to an enlargement of the area of complete spatial summation. , 2010, Investigative ophthalmology & visual science.

[32]  Robert N Weinreb,et al.  Structure-function Relationships Using the Cirrus Spectral Domain Optical Coherence Tomograph and Standard Automated Perimetry , 2012, Journal of glaucoma.

[33]  Alan Agresti,et al.  Effects and non‐effects of paired identical observations in comparing proportions with binary matched‐pairs data , 2004, Statistics in medicine.

[34]  Robert Ritch,et al.  A Test of a Model of Glaucomatous Damage of the Macula With High-Density Perimetry: Implications for the Locations of Visual Field Test Points. , 2014, Translational vision science & technology.

[35]  Petter Laake,et al.  Recommended tests and confidence intervals for paired binomial proportions , 2014, Statistics in medicine.

[36]  A. Hayen,et al.  Clinical model assisting with the collaborative care of glaucoma patients and suspects , 2015, Clinical & experimental ophthalmology.

[37]  Allison M McKendrick,et al.  Orientation of the Temporal Nerve Fiber Raphe in Healthy and in Glaucomatous Eyes. , 2017, Investigative ophthalmology & visual science.

[38]  Sieu K. Khuu,et al.  The Effect of Attentional Cueing and Spatial Uncertainty in Visual Field Testing , 2016, PloS one.

[39]  K. Woodward,et al.  The effect of attention on conventional automated perimetry and luminance size threshold perimetry. , 2004, Investigative ophthalmology & visual science.

[40]  Sieu K. Khuu,et al.  Pattern Recognition Analysis Reveals Unique Contrast Sensitivity Isocontours Using Static Perimetry Thresholds Across the Visual Field , 2017, Investigative ophthalmology & visual science.

[41]  Richard A. Russell,et al.  The United Kingdom Glaucoma Treatment Study: a multicenter, randomized, placebo-controlled clinical trial: design and methodology. , 2013, Ophthalmology.

[42]  A Heijl,et al.  Glaucoma Hemifield Test. Automated visual field evaluation. , 1992, Archives of ophthalmology.

[43]  Richard A. Russell,et al.  The influence of intersubject variability in ocular anatomical variables on the mapping of retinal locations to the retinal nerve fiber layer and optic nerve head. , 2013, Investigative ophthalmology & visual science.

[44]  William H Swanson,et al.  Choice of Stimulus Range and Size Can Reduce Test-Retest Variability in Glaucomatous Visual Field Defects. , 2014, Translational vision science & technology.

[45]  Lucy Q. Shen,et al.  Clinical Correlates of Computationally Derived Visual Field Defect Archetypes in Patients from a Glaucoma Clinic , 2017, Current eye research.

[46]  Sieu K. Khuu,et al.  Physiologic statokinetic dissociation is eliminated by equating static and kinetic perimetry testing procedures. , 2016, Journal of vision.

[47]  Chris A Johnson,et al.  Baseline visual field characteristics in the ocular hypertension treatment study. , 2002, Ophthalmology.

[48]  Yasuo Ohashi,et al.  Sectorization of the Central 30° Visual Field in Glaucoma , 1993 .

[49]  Jost B. Jonas,et al.  Diagnosis and pathogenesis of glaucomatous optic neuropathy: morphological aspects1 1 1 1Supported by Deutsche Forschungsgemeinschaft (SFB 539) , 2000, Progress in Retinal and Eye Research.

[50]  Pádraig J. Mulholland,et al.  Spatiotemporal Summation of Perimetric Stimuli in Early Glaucoma. , 2015, Investigative ophthalmology & visual science.

[51]  G. Lindgren,et al.  Normal variability of static perimetric threshold values across the central visual field. , 1987, Archives of ophthalmology.

[52]  Sieu K. Khuu,et al.  Consistency of Structure-Function Correlation Between Spatially Scaled Visual Field Stimuli and In Vivo OCT Ganglion Cell Counts. , 2018, Investigative ophthalmology & visual science.

[53]  Stuart K. Gardiner,et al.  Detection of Functional Change Using Cluster Trend Analysis in Glaucoma , 2017, Investigative ophthalmology & visual science.

[54]  Jonathan Denniss,et al.  An anatomically customizable computational model relating the visual field to the optic nerve head in individual eyes. , 2012, Investigative ophthalmology & visual science.

[55]  P. H. Swain,et al.  Two effective feature selection criteria for multispectral remote sensing , 1973 .

[56]  Chris A. Johnson,et al.  Anatomy of a supergroup: does a criterion of normal perimetric performance generate a supernormal population? , 2003, Investigative ophthalmology & visual science.

[57]  Allison M McKendrick,et al.  Sampling the Visual Field Based on Individual Retinal Nerve Fiber Layer Thickness Profile. , 2018, Investigative ophthalmology & visual science.

[58]  Tobias Elze,et al.  Reversal of Glaucoma Hemifield Test Results and Visual Field Features in Glaucoma. , 2018, Ophthalmology.

[59]  Sieu K. Khuu,et al.  The value of visual field testing in the era of advanced imaging: clinical and psychophysical perspectives , 2017, Clinical & experimental optometry.

[60]  Nomdo M. Jansonius,et al.  A mathematical model for describing the retinal nerve fiber bundle trajectories in the human eye: average course, variability, and influence of refraction, optic disc size and optic disc position. , 2012, Experimental eye research.

[61]  M. Kalloniatis,et al.  Implementing collaborative care for glaucoma patients and suspects in Australia , 2018, Clinical & experimental ophthalmology.

[62]  R. P. Mills,et al.  Categorizing the stage of glaucoma from pre-diagnosis to end-stage disease. , 2006, American journal of ophthalmology-glaucoma.

[63]  Christopher Bowd,et al.  Learning From Data: Recognizing Glaucomatous Defect Patterns and Detecting Progression From Visual Field Measurements , 2014, IEEE Transactions on Biomedical Engineering.

[64]  Bettina Selig,et al.  Spatial pattern of glaucomatous visual field loss obtained with regionally condensed stimulus arrangements. , 2010, Investigative ophthalmology & visual science.

[65]  J. Jonas,et al.  Pattern of glaucomatous neuroretinal rim loss. , 1993, Ophthalmology.

[66]  William H Swanson,et al.  The Effect of Stimulus Size on the Reliable Stimulus Range of Perimetry. , 2015, Translational vision science & technology.

[67]  D B Henson,et al.  Spatial classification of glaucomatous visual field loss. , 1996, The British journal of ophthalmology.

[68]  Christopher Bowd,et al.  Unsupervised Gaussian Mixture-Model With Expectation Maximization for Detecting Glaucomatous Progression in Standard Automated Perimetry Visual Fields , 2016, Translational vision science & technology.

[69]  Hiroshi Murata,et al.  The Usefulness of Gaze Tracking as an Index of Visual Field Reliability in Glaucoma Patients. , 2015, Investigative ophthalmology & visual science.

[70]  Parham Azarbod,et al.  Location of Initial Visual Field Defects in Glaucoma and Their Modes of Deterioration. , 2015, Investigative ophthalmology & visual science.

[71]  R. Marc,et al.  Amino Acid Signatures in the Primate Retina , 1996, The Journal of Neuroscience.

[72]  E. Bradley,et al.  Comparison of Automated and Manual Perimetry in Patients With Blepharoptosis , 2005, Ophthalmic plastic and reconstructive surgery.

[73]  B. Bengtsson,et al.  Inter-subject variability and normal limits of the SITA Standard, SITA Fast, and the Humphrey Full Threshold computerized perimetry strategies, SITA STATPAC. , 1999, Acta ophthalmologica Scandinavica.

[74]  J. Vermunt.  K-means may perform as well as mixture model clustering but may also be much worse: comment on Steinley and Brusco (2011). , 2011, Psychological methods.