Selective fusion of structural and functional data for improved glaucoma detection

Supplementary Files

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
figure 7 a
Figure 7b

How to Cite

Kim PY, Iftekharuddin KM, Davey PG, Holló G, Tóth M, Garas A, Essock EA. Selective fusion of structural and functional data for improved glaucoma detection. MAIO [Internet]. 2017 Jun. 19 [cited 2021 Dec. 9];1(3):82-99. Available from:

Copyright notice

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication, with the work twelve (12) months after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work’s authorship and initial publication in this journal.

  2. After 12 months from the date of publication, authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.


scanning laser polarimetry (SLP); standard automated perimetry; fusion; glaucoma detection; selective fusion; sectoral topographic correspondence; retinal nerve fiber layer (RNFL); fractal analysis (FA)


This work proposes novel selective feature fusion of structural and functional data for improved glaucoma detection. The structural data such as retinal nerve fiber layer (RNFL) thickness measurement acquired by scanning laser polarimetry (SLP) is fused with the functional visual field (VF) measurement recorded from the standard automated perimetry (SAP) test. The proposed selective feature fusion exploits correspondence between structural and functional data obtained over multiple sectors. The correlation coefficients for corresponding structural-function sector pairs are used as weights in subsequent feature selection. The sectors are ranked according to the correlation coefficients and the first four highly ranked sectors are retained. Following our prior work, fractal analysis (FA) features for both structural and functional data are obtained and fused for each selected sectors respectively. These fused FA features are then used for glaucoma detection. The novelty of this work stems from (i) locating structure-functional sectoral correspondence; (ii) selecting only a few interesting sector pairs using correlation coefficient between structure-function data; (iii) obtaining novel FA features from these pairs; and (iv) fusing these features for glaucoma detection. Such a method is distinctively different from other existing methods that exploit structure-function models in that structure-function sectoral correspondences have been weighted and, based on such weights, only portions of the sectors are retained for subsequent fusion and classification of structural and functional features. For statistical analysis of the glaucoma detection results, sensitivity, specificity and area under receiver operating characteristic curve (AUROC) are calculated. Performance comparison is obtained with those of existing feature-based techniques such as wavelet-Fourier analysis (WFA) and fast-Fourier analysis (FFA). Comparisons of AUROC values show that our novel selective feature fusion method for discrimination of glaucomatous and ocular normal patients slightly outperforms other existing techniques with AUROCs of 0.98, 0.98 and 0.99 for WFA, FFA and FA respectively.


Weinreb, R. N. and Khaw, P. T., “Primary open angle glaucoma,” Lancet, 363, 1711-1720 (2004).

Garway-Heath, D. F., Caprioli, J., Fitzke, F. W. and Hitchings, R. A., “Scaling the hill of vision: the physiological relationship between light sensitivity and ganglion cell numbers,” Invest Ophthalmol Vis Sci., Vol. 41, pp. 1774–1782, (2000).

Quigley, H. A., Miller, N. R. and George, T., “Clinical evaluation of nerve fiber layer atrophy as an indicator of glaucomatous optic nerve damage,” Arch Ophthalmol, 98, 1564-1571 (1980).

Quigley, H. A. and Addicks, E. M., “Quantitative studies of retinal nerve fiber layer defects,” Arch Ophthalmol, 100, 807-814 (1982).

Lauande-Pimentel, R., Carvalho, R. A., Oliveira, H. C., Gonçalves, D. C., Silva, L. M., and Costa, V. P., “Discrimination between normal and glaucomatous eyes with visual field and scanning laser polarimetry measurements,” Br. J. Ophthalmol. 85, 586-591, (2001).

Dersu, I. and Wiggins, M. N., “Understanding Visual Fields, Part II; Humphrey Visual Fields,” J. of Ophthalmic Medical Technology, 2(3), (2006).

Hood, D. and Kardon, R. H., “A framework for comparing structural and functional measures of glaucomatous damage,” Prog Retin Eye Res., 26(6), 688–710 Nov. (2007).

Hood, D., Anderson, S. C., Wall, M., Randy, H. and Kardon, R. H., “Structure versus Function in Glaucoma: An Application of a Linear Model,” Invest. Ophthalmol. Vis. Sci., 48(8), 3662-3668 Aug. (2007).

Harwerth, R. S., Wheat, J. L., Fredette, M. J., Anderson, D. R., “Linking structure and function in glaucoma,” Prog Retin Eye Res., 29(4), 249-71 (2010).

Drasdo, N., Mortlock, K. E., North, R. V., “Ganglion cell loss and dysfunction: relationship to perimetric sensitivity,” Optom Vis Sci. 85(11), 1036-1042 (2008).

Malik, R., Swanson, W. H., Garway-Heath, D. F., “Structure-function relationship’ in glaucoma: past thinking and current concepts,” Clin Experiment Ophthalmol, 40(4), 369-80 (2012).

Garway-Heath, D. F., Holder, G. E., Fitzke, F. W., and Hitchings, R. A., “Relationship between electrophysiological, psychophysical, and anatomical measurements in glaucoma.” Invest Ophthalmol Vis Sci., 43(7), 2213-20. (2002).

Reus, N. J, and Lemij, H. G., “The relationship between standard automated perimetry and GDx VCC measurements,” Invest Ophthalmol Vis Sci. 45(3), 840-5 (2004)

Sherman, J. Slotnick, S. and Boneta, J., “Discordance between structure and function in glaucoma: Possible anatomical explanations,” Optometry, 80, 487-501 (2009).

Horn, F. K., Mardin, C. Y., Laemmer, R., Baleanu, D., Juenemann, A. M., Kruse, F. E. and Tornow, R. P., “Correlation between Local Glaucomatous Visual Field Defects and Loss of Nerve Fiber Layer Thickness Measured with Polarimetry and Spectral Domain OCT,” Invest Ophthalmol Vis Sci., 50(5), 1971-1977, May. (2009).

Strouthidis, N. G., Vinciotti, V., Tucker, A. J., Gardiner, S. K., Crabb, D. P., and Garway-Heath, D. F., “Structure and Function in Glaucoma: The Relationship between a Functional Visual Field Map and an Anatomic Retinal Map,” Invest. Ophthalmol. Vis. Sci., Vol. 47(12), pp. 5356-5362, Dec., (2006).

Danesh-Meyer, H. V., Ku, J. Y. F., Papchenko, T. L., Jayasundera, T., Hsiang, J. C. and Gamble, G. D., “Regional Correlation of Structure and Function in Glaucoma, Using the Disc Damage Likelihood Scale, Heidelberg Retina Tomograph, and Visual Fields,” Ophthalmology, 113(4), 603-611, Apr. (2006).

Shah, N. N., Bowd, C., Medeiros, F. A., Weinreb, R. N., Sample, P. A., Hoffmann, E. M. and Zangwill, L. M., “Combining Structural and Functional Testing for Detection of Glaucoma,” Ophthalmology, 113, 1593-1602 (2006).

Horn, F. K., Mardin, C. Y., Bendschneider, D., Jünemann, A. G., Adler, W., and Tornow, R. P., “Frequency doubling technique perimetry and spectral domain optical coherence tomography in patients with early glaucoma,” Eye (Lond). 25(1), pp. 17-29 (2011).

Bizios, D., Heijl, A., and Bengtsson, B., “Integration and fusion of standard automated perimetry and optical coherence tomography data for improved automated glaucoma diagnostics,” BMC Ophthalmology, 11(20) (2011).

Yousefi, S., Goldbaum, M. H., Balasubramanian, M., Jung, T. P., Weinreb, R. N., Medeiros, F. A., Zangwill, L. M., Liebmann, J. M., Girkin, C. A. and Bowd, C., “Glaucoma Progression Detection Using Structural Retinal Nerve Fiber Layer Measurements and Functional Visual Field Points,” IEEE Trans. On Biomedical Engineering, 61(4), 1143-1154 (2014)

Kim, P. Y., Iftekharuddin, K. M., Davey, P. G., Tóth, M., Garas, A., Holló, G. and Essock, E. A., “Novel Fractal Feature-Based Multiclass Glaucoma Detection and Progression Prediction,” IEEE Jour. of Biomedical and Health Informatics, 17(2), 269-276 (2013)

Ferreras, A., Pablo, L. E., Garway-Heath, D. F., Fogagnolo, P., and Garcıa-Feijoo, J., “Mapping Standard Automated Perimetry to the Peripapillary Retinal Nerve Fiber Layer in Glaucoma,” Invest. Ophthalmol. Vis. Sci., Vol. 49 (7), pp. 3018-3025, Jul., (2008).

Holló, G, Naghizadeh, F., “Evaluation of Octopus Polar Trend Analysis for detection of glaucomatous progression,” Eur J Ophthalmol (2014), DOI: 10.5301/ejo.5000504.

Ahmed, S. and Iftekharuddin, K. M., “Discrimination of medulloblastoma and low grade astrocytoma PF tumors using selected MR image features,” MemBis 2008, (2008).

Zook, J. M. and Iftekharuddin, K. M., “Statistical analysis of fractal-based brain tumor detection algorithms,” Magnetic Resonance Imaging, 23, 671-678 (2005).

EyeSuite Application Note, Follow up from HFA with Octopus accessed 08/08/2016

Essock, E. A., Zheng, Y. and Gunvant, P., Analysis of GDx-VCC Polarimetry Data by Wavelet-Fourier Analysis across Glaucoma Stages, Invest Ophtalmol Vis Sci, 46(8) Aug. (2005).