본문 바로가기
KERD
논문KCI 등재

Spatial and Temporal Characteristics of Visual Field Progression in Glaucoma Assessed by Parallel Factor Analysis

1

조회

0

다운로드

0

인용

0

참고문헌

키워드

주제분류안과학

초록

Purpose: To explore spatial and temporal characteristics of glaucomatous visual field (VF) progression throughmulti-way decomposition of data. Methods: Six serial VF exams with intervals of 6.0 ± 1.0 months in 121 pre-perimetric glaucoma eyes and 80perimetric glaucoma eyes were arranged into a three-dimensional cube. The data were decomposed usingparallel factor analysis. Results: Three tri-linear components (i.e., spatial scores, temporal loadings, and subject-specific loadings) wereidentified. Component 1 clearly showed differences between superior and inferior hemispheres, linear trendsover time, and wide variability in perimetric glaucoma. Findings were compatible with well-known characteristicsof glaucomatous VF defects. Component 2 showed nasal and central areas in contrast with superior, inferior,and temporal peripheral locations, whereas component 3 showed a contrast between nasal and temporalhemispheres. Both components 2 and 3 failed to show clear temporal trends. Conclusions: Identification of spatio-temporal patterns shows new possibilities for a multi-way decompositionmethodology for earlier diagnosis and prediction of glaucomatous VF progression.

Abstract

Purpose: To explore spatial and temporal characteristics of glaucomatous visual field (VF) progression throughmulti-way decomposition of data. Methods: Six serial VF exams with intervals of 6.0 ± 1.0 months in 121 pre-perimetric glaucoma eyes and 80perimetric glaucoma eyes were arranged into a three-dimensional cube. The data were decomposed usingparallel factor analysis. Results: Three tri-linear components (i.e., spatial scores, temporal loadings, and subject-specific loadings) wereidentified. Component 1 clearly showed differences between superior and inferior hemispheres, linear trendsover time, and wide variability in perimetric glaucoma. Findings were compatible with well-known characteristicsof glaucomatous VF defects. Component 2 showed nasal and central areas in contrast with superior, inferior,and temporal peripheral locations, whereas component 3 showed a contrast between nasal and temporalhemispheres. Both components 2 and 3 failed to show clear temporal trends. Conclusions: Identification of spatio-temporal patterns shows new possibilities for a multi-way decompositionmethodology for earlier diagnosis and prediction of glaucomatous VF progression.

참고문헌 (36)

  1. Goldbaum MH, "Unsupervised learning with independent component analysis can identify patterns of glaucomatous visual field defects", Trans Am Ophthalmol Soc, 103, pp.270~280 (2005)
  2. Asman P, "Glaucoma hemifield test : automated visual field evaluation", Arch Ophthalmol, 110, pp.812~819 (1992)
  3. Marin-Franch I, "A novel strategy for the estimation of the general height of the visual field in patients with glaucoma", Graefes Arch Clin Exp Ophthalmol, 252, pp.801~809 (2014)
  4. Iester M, "Visual field loss morphology in high-and normal-tension glaucoma", J Ophthalmol, 2012, pp.327326~ (2012)
  5. Nouri-Mahdavi K, "Prediction of visual field progression in glaucoma", Invest Ophthalmol Vis Sci, 45, pp.4346~4351 (2004)
  6. Wilkins MR, "Pointwise linear progression criteria and the detection of visual field change in a glaucoma trial", Eye(Lond), 20, pp.98~106 (2006)
  7. De Moraes CG, "Examination of the performance of different pointwise linear regression progression criteria to detect glaucomatous visual field change", Clin Exp Ophthalmol, 40, pp.e190~e196 (2012)
  8. Viswanathan AC, "Early detection of visual field progression in glaucoma : a comparison of PROGRESSOR and STATPAC 2", Br J Ophthalmol, 81, pp.1037~1042 (1997)
  9. Caprioli J, "A method to measure and predict rates of regional visual field decay in glaucoma", Invest Ophthalmol Vis Sci, 52, pp.4765~4773 (2011)
  10. Bengtsson B, "A visual field index for calculation of glaucoma rate of progression", Am J Ophthalmol, 145, pp.343~353 (2008)
  11. Cho JW, "Progression detection in different stages of glaucoma : mean deviation versus visual field index", Jpn J Ophthalmol, 56, pp.128~133 (2012)
  12. Bengtsson B, "Prediction of glaucomatous visual field loss by extrapolation of linear trends", Arch Ophthalmol, 127, pp.1610~1615 (2009)
  13. Nouri-Mahdavi K, "Pointwise rates of visual field progression cluster according to retinal nerve fiber layer bundles", Invest Ophthalmol Vis Sci, 53, pp.2390~2394 (2012)
  14. Strouthidis NG, "Structure and function in glaucoma : the relationship between a functional visual field map and an anatomic retinal map", Invest Ophthalmol Vis Sci, 47, pp.5356~5362 (2006)
  15. Quigley HA, "Retinal ganglion cell atrophy correlated with automated perimetry in human eyes with glaucoma", Am J Ophthalmol, 107, pp.453~464 (1989)
  16. Yousefi S, "Learning from data : recognizing glaucomatous defect patterns and detecting progression from visual field measurements", IEEE Trans Biomed Eng, 61, pp.2112~2124 (2014)
  17. Bresson-Dumont H, "Visual field progression in glaucoma : cluster analysis", J Fr Ophtalmol, 35, pp.735~741 (2012)
  18. Pascual JP, "Spatial characteristics of visual field progression determined by Monte Carlo simulation : diagnostic innovations in glaucoma study", Invest Ophthalmol Vis Sci, 48, pp.1642~1650 (2007)
  19. Carroll JD, "Analysis of individual differences in multidimensional scaling via an N-way generalization of “Eckart-Young” decomposition", Psychometrika, 35, pp.283~319 (1970)
  20. Foundations of the PARAFAC procedure:models and conditions for an” explanatory” multimodal factor analysis, "Harshman RA", University of California at Los Angeles, 1~84 (1970)
  21. Bro R, "PARAFAC : tutorial and applications", Chemom Intell Lab Syst, 38, pp.149~171 (1997)
  22. Deburchgraeve W, "Neonatal seizure localization using PARAFAC decomposition", Clin Neurophysiol, 120, pp.1787~1796 (2009)
  23. Miwakeichi F, "Decomposing EEG data into space-time-frequency components using Parallel Factor Analysis", Neuroimage, 22, pp.1035~1045 (2004)
  24. Beckmann CF, "Tensorial extensions of independent component analysis for multisubject FMRI analysis", Neuroimage, 25, pp.294~311 (2005)
  25. Martinez-Montes E, "Concurrent EEG", fMRI analysis by multiway Partial Least Squares, 2004, pp.22, 1023~1034
  26. Paolo Giordani, "Three-Way Component Analysis Using the R Package ThreeWay", Journal of Statistical Software, 57(7) (2014), Foundation for Open Access Statistic[DOI]
  27. Kruskal JB, "Three-way arrays : rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics", Linear Algebra Appl, 18, pp.95~138 (1977)
  28. "ThreeWay: threeway component analysis (version 1.1.3)" (2015)[URL]
  29. He B, "Multimodal functional neuroimaging : integrating functional MRI and EEG", MEG, 2008, pp.1, 23~40
  30. Varoquaux G, "A group model for stable multi-subject ICA on fMRI datasets", Neuroimage, 51, pp.288~299 (2010)
  31. Robinson SD, "ICA of f MRI studies : new approaches and cutting edge applications", Front Hum Neurosci, 7, pp.724~ (2013)
  32. Sui J, "Discriminating schizophrenia and bipolar disorder by fusing f MRI and DTI in a multimodal CCA+ joint ICA model", Neuroimage, 57, pp.839~855 (2011)
  33. Weis M, "Multi-dimensional PARAFAC2 component analysis of multi-channel EEG data including temporal tracking", Conf Proc IEEE Eng Med Biol Soc, 2010, pp.5375~5378 (2010)
  34. De Moraes CG, "Effect of treatment on the rate of visual field change in the ocular hypertension treatment study observation group", Invest Ophthalmol Vis Sci, 53, pp.1704~1709 (2012)
  35. Lee JR, "Discrepancy between optic disc and nerve fiber layer assessment and optical coherence tomography in detecting glaucomatous progression", Jpn J Ophthalmol, 57, pp.546~552 (2013)
  36. Na JH, "Rates a nd patterns of macular and circumpapillary retinal nerve fiber layer thinning in preperimetric and perimetric glaucomatous eyes", J Glaucoma, 24, pp.278~285 (2015)

관련 논문AI추천

이 간행물의 다른 논문 (14건)