Reliable feature selection for automated angle closure glaucoma mechanism detection.

Glaucoma is an eye disease where a loss of vision occurs as a result of progressive optic nerve damage usually associates with high intraocular pressure. A subtype of glaucoma called primary angle-closure glaucoma (PACG) has been observed to be the result of one or more mechanisms such as Pupil block, Plateau iris, Peripheral iris roll, and Lens in the anterior segment of the eye. Reliable features in anterior segment images are important for determining the specific mechanisms involved in PACG. In this paper, first the discriminant features are selected by several feature selection algorithms in the context of PACG detection based on anterior segment optical coherence tomography (AS-OCT) images, and then a novel criteria is proposed to further select more reliable features. Our approach is based on selecting the top-ranked features in each algorithm and its rank combination for selection of the best features. Compared with the features selected by the individual feature selection methods, the features selected by our method achieves the best performance in terms of the accuracy of classification of the four PACG mechanisms by using AdaBoost classifier.

Changes in retinal nerve fibre layer, optic nerve head morphology, and visual field after acute primary angle closure.

AIMS/PURPOSE: To determine and correlate the long-term changes in retinal nerve fibre layer (RNFL) thickness, optic nerve head (ONH) morphology, and visual fields after a single episode of acute primary angle closure (APAC). METHODS: This was a cross-sectional comparative study of patients at National University Hospital (Singapore) from 2000 to 2006 after an episode of unilateral APAC. The peripapillary and macular RNFL were measured using Stratus optical coherence tomography (OCT) and ONH configuration was assessed using Heidelberg Retina Tomography (HRT)-III. Humphrey perimetry was also performed, and the presence of disc pallor was noted. APAC eyes were compared with fellow eyes as matched controls. RESULTS: Twenty-five patients were assessed at a median of 33 months (range, 11-85 months) after APAC. OCT showed that there was a reduction in the peripapillary and outer macular RNFL thickness in APAC eyes compared with controls. Humphrey perimetry revealed significantly reduced mean deviation (P=0.006) and increased pattern standard deviation (P=0.045) in APAC eyes compared with controls. HRT-III showed no difference in mean rim area, rim volume, or cup-disc ratio between APAC eyes and controls. Disc pallor was present in nine APAC eyes (36%) but was absent in fellow eyes (P=0.002), and was associated with peripapillary RNFL thinning, visual field loss, and an increased interval between the onset of symptoms and normalization of intraocular pressure (P=0.023). CONCLUSION: APAC results in peripapillary and outer macular RNFL loss, visual field defects, and optic disc pallor, even in cases in which the ONH configuration remains unchanged.

Degree of angle closure and extent of peripheral anterior synechiae: an anterior segment OCT study.

AIMS: To evaluate the relationship between angle width as determined by anterior segment optical coherence tomography (AS-OCT) and the presence of peripheral anterior synechiae (PAS). METHODS: This was a prospective observational case series in which 203 subjects with primary angle closure or open angles were recruited. Images of the nasal, temporal and inferior angles were obtained with AS-OCT in dark conditions. Subjects then underwent gonioscopy by an independent examiner who was masked to the AS-OCT findings. PAS were identified by gonioscopy and defined as abnormal adhesions of the iris to the angle that were at least half a clock hour in width and present to the level of the anterior trabecular meshwork or higher. The total clock hours of PAS were recorded. RESULTS: Sixty-eight subjects (33.5%) were PACS, 76 subjects (37.4%) had PAC/PACG, 14 (6.9%) had primary open angle glaucoma, and 45 (22.2%) subjects were normal with open angles. There was a weak but significant correlation between the angle opening distance (AOD), trabecular iris space area (TISA) and angle recess area (ARA) with clock hours of PAS (Spearman's correlation coefficients = -0.30, -0.32 and -0.32, respectively, p<0.001). The mean values of the AOD, TISA and ARA in the nasal, temporal and inferior quadrants were significantly less in eyes with PAS compared with those without (p<0.001, Mann-Whitney U test). Analysis by quadrant showed that these parameters were smaller in the nasal and temporal quadrants in eyes with PAS (p<0.01). CONCLUSIONS: Angle width determined by AS-OCT and the extent of PAS were weakly correlated, and angle width was significantly smaller in eyes with PAS.

Experience with ARRAY multifocal lenses in a Singapore population.

INTRODUCTION: To evaluate the clinical efficiency, safety and subjective visual outcomes of multifocal intraocular lenses (IOL) in the Singapore population. METHODS: This is a retrospective case series of 45 phacoemulsification with multifocal lens implantation performed in 27 patients for cataracts, over a two-year period. The efficacy, stability and safety of the lens were assessed up to six months of follow-up. A telephone interview enquiring about ratings of vision, spectacle independence, glare, driving difficulty and photic phenomena, was conducted and the results were compared with those published in the literature. RESULTS: The best corrected distance Logmar acuity was 0.1 (0.1 and near visual acuity was N5 (range N5 to N8) at six months. The distance visual acuity stabilised by one month whereas near vision remained unchanged from day one post-surgery. Posterior capsular opacification was seen in 17 patients (38.6 percent) of which two patients (4.55 percent) required YAG capsulotomy. Total spectacle independence was achieved in 12 patients (54.4 percent). Among those who required spectacles, 50 percent required spectacles more than 50 percent of the time. Five patients (22.7 percent) reported glare usually at night (80 percent) as compared with daytime glare (20 percent). The most common photic phenomena report after surgery was halo. CONCLUSION: The Advanced Medical Optics ARRAY multifocal IOL showed good efficacy, predictability, stability and safety. The subjective visual outcomes in the Singapore population were comparable to those of their Western counterparts.

Measurement of the visual contribution to postural steadiness from the COP movement: methodology and reliability.

We studied the reliability of different measures of the visual contribution to postural steadiness by recording the postural sway during standing with eyes open (EO) or eyes closed (EC). The COP trajectory was recorded in 21 subjects aged 42-61 standing on a firm or foam support. The improvement of postural steadiness due to vision was measured with a higher reliability (i.e. lower intra- and inter-subject variabilities) with the sway velocity V, than with the position RMS. Due to the increase of the variability of V and RMS with their own mean values, we quantified the visual contribution to posture by the stabilization ratio (SR), based on a logarithm transform of V or RMS. As compared to the Romberg quotient (EC/EO), SR improved the reliability of the measurement of the visual contribution to posture within individuals, across subjects, and even across different studies in the literature. Our method led to decrease the inter-subject coefficient of variation of this measurement to about 25%, using a foam support. It leads to a similar accuracy in binocular and monocular vision, and it also applies to the quantification of other non-visual sensory contributions to posture.

Interocular asymmetry of visual field defects in primary open angle glaucoma and primary angle-closure glaucoma.

AIM: To compare the interocular asymmetry in visual field loss of patients with primary open-angle (POAG) and primary angle-closure glaucoma (PACG). METHODS: Subjects entering a prospective, randomised, controlled trial of intraoperative 5-fluorouracil in glaucoma surgery in Singapore were included. Preoperative visual field testing was performed using automated white-on-white perimetry (24-2 test pattern, threshold program, Mk II, Model 750, Zeiss-Humphrey, San Leandro, CA, USA). A minimum of two tests were required with mean deviation within 2 dB on two tests, fixation losses <20%, false positives <33%, and false negatives <33%. The second field was scored using AGIS II criteria and the 'mean asymmetry score' defined as the mean difference between eyes for both AGIS scores and global indices. RESULTS: In 230 subjects assessed (128 POAG, 102 PACG), mean interocular asymmetry of visual field loss was greater for the PACG group. The mean AGIS asymmetry scores for total (PACG=9.21+/-6.87 vs POAG=6.48+/-5.58, P=0.001), superior (PACG=4.31+/-3.39 vs POAG=3.35+/-3.13, P=0.035), and inferior (PACG=4.43+/-3.31 vs POAG=2.64+/-2.77, P<0.0001) areas and mean deviation (MD) asymmetry scores (PACG=6.89+/-13.22 vs POAG=1.66+/-16.97, P=0.012) were all significantly different. Interocular correlation of visual field loss for POAG was significant; total AGIS, r=0.27 (P=0.003), superior field AGIS, r=0.24 (P=0.008), inferior field AGIS, r=0.34 (P=0.0001), and MD, r=0.27 (P=0.003). In PACG, there was no significant correlation between eyes; total AGIS, r=-0.02 (P=0.85), superior field AGIS, r=-0.02 (P=0.82), inferior field AGIS, r=-0.17 (P=0.87), and MD, r=0.015 (P=0.89). CONCLUSION: There was a greater asymmetry of visual field loss between eyes, as measured by AGIS scores and MD, in PACG than that in POAG.

Effect of cataract extraction and intraocular lens implantation on nerve fibre layer thickness measurements by scanning laser polarimeter (GDx) in glaucoma patients.

PURPOSE: To assess the influence of visually significant cataract on the measurement of nerve fibre layer thickness by scanning laser polarimetry (GDx) in glaucoma patients undergoing phacoemulsification cataract extraction. METHOD AND SUBJECTS: All subjects with primary glaucoma participating in a prospective trial of glaucoma surgery who subsequently underwent cataract extraction were eligible. A single trained observer using the GDx nerve fibre layer analyser (LDT) performed pre- and post-operative measurements of nerve fibre layer thickness (NFLT). NFLT parameters, best-corrected LogMAR visual acuity, and automated visual fields were assessed before and after phacoemulsification cataract extraction with implantation of an acrylic intraocular lens. RESULTS: A total of 49 subjects were assessed: 22 (45%) had POAG and 29 (55%) PACG; all were Asian (36 (73%) were Chinese), with mean age 67.1 (+/-7.6 SD) and mean 'LOCS III' lens opacity grading 11.4 (+/-3.1 SD). Visual acuity significantly improved (mean LogMAR 0.5 vs 0.15, P<0.0001). Corrected pattern standard deviation (6.1 vs 6.4, P=0.2) and mean deviation (-17.7 dB vs -17.0 P=0.91) were little changed after cataract removal. Pseudo-phakic measurements of NFLT were significantly different from pre-op values. Measures of absolute thickness (including the average thickness, ellipse, ellipse average, superior and inferior averages, superior integral) were significantly greater than preoperative values (all P<0.01), whereas ratios and measures of symmetry (symmetry, superior/nasal) were unchanged (all P>0.1) and 'the number' was smaller (P=0.04). Differences in measured NFLT were most strongly correlated with posterior subcapsular cataract (average thickness, P=0.01). CONCLUSIONS: Removal of cataract resulted in greater absolute measurements of NFLT but ratio values were unchanged. Scanning laser polarimetry measurements can change significantly after cataract extraction. New baseline measurements may be required.

Randomised controlled trial comparing the effect of brimonidine and timolol on visual field loss after acute primary angle closure.

AIM: To compare the effect of brimonidine and timolol in reducing visual field loss in patients with acute primary angle closure (APAC). METHODS: In addition to standard acute medical treatment, patients presenting with APAC were randomised to either brimonidine 0.2% or timolol 0.5% upon diagnosis, then twice daily for 4 weeks. After laser peripheral iridotomy (LPI), subjects underwent three baseline perimetry tests during the first week, and then at weeks 4, 8, 12, and 16. Pointwise linear regression analysis was applied to the field series of each of these subjects starting with the third test (total of five tests per subject). Progression was defined as a significant regression slope (p<0.05) showing 1 dB per year or more of sensitivity loss at the same test location in the series. Patients were also compared for prevalence of abnormal fields at 16 weeks, which was defined as an abnormal glaucoma hemifield test result and/or corrected pattern standard deviation outside the 95% confidence limits. RESULTS: 59 subjects (31 in the brimonidine group; 28 in the timolol group) completed the study. There were 47 females (79.7%), the majority of subjects (94.9%) were Chinese and the mean age was 59.2 (SD 7.2) years. There were no significant differences between the two groups with respect to demographic features, presenting intraocular pressure (IOP), duration of symptoms, time from presentation to LPI, or mean IOP at each study visit. Over the 16 week study period, despite adequate statistical power, no difference was found between groups in terms of the number of patients with progressing locations, the mean number of progressing locations per subject, or the mean slope of the progressing locations. Nine (29%) subjects in the brimonidine group and 10 (35.7%) in the timolol group were found to have significant visual field defects at 16 weeks (p = 0.58). 15 out of these 19 subjects (78.9%) already had these visual field defects in the first week. CONCLUSIONS: In the first 16 weeks after APAC, there was no difference in the prevalence of visual field defects or rate of visual field progression between brimonidine and timolol treated groups.