Longitudinal Change of Cup to Disc Ratio in Premature Infants with Enlarged Cup to Disc Ratio and Normal Intraocular Pressure

PURPOSE

To evaluate the longitudinal change of cup to disc ratio (CDR) in premature infants with enlarged CDR and normal intraocular pressure (IOP).

METHODS

This retrospective, observational study included 283 eyes of 283 premature infants at single center. Infants were divided into enlarged CDR and control groups. Data on demographics, gestational age (GA), birth weight (BW), vertical cup to disc ratio (vCDR), IOP, and corneal diameter were analyzed.

RESULTS

Of the 283 patients, 38 (13.4%) and 245 (86.6%) were in the enlarged CDR and control groups, respectively. In the enlarged CDR group, the vCDR and baseline IOP was 0.63 ± 0.12 and 12.7 ± 2.2 mmHg, respectively. In the control group, the vCDR and baseline IOP was 0.18 ± 0.05 and 10.9 ± 1.7 mmHg, respectively. The IOP at a GA of 40 weeks and at 1 and 2 years of age were significantly lower than that at baseline. The differences in vCDR between baseline and each follow-up visit were not significant. vCDR was negatively correlated with GA and BW; however, these correlations were not significant.

CONCLUSIONS

The vCDR did not significantly change up to age of 2 years of age in premature infants with enlarged CDR and normal IOP. However, close follow-up is needed until other reliable glaucoma examinations, such as optical coherence tomography and visual fields, can be possible.

Optic disc morphology in preterm children. Influence of gestational age and birth weight

PURPOSE

The characteristics of the optic disc and the development of the optic nerve can affect visual function in children. The purpose of our study was to assess optic disc morphology in preterm infants and to determine whether it is influenced by gestational age, birth weight and the presence of a retinopathy of prematurity.

METHODS

In a retrospective study, RetCam fundus images of 109 premature newborns admitted to our tertiary-level neonatal intensive care unit were reviewed. We evaluated the cup to disc ratio (C/D), optic disc diameter, cup diameter, shape of the optic disc, adherence to the ISNT rule, and presence of a peripapillary atrophy.

RESULTS

Of 218 photos, we found the following results: mean±SD gestational age 28.5±2.7 weeks, mean±SD birth weight 1122±394g, mean C/D 0.32. There was no significant correlation between C/D and gestational age or birth weight. Vertical disc diameter was greater than horizontal disc diameter, with a mean ratio (horizontal/vertical) of 4/5, lending an oval shape to the optic disc. Nineteen infants had retinopathy of prematurity in both eyes; ninety-three percent had peripapillary atrophy.

CONCLUSION

In our study, optic disc morphology in premature newborns was not influenced by gestational age, birth weight or presence of premature retinopathy.

Automatic glaucoma screening using optic nerve head measurements and random forest classifier on fundus images

Glaucoma is an optic neuropathy that gradually steals the patient's sight by damaging the optic nerve head (which is responsible for transferring images from the eye to the brain). Causing an estimated 12.3% of global blindness, glaucoma is considered as the first leading cause of irreversible blindness in the world. This paper presents a novel eye fundus image analysis algorithm for the automatic measurement of fundus related glaucoma indicators; Cup to Disc Ratio (CDR), verification of the ISNT rule, Disc Damage Likelihood Scale (DDLS), and the classification of the input fundus into glaucoma or non-glaucoma case using a random forest model. The proposed method is applied on the public image database 'HRF', and a local database containing both, normal and glaucoma cases, and resulted sensitivity, specificity, and accuracy of 1, 0.93 and 0.97 respectively. This technique presented the highest classification accuracy compared to previous works studied in the state of the art; hence, it can be used as a computer aided glaucoma diagnosis system by ophthalmologists to assist in their screening routine.

Agreement between Fourier-domain and swept-source optical coherence tomography used for optic nerve head measurements

PURPOSE

To assess the correlation between optic nerve head measurements generated by Fourier-domain (FD) and swept-source (SS) optical coherence tomography (OCT) both in healthy Caucasian subjects and patients with primary open angle glaucoma (POAG).

MATERIALS AND METHODS

This was a cross-sectional study of the right eyes of 118 subjects. In each participant, the measurements of disc area, cup to disc ratio (CDR), vertical cup to disc ratio (VCDR), rim area and rim volume were performed consecutively by FD-OCT and then SS-OCT. Participant age, gender and spherical equivalent were also recorded. Agreement between the two devices was assessed through intraclass correlation coefficients (ICC) and Bland-Altman plots.

RESULTS

The study sample consisted of 95 healthy eyes and 23 eyes with glaucoma. Mean participant age was 48.6±20.0 years, 54.2% were female, and mean spherical equivalent was -1.6±3.0 diopters. FD-OCT and SS-OCT measurements were respectively: mean disc area 1.79±0.3 vs 1.83±0.3 mm2 (ICC=0.71), mean CDR 0.38±0.2 vs 0.33±0.2 (ICC=0.91), mean VCDR 0.58±0.2 vs 0.52±0.2 (ICC=0.92), mean rim area 1.05±0.4mm² vs 1.03±0.5mm² (ICC=0.29), and mean rim volume 0.14±0.11 vs 0.21±0.17mm³ (ICC=0.53). Good agreement between the devices was noted for rim area and rim volume in glaucoma subjects (ICC=0.76 and 0.68 respectively), while weak agreement was observed for these variables in healthy subjects (ICC≤0.50).

CONCLUSIONS

The CDR and VCDR measurements provided by FD and SS OCT showed excellent agreement for the overall sample. When the devices were used for rim measurements, agreement was excellent only in the POAG patients.

Automated detection of glaucoma using structural and non structural features

Glaucoma is a chronic disease often called “silent thief of sight” as it has no symptoms and if not detected at an early stage it may cause permanent blindness. Glaucoma progression precedes some structural changes in the retina which aid ophthalmologists to detect glaucoma at an early stage and stop its progression. Fundoscopy is among one of the biomedical imaging techniques to analyze the internal structure of retina. Our proposed technique provides a novel algorithm to detect glaucoma from digital fundus image using a hybrid feature set. This paper proposes a novel combination of structural (cup to disc ratio) and non-structural (texture and intensity) features to improve the accuracy of automated diagnosis of glaucoma. The proposed method introduces a suspect class in automated diagnosis in case of any conflict in decision from structural and non-structural features. The evaluation of proposed algorithm is performed using a local database containing fundus images from 100 patients. This system is designed to refer glaucoma cases from rural areas to specialists and the motivation behind introducing suspect class is to ensure high sensitivity of proposed system. The average sensitivity and specificity of proposed system are 100 and 87 % respectively.

An adaptive threshold based image processing technique for improved glaucoma detection and classification

Glaucoma is an optic neuropathy which is one of the main causes of permanent blindness worldwide. This paper presents an automatic image processing based method for detection of glaucoma from the digital fundus images. In this proposed work, the discriminatory parameters of glaucoma infection, such as cup to disc ratio (CDR), neuro retinal rim (NRR) area and blood vessels in different regions of the optic disc has been used as features and fed as inputs to learning algorithms for glaucoma diagnosis. These features which have discriminatory changes with the occurrence of glaucoma are strategically used for training the classifiers to improve the accuracy of identification. The segmentation of optic disc and cup based on adaptive threshold of the pixel intensities lying in the optic nerve head region. Unlike existing methods the proposed algorithm is based on an adaptive threshold that uses local features from the fundus image for segmentation of optic cup and optic disc making it invariant to the quality of the image and noise content which may find wider acceptability. The experimental results indicate that such features are more significant in comparison to the statistical or textural features as considered in existing works. The proposed work achieves an accuracy of 94.11% with a sensitivity of 100%. A comparison of the proposed work with the existing methods indicates that the proposed approach has improved accuracy of classification glaucoma from a digital fundus which may be considered clinically significant.