Inferior Superior Nasal Temporal Research Articles

DEC-DRR: deep ensemble of classification model for diabetic retinopathy recognition.

Most diabetes patients are liable to have diabetic retinopathy (DR); however, the majority of them might not be even aware of the ailment. Therefore, early detection and treatment of DR are necessary to prevent vision loss. But, avoiding DR is not a simple process. An ophthalmologist can typically identify DR through an optical evaluation of the fundus and through the evaluation of color pictures. However, due to the increased count of DR patients, this could not be possible as it consumes more time. To rectify this problem, a novel deep ensemble-based DR classification technique is developed in this work. Initially, a Wiener filter (WF) is applied for preprocessing the image. Then, the enhanced U-Net-based segmentation process is done. Subsequent to the segmentation process, features are extracted that include statistical features, inferior superior nasal temporal (ISNT), cup to disc ratio (CDR), and improved LGBP as well. Further, deep ensemble classifiers (DEC) like CNN, Bi-GRU, and DMN are used to recognize the disease. The outcomes from DMN, CNN, and Bi-GRU are then subjected to improved SLF. Additionally, the weights of DMN, CNN, and Bi-GRU are adjusted via pelican updated Tasmanian devil optimization (PU-TDO). Finally, outputs on DR (microaneurysms, hemorrhages, hard exudates, and soft exudates) are obtained. The performance of DEC + PU-TDO for diabetic retinopathy is computed over extant models with regard to different measures for four datasets. The results on accuracy using the DEC + PU-TDO scheme for the IDRID dataset is maximum around 0.975 at 90th LP while other models have less accuracy. The FPR of DEC + PU-TDO is less around 0.039 at the 90th LP for the SUSTech-SYSU dataset, while other extant models have maximum FPR.

An efficient framework for optic disk segmentation and classification of Glaucoma on fundus images

Accurately segmenting the Optic Disk is a crucial step in classifying Glaucoma using Fundus images. Machine learning and artificial intelligence techniques are widely used in Glaucoma detection, and the main indicators observed in Fundus images are the presence of Papillary Atrophy, Cup to Disc Ratio values, diminishing Neural Retinal Rim (NRR), the Inferior Superior Nasal Temporal (ISNT) rule, and Cup Diameter. In this research, we investigated various segmentation and classification techniques that can be applied to Optic disk segmentation and classification of normal and glaucomatous eyes. The proposed method will be beneficial to clinicians and healthcare workers in facilities with limited resources. In this paper, histogram processing is used to determine the type of image, and based on this information; we decide whether the image requires segmentation. Some datasets in the standard dataset contain complete retinal images while others include segmented optic disks. The segmented images are directly given as input for classification using the proposed Convolutional Neural Network (CNN). For complete retinal images, segmentation is performed using the Simple Linear Iterative clustering (SLIC) and normalized graph cut algorithm. The proposed framework's performance is compared with that of pretrained neural networks, including VGG19, InceptionV3, and ResNet50V2, using major metrics. We trained and tested these architectures with 3115 images from six standard datasets. Our proposed framework outperforms all with an accuracy of 96.33 %.

The Inferior, Superior, Temporal Rim Width Pattern (IST Rule) Detects Glaucoma in a Japanese Population.

Précis:The inferior>superior>temporal rim width rate (IST pattern) rather than inferior≥superior≥nasal≥temporal (ISNT) pattern was suited for screening glaucoma in Japanese subjects. Failure of the IST pattern was associated with several important risk factors for glaucoma.Purpose:The purpose of this study was to find a rim width rate pattern to yield the highest positive likelihood ratio (LR+) in detecting glaucoma eyes and to identify risk factors for glaucoma correlating with its failure in a population-based setting.Methods:Disc stereophotographs of 2474 eyes of 2474 normal subjects and 237 eyes of 237 glaucoma subjects found in the Kumejima Study were analyzed using computer-assisted planimetry. Among all combinations of the inferior (I), superior (S), nasal (N) and/or temporal (T) rim width rate, a pattern showing the highest LR+ was selected and risk factors for glaucoma correlating with its failure were determined using multiple logistic regression analysis.Results:The average I, S, N, and T rim widths (SD) were 0.45 (0.10), 0.39 (0.09), 0.47 (0.11), and 0.27 (0.07) mm. Among all combinations, the I>S>T rim width rate pattern (IST pattern) disregarding the N rim width showed the highest LR+ of 2.002 (95% confidence interval, 1.778–2.253). Failure of the IST pattern in normal eyes correlated with a smaller disc area (P<0.001) and disc ovality (P=0.005) and larger β-peripapillary area (P<0.001) and compliance with in glaucoma eyes with a smaller β-PPA area (P=0.027), thicker central corneal thickness (P=0.017), lower intraocular pressure (P=0.019), and higher body mass index (P=0.037).Conclusion:Among all combinations, the I>S>T rim width pattern, the IST pattern, yielded the highest LR+ in detecting glaucoma in Japanese glaucoma eyes and its failure of or compliance with the pattern significantly correlated with several known risk factors for glaucoma.

Does the ISNT rule apply to the radial peripapillary capillary vessel density in OCT angiography?

To investigate the applicability of ISNT (inferior ≥ superior ≥ nasal ≥ temporal), IST (inferior ≥ superior ≥ temporal), and T min (temporal quadrant with the minimum value) rules to the peripapillary nerve fiber layer (NFL) thickness and radial peripapillary capillary (RPC) vessel density (VD) using Optical Coherence Tomography (OCT) and OCT angiography (OCT-A). This cross-sectional study included 134 eyes of 74 healthy individuals. NFL thickness and RPC VD were measured in all four quadrants using OCT and OCT-A in order to determine the number of eyes that obey the ISNT, IST, and T min rules. Mean age was 48.8 ± 15.5 (range 25-82) years. The ISNT rule was valid in 52 eyes (38.81%) on OCT and only 12 eyes (8.95%) on OCT-A scans. The IST rule was followed by 83 (61.94%) and 37 (27.61%) eyes on OCT and OCT-A scans respectively. The T min rule was valid in 86 eyes (64.18%) in OCT scans and in 26 eyes (19.4%) in OCT-A scans. The topography of the RPC network does not obey the ISNT rule in healthy eyes. The ISNT rule and its variants were found to be more relevant in OCT NFL thickness measurements compared to OCT-A RPC VD measurements.

Survey on Automatic Detection of Glaucoma through Deep Learning Using Retinal Fundus Images

Glaucoma - a disease which causes damage to our eye's optic nerve and subsequently blinds the vision. This occurs due to increased intraocular pressure (IOP) which causes the damage of optic nerve axons at the back of the eye, with eventual deterioration of vision. Presently, many works have been done towards automatic glaucoma detection using Fundus Images (FI) by extracting structural features. Structural features can be extracted from optic nerve head (ONH) analysis, cup to disc ratio (CDR) and Inferior, Superior, Nasal, Temporal (ISNT) rule in Fundus Image for glaucoma assessment.This survey presents various techniques for the early detection of glaucoma. Among the various techniques, retinal image-based detection plays a major role as it comes under non-invasive methods of detection. Here, a review and study were conducted for the different techniques of glaucoma detection using retinal fundus images. The objective of this survey is to obtain a technique which automatically analyze the retinal images of the eye with high efficiency and accuracy

Application of the ISNT rules on retinal nerve fibre layer thickness and neuroretinal rim area in healthy myopic eyes.

We determined the applicability of inferior>superior>nasal>temporal (ISNT) rules on retinal nerve fibre layer (RNFL) thickness and rim area and evaluated the impact of various ocular factors on the performance of the ISNT rules in healthy myopic eyes. A total of 138 eyes from 138 healthy myopic subjects were included in this cross-sectional observational study. The peripapillary RNFL and optic disc in each eye were imaged with Cirrus HD optical coherence tomography (OCT) and Heidelberg Retina Tomograph II (HRT2), respectively. The performance of the inferior>superior (IS), inferior>superior>nasal>temporal (IST) and ISNT rules on RNFL thickness and rim area was determined and compared between low-to-moderate myopia and high myopia. The effects of ocular factors [including axial length, disc area, disc tilt, disc torsion, disc-fovea angle (DFA) and retina artery angle] on the performance of ISNT rules were evaluated with logistic regression analysis. The mean axial length and refractive error were 25.57±1.09mm (range, 22.52-28.77mm) and -5.12±2.30D [range, -9.63 to -0.50dioptres (D)], respectively. Sixty-three per cent of the healthy eyes were compliant with the ISNT rule on rim area, while ISNT rule on RNFL thickness was followed in only 11.6% of the included eyes. For rim area, smaller disc area was significantly associated with increased compliance of the IS rule (odds ratio: 0.46, p=0.039), IST rule (odds ratio: 0.46, p=0.037) and ISNT rule (odds ratio: 0.44, p=0.030). For RNFL thickness, greater DFA was significantly associated with increased compliance of the IS and IST rules (odds ratio: 1.30, p<0.001; odds ratio: 1.19, p=0.006, respectively). In healthy myopic subjects, 88.4% and 37% of eyes did not comply with the ISNT rule on RNFL thickness and rim area, respectively. Due to significant low compliance in healthy eyes, the ISNT rule and its variants have limited potential utility in diagnosing glaucoma in myopic subjects.

Neural Network Analysis of Different Segmentation Strategies of Nerve Fiber Layer Assessment for Glaucoma Diagnosis.

To compare the diagnostic performance of different segmentations of the nerve fiber layer (NFL) thickness measurements using an artificial neural network and to define the optimal number of sectors with best diagnostic ability for glaucoma diagnosis. A total of 117 glaucoma patients and 123 normal subjects were included in the study. NFL thickness measurements were performed using the Spectralis-OCT (Heidelberg Engineering) to obtain the NFL thickness average; measurements from 2 semicircles, 4 quadrants, and 6, 8, 12, 16, 24, 32, and 64 sectors; and 768 uniformly divided locations around the peripapillary NFL. An artificial neural network evaluation was performed to compare the influence of sector analysis on the diagnostic performance of optical coherence tomography. Receiver operating characteristic curves were used to compare the diagnostic ability of the different segmentation analyses. The 6 sectors divided by the horizontal division of the nasal and temporal quadrants were better than the 6 sectors divided by the vertical line through the superior and inferior quadrants [areas under curve, 0.778; 95% confidence interval (CI), 0.720-0.829 and 0.814; 95% CI, 0.759-0.861, respectively]. In the case of quadrants, clock quadrants (area under curve 0.770; 95% CI, 0.712-0.822) were better than the ISNT (inferior-superior-nasal-temporal) quadrants (area under curve, 0.770; 95% CI, 0.712-0.822; P=0.003). The first segmentation strategy that improved the diagnostic value of 4 ISNT quadrants was the 12-sector analysis (area under curve, 0.845; 95% CI, 0.793-0.889; P=0.001). The 2 best candidate strategies for the OCT report were the 12-sector analysis and the 4 planimetric quadrant (alternatively, the 4 clock quadrants) analysis.

Applicability of ISNT and IST rules to the retinal nerve fibre layer using spectral domain optical coherence tomography in early glaucoma

BackgroundTo report the applicability of ISNT (inferior>superior>nasal>temporal) and IST (inferior>superior>temporal) rules on the retinal nerve fibre layer (RNFL) using spectral domain optical coherence tomography (SD-OCT) for detecting early glaucoma.MethodsA prospective,...

Applicability of the ISNT and IST rules on retinal nerve fiber layer measurement on spectral-domain optical coherence tomography in normal Indian children.

To determine the applicability of the ISNT (inferior>superior>nasal>temporal) and IST (inferior>superior>temporal) rules on retinal nerve fiber layer (RNFL) measurement on spectral-domain optical coherence tomography (SD-OCT) in normal children. A prospective, cross-sectional study including consecutive subjects between the ages of 5-18 years who were born at term (≥37 weeks gestational age) and with a normal birth weight (≥2500 g) presenting to the out-patient department for refractive error examination. RNFL measurement was done on Spectralis SD-OCT. Exclusion criteria were best-corrected visual acuity less than 20/20, spherical equivalent (SE) > ± 5 diopter (D), applanation IOP >21 mmHg, cup-to-disc (C/D) ratio of >0.5, C/D ratio asymmetry of >0.2 between eyes and any retinal or optic disc anomaly as determined by mydriatic fundus examination. Subjects with amblyopia, strabismus, or family history of optic nerve or retinal disease were excluded. Poor cooperation for SDOCT imaging and lack of consent were other exclusion criteria. The ISNT rule on the RNFL was followed only by 30 eyes (23.8 %), while the IST rule was followed by 66 eyes (52.4 %) (p < 0.001). The superior RNFL was thicker than the inferior in 57 eyes (45.2 %) while the temporal RNFL was thicker than the nasal in 63 eyes (50 %). The age, gender, spherical equivalent, and disc size did not predict the followability of the ISNT and IST rules (p > 0.05). The ISNT and the IST rules for RNFL are not universally followed by all normal eyes in children. All deviations should therefore not be considered pathological.

MASK IMAGE GENERATION FOR SEGMENTING RETINAL FUNDUS IMAGE FEATURES INTO ISNT QUADRANTS USING ARRAY CENTROID METHOD

Retinal fundus image processing paves the way for diagnosis of many eye disorders. The fundus image features such as optic disc, optic cup, optic rim and blood vessels help to analyse the pathological condition of eye. The analysis involves calculation of ocular parameters such as Rim to Disc Ratio (RDR) and Inferior Superior Nasal Temporal (ISNT) Ratio and verification of ISNT Rule. For this analysis the fundus image features have to be segmented into ISNT quadrants. This paper presents a novel approach towards mask image generation for segmenting fundus image feature into ISNT quadrants using array centroid method. The existing method uses a predefined mask image which is not accurate and the proposed array centroid method overcomes the limitations of existing method. The method involves centroid calculation, array initialization; mask image generation and, mask- feature image multiplication. The proposed method is applied to the fundus images collected from a reputed eye hospital.

Assessment of Disc Damage Likelihood Scale (DDLS) for Automated Glaucoma Diagnosis

Glaucoma is the second leading ocular disease of irreversible blindness. Structural damages in optic disc such as deforming of neuroretinal rim, optic cup precedes the functional damages so their early assessment is crucial. Functional damages involve visual field impairment & blindness. Tonometery and visual field assessment are the manual method of assessing glaucoma and require clinical setup and expert advice. Manual methods are not sufficient to assess glaucoma in its early stages. Structural assessment can detect Glaucoma in early stage and diminishes the risk of irreversible visual impairment. Optic disc photography is a Qualitative and less expensive method. Cup to Disc Ratio(CDR), Inferior Superior Nasal Temporal(ISNT) rule and Peripapillary Atrophy (PPA) are assessed for determining Glaucoma Stage. But these features are prone to errors as disc size is not considered in Cup to disc ratio. Disc Damage Likelihood Scale (DDLS) presents a novel approach for rim width assessment, which can increase the reliability of automated glaucoma diagnosis in conjunction with other features. Incorporation of Disc Damage likelihood Scale (DDLS) & features like blood pressure, age, ethnicity in automated assessment techniques can increase the reliability of automated glaucoma diagnosis.

Tomographic characteristics of optic nerve head on Heidelberg retina tomograph III in healthy Chinese subjects

Background Normal adult optic disc rim width follows inferior ≥ superior ≥ nasal ≥ temporal (ISNT) rule.Analysis of the optic disc structural parameters with Heidelberg retina tomograph (HRT) can understand whether ISNT principle is suitable to other optic disc structure parameters.Objective This study was to investigate the characteristics of optic nerve head structure parameters in normal Chinese adults.Methods The parents of twins who participated Guangzhou Twin Eye Study were enrolled in Zhongshan Ophthalmic Center from 2006 June to 2011 August.All subjects received the routine eye examinations,including visual acuity,slit lamp microscope,direct ophthalmoscope examination,auto-refraction examination and HRT Ⅲ examination.All data from the right eyes were collected and analyzed.HRT values from different quadrants of optical nerve head were compared with one-way analysis of variance,and the multiple comparison between quadrants was carried out by Bonferroni test.The differences of optical nerve head parameters in different gender were analyzed using independent sample t test and Bland-Altman test.Results In this study,1672 eyes of 1672 subjects were included,with the 759 male and 913 female persons and average age of (41.8±5.3)years.No significant differences were seen in the disc area (DA)between the superior and inferior,as well as the nasal and temporal quadrants among the subjects (P＞0.05).In addition,there were not significantly different in the rim area (RA) between the superior and nasal disc as well as the rim volume (RV) among the inferior,superior and nasal disc (P＞O.05).However,significant differences were found in the cup area (CA),cup/disk area ratio (C/DAR),cup volume (CV),mean cupdepth (MCD),maximum cup depth (MxCD),height variation contour (HVC),cup shape measure (CSM),mean retinal nerve fiber layer thickness (mRNFLT) and retinal nerve fiber layer cross section area (RNFLcsa) among the different quadrants (P＜0.001).The local differences from only DA and RA complied with an ordination of the ISNT rule.The values of DA,CA,C/DAR,CV,MCD,MxCD from male individuals were higher,but those of the RV,HVC,mRNFLT RNFLcsa were lower in comparison with female individuals.Nevertheless,all the differences were ＜ 0.1 with a maximal mean difference in DA and CA (both 0.07 mm2).Conclusions The optical nerve head configurations measured by HRT have different distributing characteristics in four quadrants in normal adults.Most parameters show the higher values in the inferior and superior than those in nasal and temporal of disc,but DA and RA meet ISNT rule.The differences of most parameters between male and female subjects can be ignored. Key words: Bio-metrics; Optic nerve head/parameter, structure; Tomography/method; Heidelberg retinal tomograph; Adult; Gender

Diagnostic Performance of the ISNT Rule for Glaucoma Based on the Heidelberg Retinal Tomograph

We determined the accuracy of the inferior > superior > nasal > temporal (ISNT) neuroretinal rim area rule and its variants in adult Asian populations, and evaluated whether disc area impacts its performance characteristics. Participants in the Singapore Malay Eye Study (SiMES) and Singapore Indian Eye Study (SINDI) underwent standardized ocular examinations, including optic disc imaging with the Heidelberg retinal tomograph (HRT). Glaucoma was defined using the ISGEO criteria. HRT rim areas in the superior, inferior, nasal, and temporal quadrants were quantified. We determined sensitivity, specificity, and positive (PPV) and negative (NPV) predictive values of violating the ISNT rule and 4 variants (I > S > T, I > S, I > T, and combined I > T and S > T). The influence of disc area was analyzed with multivariate marginal logistic regression. There were 6112 participants (mean age: 57.6 ± 10.3 years). Glaucoma was present in 194 individuals (3.2%). Among 11,840 eyes, 232 (93.2%) of 249 glaucomatous eyes and 9768 (84.3%) of 11,591 nonglaucomatous eyes, violated the ISNT rule. The ISNT rule had highest sensitivity (93.5%), but lowest specificity (15.7%); I > T had highest specificity (98.2%), but low sensitivity (7.4%). For all variants, PPVs were low (2.1%-8.4%) and NPVs were high (97.9-99.1%). Larger disc area was associated with reduced specificity for the ISNT rule (P < 0.001), and reduced sensitivity (P = 0.01) and increased specificity for I > S > T (P < 0.05). PPV increased (P < 0.05) and NPV decreased (P < 0.001) with increasing disc area. The ISNT rule based on HRT has high sensitivity, and the I > T, S > T, and combined I > T and S > T variants have high specificity. Disc area influences sensitivity, specificity, PPV, and NPV of the ISNT rule and its variants. The high sensitivity of the ISNT rule, and high specificities of its variants, may have potential utility when used in combination with other HRT algorithms for glaucoma assessment.