No-reference quality index for color retinal images.

Retinal image quality assessment (RIQA) is essential to assure that the images investigated by ophthalmologists or automatic systems are suitable for reliable medical diagnosis. Measure-based RIQA techniques have several advantages over the more commonly used binary classification-based RIQA methods. Numeric quality measures can aid ophthalmologists in associating a degree of confidence to the diagnosis performed through the investigation of a certain retinal image. Moreover, a numeric quality index can provide a mean for identifying the degree of enhancement required as well as to evaluate and compare the improvement achieved by enhancement techniques. In this work, a no-reference retinal image sharpness numeric quality index is introduced that is computed from the wavelet decomposition of the images. In order to account for the obscured retinal structures in unevenly illuminated image regions, the quality index is modified by a homogeneity parameter calculated from the previously introduced retinal image saturation channel. The proposed quality index was validated and tested on two datasets having different resolutions and quality grades. A strong (Spearman's coefficient > 0.8) and statistically highly significant (p-value < 0.001) correlation was found between the introduced quality index and the subjective human scores for the two different datasets. Moreover, multiclass classification using solely the devised retinal image quality index as a feature resulted in a micro average F-measure of 0.84 and 0.95 using the high and low resolution datasets, respectively. Several comparisons with other retinal image quality measures demonstrated superiority of the proposed quality index in both performance and speed.

Retinal image quality assessment based on image clarity and content.

Retinal image quality assessment (RIQA) is an essential step in automated screening systems to avoid misdiagnosis caused by processing poor quality retinal images. A no-reference transform-based RIQA algorithm is introduced that assesses images based on five clarity and content quality issues: sharpness, illumination, homogeneity, field definition, and content. Transform-based RIQA algorithms have the advantage of considering retinal structures while being computationally inexpensive. Wavelet-based features are proposed to evaluate the sharpness and overall illumination of the images. A retinal saturation channel is designed and used along with wavelet-based features for homogeneity assessment. The presented sharpness and illumination features are utilized to assure adequate field definition, whereas color information is used to exclude nonretinal images. Several publicly available datasets of varying quality grades are utilized to evaluate the feature sets resulting in area under the receiver operating characteristic curve above 0.99 for each of the individual feature sets. The overall quality is assessed by a classifier that uses the collective features as an input vector. The classification results show superior performance of the algorithm in comparison to other methods from literature. Moreover, the algorithm addresses efficiently and comprehensively various quality issues and is suitable for automatic screening systems.

Cerebral microinfarcts in primary open-angle glaucoma correlated with DTI-derived integrity of optic radiation.

PURPOSE: To evaluate the correlation between the extent of cerebral white matter lesions (WMLs) and the integrity of the visual pathway represented by fractional anisotropy (FA) in patients with primary open-angle glaucoma (POAG). METHODS: This case-control study included a total of 61 German patients (39 POAG patients, 22 controls) matched for age and sex. Fractional anisotropy of the optic radiation was determined by 3-Tesla diffusion tensor imaging. White matter lesions and brain volumes were manually measured by using a T2-weighted, 3-D fluid-attenuated inversion recovery sequence. RESULTS: In POAG patients WML volumes were significantly (P = 0.04) increased in the subcortical area. This applied for both absolute and relative units to the specific patient's brain volume, compared to controls. The WML volumes were significantly (P = 0.003) greater in middle-aged (40-59 years) POAG patients than control patients. In controls there was a significant age correlation of WML volumes in the total brain, subcortical, and optic radiation regions of interest. There was a significant correlation between FA and WML in POAG regarding the total brain, the periventricular region, and the optic radiation in both hemispheres. In POAG, FA left and right optic radiation correlated significantly with age (P = 0.002). CONCLUSIONS: We were able to demonstrate that (1) POAG patients aged 40 to 60 years had higher volumes of cerebral microinfarcts and (2) POAG patients showed a significant correlation between cerebral microinfarcts and degeneration of the optic radiation. This indicates that cerebral microinfarcts might be an intracerebral risk factor for glaucomatous optic nerve atrophy.

Glaucoma classification based on visual pathway analysis using diffusion tensor imaging.

Most of the existing methods for diagnosing glaucoma analyze the eye with a main focus on the retina, despite the transsynaptic nature of the fiber degeneration caused by glaucoma. Thus, they ignore a significant part of the visual system represented by the visual pathway in the brain. The advances in neuroimaging, especially diffusion tensor imaging (DTI), enable the identification and characterization of white matter fibers. In this work, we propose a system based on DTI analysis of the visual pathway fibers in the optic radiation for detecting and discriminating different glaucoma entities. The optic radiation is identified semi-automatically. DTI provides information about the fiber orientation as well as a set of derived parameters describing the degree of diffusion anisotropy and diffusivity. Features for each DTI derived measure are extracted from a specified region of interest on the optic radiation. The features are grouped into three sets: Histogram, co-occurrence matrices, and Laws features. For feature selection, the features are ranked using a support vector machine classifier. The highest ranked features are used for classification. A support vector machine classifier is used for classification in a 10-fold cross validation setup. The system is applied to three age-matched subjects' categories containing 27 healthy, 39 primary open angle glaucoma (POAG), and 18 normal tension glaucoma (NTG) subjects. The discrimination accuracy between healthy and glaucoma (POAG and NTG) subjects is 94.1% with an area under the ROC of 0.97. Classification accuracy of 92.4% is obtained for the normal and the POAG groups while it increased to 100% in case of healthy and NTG groups. In addition, the system could differentiate between glaucoma types (POAG and NTG) with an accuracy of 98.3%. A complementary analysis was performed to estimate the selection bias in the obtained accuracy. The bias ranged from 10% to 20% depending on the group pair under consideration. The classification results indicate the high performance of the system compared to retina-based glaucoma detection systems. The proposed approach utilizes visual pathway analysis rather than the conventional eye analysis which presents a new trend in glaucoma detection. Analyzing the entire visual system could provide significant information that can improve the glaucoma examination flow and treatment.

DTI parameters of axonal integrity and demyelination of the optic radiation correlate with glaucoma indices.

BACKGROUND: In glaucoma, damage of retinal ganglion cells may continue to the linked optic radiations. This study investigates the correlation of glaucoma severity indicators with parameters of axonal and myelin integrity of the optic radiations. METHODS: In this observational case-control study, 13 patients with normal-tension glaucoma, 13 patients with primary open-angle glaucoma, and seven control subjects (mean age, 57.6 ± 12.5 years) were randomly selected for diffusion tensor imaging (DTI) of the optic radiations. The results of the frequency doubling test (FDT) and the HRT-based linear discriminant functions of Burk (BLDF) and Mikelberg (MLDF) were correlated with the mean of the fractional anisotropy (FA), apparent diffusion coefficient (ADC), and radial diffusivity (RD) of the optic radiations. Multiple correlation analysis, corrected for age, stage of cerebral microangiopathy, diagnosis group, and gender was conducted at increasing thresholds of linear anisotropy (C(L)) to reduce mismeasurements because of complex fiber situations. RESULTS: The best correlations were found for BLDF with FA at C(L) threshold 0.3 (0.594, p = 0.001), with ADC at C(L) 0.4 (-0.511, p = 0.005), and with RD at C(L) 0.4 (-0.585, p = 0.001). MLDF correlated with FA at C(L) 0.4 (0.393, p = 0.035). The FDT score correlated with FA at C(L) 0 (-0.491, p = 0.007) and with RD at C(L) 0 (-0.375, p = 0.045). CONCLUSIONS: In glaucoma, DTI-derived parameters of the axonal integrity (FA, ADC) and demyelination (RD) of the optic radiation are linked to HRT-based indices of glaucoma severity and to impairment of the spatial-temporal contrast sensitivity.

Changes of radial diffusivity and fractional anisotropy in the optic nerve and optic radiation of glaucoma patients.

Purpose of this study was to evaluate with diffusion-tensor imaging (DTI) changes of radial diffusivity (RD) and fractional anisotropy (FA) in the optic nerve (ON) and optic radiation (OR) in glaucoma and to determine whether changes in RD and FA correlate with disease severity. Therefore, glaucoma patients and controls were examined using 3T. Regions of interest were positioned on RD and FA maps, and mean values were calculated for ON and OR and correlated with optic nerve atrophy and reduced spatial-temporal contrast sensitivity (STCS) of the retina. We found, that RD in glaucoma patients was significantly higher in the ON (0.74 ± 0.21 versus 0.58 ± 0.17·10(-3) mm(2) s(-1); P < 0.05) and OR (0.79 ± 0.23 versus 0.62 ± 0.14·10(-3) mm(2) s(-1); P < 0.05) compared to controls. Aside, FA was significantly decreased (0.48 ± 0.15 versus 0.66 ± 0.12 and 0.50 ± 0.20 versus 0.66 ± 0.11; P < 0.05). Hereby, correlation between changes in RD/FA and optic nerve atrophy/STCS was observed (r > 0.77). In conclusion, DTI at 3 Tesla allows robust RD and FA measurements in the ON and OR. Hereby, the extent of RD increase and FA decrease in glaucoma correlate with established ophthalmological examinations.

A new approach to assess intracranial white matter abnormalities in glaucoma patients: changes of fractional anisotropy detected by 3T diffusion tensor imaging.

RATIONALE AND OBJECTIVES: The aims of this study was to evaluate, using 3-T diffusion tensor imaging, changes of fractional anisotropy (FA) in the orbital and intracranial part of the optic nerve (ON), the optic chiasm, the lateral geniculate nucleus, and different parts of the optic radiation (OR) in patients with glaucoma compared to controls and to determine whether FA correlates with disease severity. MATERIALS AND METHODS: Twenty patients with glaucoma and 22 age-matched controls were examined using 3-T diffusion tensor imaging. Regions of interest were positioned on the FA maps, and mean values were calculated for each ON, optic chiasm, lateral geniculate nucleus, and OR. Results were compared to those from controls and correlated with ON atrophy and reduced spatial-temporal contrast sensitivity of the retina. RESULTS: Compared to controls, FA in patients with glaucoma was significantly lower in the intracranial part of the ON (0.48 ± 0.15 vs 0.66 ± 0.12, P < .05) and in the OR (0.40 ± 0.16 to 0.48 ± 0.17 vs 0.53 ± 0.20 to 0.64 ± 0.11, P < .05). A high correlation between reduced FA in the intracranial ON and OR and ON atrophy and spatial-temporal contrast sensitivity of the retina was observed (r > 0.81). Otherwise, there was no significant difference in FA between patients with glaucoma and controls measured in the orbital part of the ON, optic chiasm, and lateral geniculate nucleus. CONCLUSIONS: Diffusion tensor imaging at 3 T allows robust FA measurements in the intracranial part of the ON and the OR. FA is significantly reduced in patients with glaucoma compared to controls, with a good correlation with established ophthalmologic examinations.

A framework for voxel-based morphometric analysis of the optic radiation using diffusion tensor imaging in glaucoma.

Glaucoma is an optic neuropathy affecting the entire visual system. The understanding of the glaucoma mechanism and causes remains unresolved. Diffusion tensor imaging (DTI) has been used to analyze the optic nerve and optic radiation showing global fiber abnormalities associated with glaucoma. Nevertheless, the complex structure of the optic radiation and the limitations of DTI make the localization of the glaucoma effect a difficult task. The aim of this work is to establish a framework for the determination of the local changes of the optic radiation due to glaucoma using DTI. The proposed system utilizes a semiautomated algorithm to produce an efficient identification of the optic radiation. Segmented optic radiations are transformed to a unified space using shape-based nonrigid registration. Using the deformation fields that resulted from the registration, the maps of the diffusion tensor-derived parameters are transformed to the unified space. This allows for statistical voxel-wise analysis to produce significant abnormality maps. The proposed system is applied to a group of 13 glaucoma patients and a normal control group of 10 subjects. The groups are age matched to eliminate the age effect on the analysis. Diffusion-related parameters (axial, radial and mean diffusivities) and an anisotropy index (fractional anisotropy) are studied. The anisotropy analysis indicates that the majority of the significant voxels show decreased fractional anisotropy in the glaucoma patients compared with the control group. In addition, the significant regions are mainly distributed in the middle (in reference to anterior-posterior orientation) of the optic radiation. Glaucoma subjects have increased radial diffusivity and mean diffusivity significant voxels with a main concentration in the proximal part of the right optic radiation. The proposed analysis provides a framework to capture the significant local changes of the optic radiation due to glaucoma. The preliminary analysis suggests that the glaucomatous optic radiation may suffer from localized white matter degeneration. The framework facilitates further studies and understanding of the pathophysiology of glaucoma.