Enhancement of fundus photographs taken through cataracts

An Annotation-Free Restoration Network for Cataractous Fundus Images

Cataracts are the leading cause of vision loss worldwide. Restoration algorithms are developed to improve the readability of cataract fundus images in order to increase the certainty in diagnosis and treatment for cataract patients. Unfortunately, the requirement of annotation limits the application of these algorithms in clinics. This paper proposes a network to annotation-freely restore cataractous fundus images (ArcNet) so as to boost the clinical practicability of restoration. Annotations are unnecessary in ArcNet, where the high-frequency component is extracted from fundus images to replace segmentation in the preservation of retinal structures. The restoration model is learned from the synthesized images and adapted to real cataract images. Extensive experiments are implemented to verify the performance and effectiveness of ArcNet. Favorable performance is achieved using ArcNet against state-of-the-art algorithms, and the diagnosis of ocular fundus diseases in cataract patients is promoted by ArcNet. The capability of properly restoring cataractous images in the absence of annotated data promises the proposed algorithm outstanding clinical practicability.

Measurement of ocular counter-roll using iris images during binocular fixation and head tilt

Objective

To compare the ocular counter-roll (OCR) measured using iris images during binocular fixation and head tilt with OCR measured via fundus photography.

Methods

Fifty-three healthy college students participated in this study. The mean OCR was measured by collection of iris images and fundus images under seven head tilt conditions (0 degrees; 10, 20, and 30 degrees right; and 10, 20, and 30 degrees left). Three iris images (crossed pupil center, pupil center, and pupil periphery) were taken using a slit-lamp biomicroscope with an ophthalmic camera and a half-silvered mirror; fundus images were collected via fundus photography. The mean OCR values were compared between images taken with each method.

Results

No iris images or head tilt conditions revealed any significant differences in mean OCR comparison with fundus images. The mean difference in OCR was smallest, and the correlation was greatest, between the crossed pupil center and fundus images.

Conclusion

A half-silvered mirror and iris images can replace fundus photography for the measurement of OCR.

Computer-aided diagnosis based on enhancement of degraded fundus photographs

PURPOSE

Retinal imaging is an important and effective tool for detecting retinal diseases. However, degraded images caused by the aberrations of the eye can disguise lesions, so that a diseased eye can be mistakenly diagnosed as normal. In this work, we propose a new image enhancement method to improve the quality of degraded images.

METHODS

A new method is used to enhance degraded-quality fundus images. In this method, the image is converted from the input RGB colour space to LAB colour space and then each normalized component is enhanced using contrast-limited adaptive histogram equalization. Human visual system (HVS)-based fundus image quality assessment, combined with diagnosis by experts, is used to evaluate the enhancement.

RESULTS

The study included 191 degraded-quality fundus photographs of 143 subjects with optic media opacity. Objective quality assessment of image enhancement (range: 0-1) indicated that our method improved colour retinal image quality from an average of 0.0773 (variance 0.0801) to an average of 0.3973 (variance 0.0756). Following enhancement, area under curves (AUC) were 0.996 for the glaucoma classifier, 0.989 for the diabetic retinopathy (DR) classifier, 0.975 for the age-related macular degeneration (AMD) classifier and 0.979 for the other retinal diseases classifier.

CONCLUSION

The relatively simple method for enhancing degraded-quality fundus images achieves superior image enhancement, as demonstrated in a qualitative HVS-based image quality assessment. This retinal image enhancement may, therefore, be employed to assist ophthalmologists in more efficient screening of retinal diseases and the development of computer-aided diagnosis.

Enhancement of retinal images: pros and problems

Evaluation of retinal images is essential to modern ophthalmic care. With the advent of image processing equipment, digital recording and processing of retinal images is starting to replace the standard film based fundus photography. The ability to enhance images is cited as one of the major benefits of this expensive technology. This paper critically reviews the practices employed in the image enhancement literature. It is argued that the papers published to date have not presented convincing evidence regarding the diagnostic value of retinal image enhancement. The more elaborate studies in radiology suggest, at best, modest diagnostic improvement with enhancement. The special difficulties associated with the demonstration of an improved diagnosis in ophthalmic imaging are discussed in terms of the diagnostic task and the selection of study populations.

The fractal properties of retinal vessels: embryological and clinical implications

The branching patterns of retinal arterial and venous systems have characteristics of a fractal, a geometrical pattern whose parts resemble the whole. Fluorescein angiogram collages were digitised and analysed, demonstrating that retinal arterial and venous patterns have fractal dimensions of 1.63 +/- 0.05 and 1.71 +/- 0.07, respectively, consistent with the 1.68 +/- 0.05 dimension of diffusion limited aggregation. This finding prompts speculation that factors controlling retinal angiogenesis may obey Laplace's equation, with fluctuations in the distribution of embryonic cell-free spaces providing the randomness needed for fractal behaviour and for the uniqueness of each individual's retinal vascular pattern. Since fractal dimensions characterise how completely vascular patterns span the retina, they can provide insight into the relationship between vascular patterns and retinal disease. Fractal geometry offers a more accurate description of ocular anatomy and pathology than classical geometry, and provides a new language for posing questions about the complex geometrical patterns that are seen in ophthalmic practice.

Electro-optic fundus imaging

Fundus imaging and photography are cornerstones of modern ophthalmic practice. The recent developments in electro-optic and computer imaging technology resulted in many improvements in the acquisition and analysis of fundus images, which already are being used in commercial fundus imaging systems. This paper reviews the basic aspects of the electro-optic methods for fundus imaging, with emphasis on the differences between these new techniques and conventional, film-based, fundus photography. Potential benefits of these systems in image acquisition, archival, communication, processing, and quantitative analysis, as as well as their current advantages and shortcomings are discussed.

Restoration of retinal images obtained through cataracts

An optical model for imaging the retina through cataracts has been developed. The images are treated as sample functions of stochastic processes. On the basis of the model a homomorphic Weiner filter can be designed that will optimally restore the cataractous image (in the mean-square-error sense). The design of the filter requires a priori knowledge of the statistics of either the cataract transmittance function or the noncataractous image. The cataract transmittance function, assumed to be low pass in nature, can be estimated from the cataractous image of the retina. The statistics of the noncataractous image can be estimated using an old, precataractous photograph of the same retina, which is frequently available. Various modes of this restoration concept were applied to clinical photographs and found to be effective. The best results were obtained with short-space enhancement using averaged short-space estimates of the spectra of the two images.