Treatment Of Ophthalmologic Diseases Research Articles

Improving sensitivity and connectivity of retinal vessel segmentation via error discrimination network.

Automated retinal vessel segmentation is crucial to the early diagnosis and treatment of ophthalmological diseases. Many deep-learning-based methods have shown exceptional success in this task. However, current approaches are still inadequate in challenging vessels (e.g., thin vessels) and rarely focus on the connectivity of vessel segmentation. We propose using an error discrimination network (D) to distinguish whether the vessel pixel predictions of the segmentation network (S) are correct, and S is trained to obtain fewer error predictions of D. Our method is similar to, but not the same as, the generative adversarial network. Three types of vessel samples and corresponding error masks are used to train D, as follows: (1) vessel ground truth; (2) vessel segmented by S; (3) artificial thin vessel error samples that further improve the sensitivity of D to wrong small vessels. As an auxiliary loss function of S, D strengthens the supervision of difficult vessels. Optionally, we can use the errors predicted by D to correct the segmentation result of S. Compared with state-of-the-art methods, our method achieves the highest scores in sensitivity (86.19%, 86.26%, and 86.53%) and G-Mean (91.94%, 91.30%, and 92.76%) on three public datasets, namely, STARE, DRIVE, and HRF. Our method also maintains a competitive level in other metrics. On the STARE dataset, the F1-score and area under the receiver operating characteristic curve (AUC) of our method rank second and first, respectively, reaching 84.51% and 98.97%. The top scores of the three topology-relevant metrics (Conn, Inf, and Cor) demonstrate that the vessels extracted by our method have excellent connectivity. We also validate the effectiveness of error discrimination supervision and artificial error sample training through ablation experiments. The proposed method provides an accurate and robust solution for difficult vessel segmentation.

Deep Att-ResGAN: A Retinal Vessel Segmentation Network for Color Fundus Images

Retinal vessel segmentation plays a significant role in the diagnosis and treatment of ophthalmological diseases. Recent studies have proved that deep learning can effectively segment the retinal vessel structure. However, the existing methods have difficulty in segmenting thin vessels, especially when the original image contains lesions. Based on generative adversarial network (GAN), this paper proposes a deep network with residual module and attention module (Deep Att-ResGAN). The network consists of four identical subnetworks. The output of each subnetwork is imported to the next subnetwork as contextual features that guide the segmentation. Firstly, the problems of the original image, namely, low contrast, uneven illumination, and data insufficiency, were solved through image enhancement and preprocessing. Next, an improved U-Net was adopted to serve as the generator, which stacks the residual and attention modules. These modules optimize the weight of the generator, and enhance the generalizability of the network. Further, the segmentation was refined iteratively by the discriminator, which contributes to the performance of vessel segmentation. Finally, comparative experiments were carried out on two public datasets: Digital Retinal Images for Vessel Extraction (DRIVE) and Structured Analysis of the Retina (STARE). The experimental results show that Deep Att-ResGAN outperformed the equivalent models like U-Net and GAN in most metrics. Our network achieved accuracy of 0.9565 and F1 of 0.829 on DRIVE, and accuracy of 0.9690 and F1 of 0.841 on STARE.

New drug delivery system in ophthalmology: results studying the surface structure of soft contact lenses from various polymer

The development of an ophthalmic therapeutic system includes research on the spatial structure of soft contact lens polymers and the study of the processes of saturation and release of medicinal substances from them. This allows you to determine the methods of saturation of contact lenses with medicinal agents and will open up new opportunities in the treatment of ophthalmological diseases. The purpose of this preliminary fragment of large-scale research was to study the surface structure of soft contact lenses made of various polymers. The following polymers were used in the work: Nelfilcon A, Hilafilcon B, Nezofilcon A, Etafilcon A, Lotrafilcon B. The following pharmaceutical substances were used: Brimonidine Tartrate, Betaxolol Hydrochloride, Pyridoxine Hydrochloride. The surface structure of soft contact lenses was studied using atomic force microscopy. Each material under study has a different surface character, which together with the differences in pore properties determines its individuality. Based on this, it should be assumed that the surface of soft contact lenses affects the possibility of their potential use as a means of delivering drug agent molecules to the eye tissues. In all cases of soft contact saturation, the highest absorption capacity was demonstrated by Hilafilcon B and Etafilcon A with a similar surface.

Photoablation of Human Vitreous Opacities by Light-Induced Vapor Nanobubbles.

Myopia, diabetes, and aging are the main causes of progressive vitreous collagen aggregation, resulting in vitreous opacities, which can significantly disturb vision. As vitreous opacities, which induce the visual phenomenon of "floaters", are accessible with nanomaterials and light, we propose a nanotechnology-based approach to locally ablate them with highly reduced light energy compared to the more traditional YAG laser therapy. Our strategy relies on the plasmon properties of gold nanoparticles that generate vapor nanobubbles upon pulsed-laser illumination whose mechanical force can ablate vitreous opacities. We designed gold nanoparticles coated with hyaluronic acid (HA), which have excellent diffusional mobility in human vitreous, an essential requirement to reach the vitreous opacities. In addition, we found that HA-coated gold nanoparticles can accumulate extensively on human vitreous opacities that were obtained by vitrectomy from patients with vision-degrading myodesopsia. When subsequently applying nanosecond laser pulses, the collagen aggregates were efficiently destroyed with ∼1000 times less light energy than typically used in YAG laser therapy. This low-energy "floater-specific destruction", which is due to the accumulation of the small gold nanoparticles on the opacities, is attractive, as it may be safer to the surrounding ocular tissues while at the same time being easier and faster to apply compared to YAG laser therapy, where the opacities need to be ablated piece by piece by a tightly focused laser beam. Gold nanoparticle-assisted photoablation may therefore provide a safer, faster, and more reliable destruction of vitreous opacities in the treatment of ophthalmologic diseases.

An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images

Algorithms for retinal vessel segmentation are powerful tools in automatic tracking systems for early detection of ophthalmological and cardiovascular diseases, and for biometric identification. In order to create more robust and reliable systems, the algorithms need to be accurately evaluated to certify their ability to emulate specific human expertise. The main contribution of this paper is an unsupervised method to detect blood vessels in fundus images using a coarse-to-fine approach. Our methodology combines Gaussian smoothing, a morphological top-hat operator, and vessel contrast enhancement for background homogenization and noise reduction. Here, statistics of spatial dependency and probability are used to coarsely approximate the vessel map with an adaptive local thresholding scheme. The coarse segmentation is then refined through curvature analysis and morphological reconstruction to reduce pixel mislabeling and better estimate the retinal vessel tree. The method was evaluated in terms of its sensitivity, specificity and balanced accuracy. Extensive experiments have been conducted on DRIVE and STARE public retinal images databases. Comparisons with state-of-the-art methods revealed that our method outperformed most recent methods in terms of sensitivity and balanced accuracy with an average of 0.7819 and 0.8702, respectively. Also, the proposed method outperformed state-of-the-art methods when evaluating only pathological images that is a more challenging task. The method achieved for this set of images an average of 0.7842 and 0.8662 for sensitivity and balanced accuracy, respectively. Visual inspection also revealed that the proposed approach effectively addressed main image distortions by reducing mislabeling of central vessel reflex regions and false-positive detection of pathological patterns. These improvements indicate the ability of the method to accurately approximate the vessel tree with reduced visual interference of pathological patterns and vessel-like structures. Therefore, our method has the potential for supporting expert systems in screening, diagnosis and treatment of ophthalmological diseases, and furthermore for personal recognition based on retinal profile matching.

Clinical application of stem cells: An update 2015

Stem cell transplantation has the long history of more than 50 years from the first bone marrow transplantation in 1957. From the 2000s, clinical applications of stem cells significantly increased with more diseases and more patients treated with stem cells. Both autologous stem cells and allogenic stem cells as well as adult stem cells and induced pluripotent stem cells (iPSCs), and both in vitro non-expanded stem cells and in vitro expanded stem cells were clinically applied. For adult stem cells, besides hematopoietic stem cells (HSCs), mesenchymal stem cells (MSCs), neural stem cells, endothelial progenitor cells, limbal stem cells… also were used in the treatment of some diseases. To the year 2015, applications of MSCs have dramatically increased when some MSCs based drugs that were approved and commercialized in some countries. About iPSCs, Japanese scientists also firstly applied the iPSCs in treatment of ophthalmological diseases. Currently, the European Medicines Agency approved the first expanded stem cell therapy to repair damaged cornea in the Europe. This review aimed to summarize, update clinical applications of stem cells to 2015.

ABC Transporters in the Eyes of Dogs and Implications in Drug Therapy

Purpose: The current study aims to quantifies the level of expression of selected adenosine triphosphate-binding cassette (ABC) efflux transporters and the major drug metabolizing enzyme CYP450 3A12 in the eyes of dogs.Materials and methods: The levels of expression were quantified by real-time polymerase chain reaction in the cornea, conjunctiva and retinal tissue.Results: ABCB1 mRNA is present at high levels in all analysed tissues. ABCC1, ABCC3 and ABCC4 are expressed predominantly in the conjunctiva and at very low levels in the cornea. ABCC2 could not be detected in any of the tissues. CYP3A12 expression was found in the retina and conjunctiva.Conclusion: These data are presented for the first time for ocular tissues of dogs of different breeds and a comparison with other species such as humans and rabbits demonstrated remarkable species differences, which might be of clinical relevance. The impact of these findings is discussed with reference to topical and systemic drug application in the treatment of ophthalmological diseases.

Reflection of laser radiation from retina quasi-crystal layers: Model investigations

Reflection of laser radiation from the upper and lower bound of the quasi-crystal layers by retina (a layer of nervous fibers and photoreceptor disks) in the framework of holographic model of physiological optics was considered. Cases of dark-adapted and completely decolorized photoreceptor disks were considered. Two problems were considered for reflection from the lower bounds: (1) ordinary wave reflection from crystal-isotropic media interface; (2) extraordinary wave reflection from crystal-isotropic media interface. Graphs for two components of back-scattered field, depending upon the laser incidence angle at retina and the angle between incidence plane and optical axis of retina layer nerve fibers were obtained. Cases of dark-adapted and completely decolorized photoreceptor disks were considered. The results obtained may be used in laser methods for diagnostics and treatment of ophthalmologic diseases.

Brain damage related vision loss

Twenty percent of visual impairment in children is caused by brain damage. Children with brain damage related visual impairment (CVI) should be assessed in infancy and during their preschool and school age for detection of deviations from normal development of cognitive visual functions at the times these functions should normally emerge. During the last 20 years, treatment of ophthalmologic diseases has advanced greatly. A similar development has occurred in the knowledge of functioning of visually impaired children and assessment of impaired vision. However, early intervention and assessment for special education for children with CVI have not been taught by the leading teaching centres and thus paediatric vision (re)habilitation is lacking behind other areas of ophthalmology and optometry. The groups of children with motor problems, auditory processing problems, intellectual deficiencies of varying severity, who are at high risk of having CVI, are well-known but routine assessment of vision of these children is not a part of vision screening. With some further education of all paediatric services, a change in attitudes toward CVI and minor changes in routine vision services this poorly served fifth of visually impaired children could get adequate treatment, early intervention and rehabilitation.

Lenticular changes associated with beta radiation of the eye and their significance.

aclinical evaluation of radiation therapy of lesions of the eye requires close co-operation between the ophthalmologist and the radiologist. The ophthalmologist in general is not qualified, without special training, to carry out radiation treatment, and the radiologist is usually not qualified to employ such therapy without a thorough knowledge of the pathogenesis of the lesion treated. This study represents a co-ordinated effort between the Departments of Radiology and Ophthalmology at Western Reserve University. Prior to 1940, gamma rays from radium and grenz rays were used in radiation therapy for various ophthalmologic conditions. In that year, Burnam and Neill (1) reported on the use of beta rays originating from radon gas, the daughter isotope of radium, contained in a glass bulb enclosed within a brass cylinder. This type of applicator was in general use until artificially produced radioactive isotopes became available. In 1950 two of the present authors (C. I T. and H. L. F.) reported on the use of a Sr90 beta-ray applicator in the treatment of ophthalmologic diseases (2, 3). This applicator had the advantage of being a pure beta particle emitter and, because of the long half-life of Sr90, did not require frequent replenishing. Reports are now available concerning the physical characteristics of the applicator, the biological and therapeutic response to the radiation, and the recommended dosage schedules for treating certain ophthalmologic conditions (4). During the last few years, much has been written concerning the complications observed following beta irradiation of the eve (4. 6. 8. 9). Manv of these changes are the natural sequelae of large doses. They include scleral atrophy, conjunctival scarring, and telangiectasia. The one change that has not been completely evaluated clinically, although it has received widespread attention experimentally, is that which occurs in the lens. Any damage to that structure would appear to be very significant, since it may be associated with impairment of vision. A well established pattern is known to occur, and certain pathological changes take place in a lens exposed to a sufficient amount of radiation (5–8). As a rule, these changes are stationary. Rarely, but especially after high doses of radiation, complete opacity has been observed. The onset of cataract formation ranges from two to ten years after irradiation, depending upon the total dose delivered. Several reports place the maximum as long as fifteen years following exposure to ionizing radiation (5, 6, 9). In general, 500 r is considered potentially dangerous to the human lens (5), while experimental investigations by Leinfelder and Dickerson (15) would indicate that 5,000 r produces a massive insult. Von Sallmann et al. have indicated that direct or indirect injury to cell nuclei by irradiation is dose dependent (8).