Modelling on-demand preprocessing framework towards practical approach in clinical analysis of diabetic retinopathy

<p>Diabetic retinopathy (DR) refers to a complication of diabetes and a prime cause of vision loss in middle-aged people. A timely screening and diagnosis process can reduce the risk of blindness. Fundus imaging is mainly preferred in the clinical analysis of DR. However; the raw fundus images are usually subjected to artifacts, noise, low and varied contrast, which is very hard to process by human visual systems and automated systems. In the existing literature, many solutions are given to enhance the fundus image. However, such approaches are particular and limited to a specific objective that cannot address multiple fundus images. This paper has presented an on-demand preprocessing frame work that integrates different techniques to address geometrical issues, random noises, and comprehensive contrast enhancement solutions. The performance of each preprocessing process is evaluated against peak signal-to-noise ratio (PSNR), and brightness is quantified in the enhanced image. The motive of this paper is to offer a flexible approach of preprocessing mechanism that can meet image enhancement needs based on different preprocessing requirements to improve the quality of fundus imaging towards early-stage diabetic retinopathy identification.</p>

Classification of Stages Diabetic Retinopathy Using MobileNetV2 Model

Diabetic retinopathy (DR) is a complication of diabetes mellitus that causes retinal damage that can lead to vision loss if not detected and treated promptly. The common diagnosis stages of the disease take time, effort, and cost and can be misdiagnosed. In the recent period with the explosion of artificial intelligence, deep learning has become the most popular tool with high performance in many fields, especially in the analysis and classification of medical images. The Convolutional Neural Network (CNN) is more widely used as a deep learning method in medical imaging analysis with highly effective. In this paper, the five-stage image of modern DR (healthy, mild, moderate, severe, and proliferative) can be detected and classified using the deep learning technique. After cross-validation training and testing on the corresponding 5,590-image dataset, a pre-MobileNetV2 training model is proposed in classifying stages of diabetic retinopathy. The average accuracy of the model achieved was 93.89% with the precision of 94.00%, recall 92.00% and f1-score 90.00%. The corresponding thermal image is also given to help experts for evaluating the influence of the retina in each different stage.

Discovering the Potential of Natural Antioxidants in Age-Related Macular Degeneration: A Review

Age-related macular degeneration (AMD) is a multifactorial disease associated with anatomical changes in the inner retina. Despite tremendous advances in clinical care, there is currently no cure for AMD. This review aims to evaluate the published literature on the therapeutic roles of natural antioxidants in AMD. A literature search of PubMed, Web of Science and Google Scholar for peer-reviewed articles published between 1 January 2011 and 31 October 2021 was undertaken. A total of 82 preclinical and 18 clinical studies were eligible for inclusion in this review. We identified active compounds, carotenoids, extracts and polysaccharides, flavonoids, formulations, vitamins and whole foods with potential therapeutic roles in AMD. We evaluated the integral cellular signaling pathways including the activation of antioxidant pathways and angiogenesis pathways orchestrating their mode of action. In conclusion, we examined the therapeutic roles of natural antioxidants in AMD which warrant further study for application in clinical practice. Our current understanding is that natural antioxidants have the potential to improve or halt the progression of AMD, and tailoring therapeutics to the specific disease stages may be the key to preventing irreversible vision loss.

Clinical Features and Surgical Management of Pituitary Adenoma During Pregnancy: Case Series and Literature Review

Purpose Although conservative treatment was recommended for pregnant patients with pituitary adenomas (PAs), surgical treatment is occasionally necessary for those with acute symptoms. However, surgical intervention among these patients is poorly studied. Methods Six patients with PAs who underwent surgical treatment during pregnancy at Peking Union Medical College Hospital between January 1990 and June 2021 and another 35 pregnant patients profiled in the literature were included. Results All the 41 enrolled patients (mean age 29.8 ± 5.3 years) had acute symptoms including visual field defects, severe headaches, or vision loss requiring emergency pituitary surgeries. Mean tumor diameter was 2.16 ± 0.9 cm, and 92.6% were macroadenomas. PA apoplexies were found in 23 patients. The average gestation time at surgery was 25.1 ± 7.1 weeks; 55.9% of these patients underwent surgery in the second trimester of pregnancy. Multidisciplinary team was involved from before surgery to after delivery. Except one patient underwent an induced abortion, and one fetus died due to a nuchal cord, thirty-nine patients delivered successfully, and 37 of fetuses were healthy till the last follow-up. One fetus died of congenital diaphragmatic hernia, and another had a low Apgar score after a cesarean section but survived. Conclusion PA surgery for pregnant patients with PAs is effective and safe during the second and third trimesters. Pregnant patients requiring emergency PA surgery need multidisciplinary evaluation and healthcare management. Cooperation of neurosurgery, endocrinology, obstetrics, anesthesiology, and neonatology is necessary for a successful surgical intervention for pregnant patients with PAs.

Therapeutic Management of Ocular Ischemia in Takayasu’s Arteritis: A Case-Based Systematic Review

BackgroundTakayasu’s arteritis (TA) is a rare, chronic granulomatous large-vessel vasculitis that can lead to ocular ischemia. Ocular outcomes after therapeutic management in TA remain largely unknown. We herein conduct a case-based systematic review to address the current treatment options in this particular cohort.MethodsPubMed, Medline, and EMBASE databases were searched pertaining to ocular outcomes after systemic treatment in TA. Studies reporting ocular examinations before and after treatment in TA patients with ocular ischemia were included. Clinical characteristics, therapies, ocular outcomes, and complications were recorded.ResultsA 29-year-old woman with newly diagnosed TA showed dramatic regression of Takayasu’s retinopathy (TR) following balloon angioplasty. Optical coherence tomography angiography (OCTA) was used as a novel strategy for subsequent follow-up. A total of 117 eyes of 66 patients with a median age of 27 years were included for systematic review. TR was the most common ocular manifestation. Oral steroids were prescribed in nearly all patients (n = 65), followed by the use of methotrexate and antiplatelet therapy. Of the patients, 65.8% and 34.2% underwent open surgery and endovascular procedure, respectively. The median follow-up period was 12 weeks (interquartile range 8–33.5). Surgical therapy showed better ocular improvement (including visual and imaging responses) in both acute and chronic vision loss, along with fewer complications than medical therapy alone. In the surgical group, the visual prognosis was significantly better in patients with initial visual acuity better than 20/200 (p = 0.03) and those who underwent surgery before stage III TR (p = 0.01). Ocular outcomes were equivalent in the two surgical approaches.ConclusionClinicians should be familiar with ophthalmic manifestations of this potentially treatable complication in TA. Compared with medical therapy alone, surgical intervention might be a better choice for both acute and chronic vision loss. Surgery is best recommended before the onset of irreversible ischemia to the globe. A combined regimen (oral steroids, immunosuppressants, and antiplatelet drugs) might be effective for those with surgical contradictions or reluctance to an invasive procedure. Physicians should be aware of the importance of ocular examinations, including OCTA, during the diagnosis and follow-up in TA.

Capturing the experiences of patients with inherited optic neuropathies: a systematic review of patient-reported outcome measures (PROMs) and qualitative studies

Purpose To identify and comprehensively evaluate studies capturing the experience of individuals affected by an inherited optic neuropathy (ION), focusing on patient-reported outcome measures (PROMs) and qualitative studies where the health status and quality of life (QoL) of these individuals have been explored. Methods Systematic review of five databases using a search strategy combining four concepts: (1) ION; (2) QoL and health status; (3) PROMs; and (4) qualitative research. Studies assessing the impact of ION on any QoL domain using a PROM or qualitative methodology were included and appraised, using criteria based on the COSMIN checklist (for PROM studies) and the CASP checklist (for qualitative studies). Results Of 1326 unique articles identified, six studies were included. Five PROMs were identified: Visual Function Index (VF-14); Hospital Anxiety and Depression Scale (HADS); a novel graphical online assessment tool (NGOAT) for reporting emotional response to vision loss; a new PROM informed by the DSM-V Criteria for Major Depressive Disorder; and an interpersonal and career ‘impact rating’ PROM. The psychometric performance of included PROMs were poorly described. Qualitative studies found that vision loss resulted in psychosocial losses including loss of social and communication skills and loss of independence and freedom. Factors that modified the response to vision loss were also identified. Conclusion The current PROMs used by individuals with ION have poor content coverage, primarily measuring activity limitation and emotional well-being, and insufficient reporting of psychometric performance. There is a need to develop a PROM for individuals ION to report their experiences of living with their condition.

Modulated anti-VEGF therapy under the influence of lipid metabolizing proteins in Age related macular degeneration: a pilot study

Age-related macular degeneration (AMD) is a devastating retinal disease that results in irreversible vision loss in the aged population. The complex genetic nature and degree of genetic penetrance require a redefinition of the current therapeutic strategy for AMD. We aimed to investigate the role of modifiers for current anti-VEGF therapy especially for non-responder AMD patients. We recruited 78 wet AMD cases (out of 278 AMD patients) with their socio-demographic and treatment regimen. Serum protein levels were estimated by ELISA in AMD patients. Data pertaining to the number of anti-VEGF injections given (in 1 year) along with clinical images (FFA and OCT) of AMD patients were also included. Visual acuity data (logMAR) for 46 wet AMD cases out of a total of 78 patients were also retrieved to examine the response of anti-VEGF injections in wet AMD cases. Lipid metabolizing genes (LIPC and APOE) have been identified as chief biomarkers for anti-VEGF response in AMD patients. Both genotypes ‘CC’ and ‘GC’ of LIPC have found to be associated with a number of anti-VEGF injections in AMD patients which could influence the expression of B3GALTL,HTRA1, IER3, LIPC and SLC16A8 proteins in patients bearing both genotypes as compared to reference genotype. Elevated levels of APOE were also observed in group 2 wet AMD patients as compared to group 1 suggesting the significance of APOE levels in anti-VEGF response. The genotype of B3GALTL has also been shown to have a significant association with the number of anti-VEGF injections. Moreover, visual acuity of group 1 (≤ 4 anti-VEGF injections/year) AMD patients was found significantly improved after 3 doses of anti-VEGF injections and maintained longitudinally as compared to groups 2 and 3. Lipid metabolising genes may impact the outcome of anti-VEGF AMD treatment.

Flexible cue anchoring strategies enable stable head direction coding in both sighted and blind animals

Vision plays a crucial role in instructing the brain's spatial navigation systems. However, little is known about how vision loss affects the neuronal encoding of spatial information. Here, recording from head direction (HD) cells in the anterior dorsal nucleus of the thalamus in mice, we find stable and robust HD tuning in blind animals. In contrast, placing sighted animals in darkness significantly impairs HD cell tuning. We find that blind mice use olfactory cues to maintain stable HD tuning and that prior visual experience leads to refined HD cell tuning in blind adult mice compared to congenitally blind animals. Finally, in the absence of both visual and olfactory cues, the HD attractor network remains intact but the preferred firing direction of HD cells continuously drifts over time. We thus demonstrate remarkable flexibility in how the brain uses diverse sensory information to generate a stable directional representation of space.

Sesamin inhibits cellular inflammation of microglial cells in the retina and alleviates diabetic retinopathy

Diabetic retinopathy (DR) is the most common micro-vascular complication of diabetes, and the leading cause of vision loss and blindness globally. Due to the unsatisfied outcome of current therapies, a novel strategy needs to be developed. BV2 microglial cells were treated with 25 natural compounds respectively in the stimulation of high glucose (HG), to screen for the potential candidate drug. Streptozotocin (STZ)- induced diabetic mice were injected with different doses of the candidate Sesamin every two days for one month. Then, its protective role and possible mechanism were evaluated. Sesamin was selected as candidate drug due to its inhibition on the secretion of tumor necrosis factor-α (TNFα) in the screen assay. Sesamin also dose-dependently inhibited mRNA levels of HG-induced inflammatory cytokines, including TNFα, interleukin (IL)-1β and IL-6, activated NF-κB signaling pathway, and reduced oxidative stress by decreasing reactive oxygen species levels and increasing antioxidant enzymes in the BV2 and primary retinal microglia. Additionally, Sesamin alleviated brain-retinal barrier breakdown by Evan's blue leakage assay and reduced inflammation in Streptozotocin-induced diabetic mice. In conclusion, Sesamin effectively inhibits HG-induced microglial inflammation in the retina both in vivo and in vitro, suggesting that Sesamin might serve as a candidate drug for DR treatment.