A 54-year-old man developed left eye inflammation three days after cataract surgery and was diagnosed with endophthalmitis. Aqueous culture revealed Ochrobactrum anthropi resistant to vancomycin and cephalosporin. Systemic and intravitreal ciprofloxacin injections caused only transient improvement and eventually, pars plana vitrectomy was done. There was complete resolution, good visual recovery, and no recurrence. O.anthropi is an uncommon organism with a characteristic resistance to empirical antibiotics and usually causes chronic infection in immunocompromised. We report a rare case of acute endophthalmitis in an immunocompetent patient. To the best of our knowledge, this is the first report of O. anthropi endophthalmitis from India.
Load forecasting is an issue of great importance for the reliable operation of the electric power system grids. Various forecasting methodologies have been proposed in the international research bibliography, following different models and mathematical approaches. In the current work, several latest methodologies based on artificial neural networks along with other techniques have be discussed, in order to obtain short-term load forecasting. In this paper, approaches taken by different researchers considering different parameters in means of predicting the lease error has been shown. The paper investigates the application of artificial neural networks (ANN) with fuzzy logic (FL), Genetic Algorithm(GA), Particle Swarm Optimization(PSO) and Support Vector Machines(SVM) as forecasting tools for predicting the load demand in short term category. The extracted outcomes indicate the effectiveness of the proposed method, reducing the relative error between real and theoretical data
Abstract We present SLIViT, a deep-learning framework that accurately measures disease-related risk factors in volumetric biomedical imaging, such as magnetic resonance imaging (MRI) scans, optical coherence tomography (OCT) scans, and ultrasound videos. To evaluate SLIViT, we applied it to five different datasets of these three different data modalities tackling seven learning tasks (including both classification and regression) and found that it consistently and significantly outperforms domain-specific state-of-the-art models, typically improving performance (ROC AUC or correlation) by 0.1-0.4. Notably, compared to existing approaches, SLIViT can be applied even when only a small number of annotated training samples is available, which is often a constraint in medical applications. When trained on less than 700 annotated volumes, SLIViT obtained accuracy comparable to trained clinical specialists while reducing annotation time by a factor of 5,000 demonstrating its utility to automate and expedite ongoing research and other practical clinical scenarios. *Oren Avram and Berkin Durmus equally contributed to this work. **Srinivas R. Sadda and Eran Halperin jointly supervised this study.
<i>Aim:</i> To investigate the occurrence of neuronal damage, as the earliest change occurring, before the clinical evidence of diabetic retinopathy. <i>Methods:</i> 70 eyes of subjects with type 2 diabetes mellitus and with no evidence of diabetic retinopathy (cases) and 40 eyes of subjects with no diabetes mellitus (controls) were studied using spectral-domain OCT and microperimetry. The influence of age and gender on the outcome measures was also analyzed. <i>Results:</i> Age- and gender-matched subjects showed a decreased mean retinal nerve fiber layer thickness in cases when compared to the controls (27 vs. 33 µm; p = 0.018). Among the cases, subjects between 40 and 45 years of age showed a reduced mean central foveal thickness (175.1 vs. 198.1 µm; p = 0.05), mean retinal thickness in the central 6-mm fundus (260.5 vs. 275.3 µm; p = 0.006) and mean retinal nerve fiber layer thickness (29 vs. 39 µm; p = 0.036) when compared to the controls. However, no differences were noted in the microperimetry outcomes in cases when compared to the controls. The duration of diabetes and the glycemic control did not show any significant changes on the outcome measures in cases, except for a significantly lower mean retinal sensitivity in diabetics with glycosylated hemoglobin values <7% as compared to those with glycosylated hemoglobin ≥7% (14.1 ± 2.9 vs. 15.4 ± 1.7 dB; p = 0.027). <i>Conclusion:</i> The results suggest that there is some evidence of early neuronal damage particularly on spectral-domain OCT, before the clinical evidence of diabetic retinopathy, in subjects with type 2 diabetes mellitus.
To report the outcome of a case of subretinal lens fragment that was observed after vitreous surgery for a giant retinal tear.Case report. The patient underwent vitreous surgery for a giant retinal tear; in the immediate postoperative period, a fragment of lens was observed in the subretinal space.The patient was managed with topical and systemic steroids alone. At a follow-up, 6 months later, the lens matter had absorbed.In the present case, the subretinal lens fragment showed complete resolution with conservative treatment, obviating the need for surgical intervention.