Glaucoma is an eye disease once it occurs, it cannot be cured. Be that as it may, in the event that it is starting stage doesn't take the therapeutic treatment its prompts the lasting visual impairment.  Most of the literature surveys explain various techniques which are used with the help of the optic cup and optic disc to detect glaucoma. It tends to be successfully identified through the best possible segmentation of optic cup and optic disc. In this paper, we proposed about, NRR [neuro retinal rim] OTSU segmentation based technique. The disease will be confirmed by calculating the CDR [cup to disk ratio], RDR [rim to disk ratio], ISNT ratio [inferior, superior, nasal, temporal] and in analysis of glaucoma detection CDR and SVM [support vector machine] play the major role in identifying the glaucoma present or not. Our experimental technique has got the outcome of 94% accuracy.

The present study was designed to evaluate the antioxidant activity of Livomap on ethanol induced hepatotoxicity in albino wistar rats. A total of 30 rats were divided into five groups of six rats in each group. Group 1 served as normal control, Group 2-normal rat + livomap (50mg/Kg), Group 3-ethanol control rats, Group 4-ethanol + livomap (25mg/Kg) and Group 5-ethanol + livomap (50mg/Kg). The liver toxicity was induced by the administration of ethanol to the animals at a dose of 3 g/kg orally for 35 days. During the period, livomap was coadministered to the rats at doses of 25 and 50 mg/kg for 35 days. Ethanol induced rats exhibited significant increase in the levels of lipid peroxidative products and decrease in the levels of antioxidants. Co-administration of livomap to ethanol-induced rats significantly minimized the alterations in the levels of lipid peroxidation products and antioxidants. Results suggest that livomap might be beneficial in alleviating ethanol-induced oxidative damage and may be attributed to the antioxidant property of polyherbal formulation.

Detection of cancer is the utmost fascinating analysis space for scientists in the early period. The projected method is meant to identify cancer in the beginning phase. The projected method comprises several phases, such as image acquisition, pre-processing, segmentation, feature extraction, and classification. In our proposed work, segmentation is done to fragment the CT image. We use solid feature extraction (GLCM) technique to extract certain essential features from the segmented images. Further extracted features are considered for classification (Multi SVM) process to check whether cancerous or non-cancerous.

No abstract

No abstract