Search

Glaucoma is an ocular disease which causes the eyes' optic nerves to suffer from irreversible blindness because of increased intraocular pressure. Early detection and glaucoma screening can prevent loss of vision. A common way to diagnose the progression of glaucoma is through examination by a special ophthalmologist of the dilated pupil of the eye. But this approach is difficult and takes a lot of time, so automation can solve the problem with the concept of double tier deep convolution neural networks. This network is well suited for resolving this type of problem, as it can deduce hierarchical data from the image that allows them to discern among glaucoma and non-glaucoma diagnostic patterns. It is composed with different layers. Every layer contains hidden layers like turbidity, max pooling, output and the fully connected layer. The retinal images are processed in the hidden layers, and the results obtained are combined and classified as normal or glaucomatous. The efficiency of the double tier deep convolutional neural network has been compared with different existing recognition methodologies. The outcomes show that the double tier deep convolutional neural network gives better performance when compared with other methodologies in terms of accuracy of 92.64%, sensitivity of 92.18%, specificity of 91.20% and precision of 90.76%. [ABSTRACT FROM AUTHOR]

Gliomas are often difficult to find and distinguish using typical manual segmentation approaches because of their vast range of changes in size, shape, and appearance. Furthermore, the manual annotation of cancer tissue segmentation under the close supervision of a human professional is both time-consuming and exhausting to perform. It will be easier and faster in the future to get accurate and quick diagnoses and treatments thanks to automated segmentation and survival rate prediction models that can be used now. In this article, a segmentation model is designed using RCNN that enables automatic prognosis on brain tumors using MRI. The study adopts a U-Net encoder for capturing the features during the training of the model. The feature extraction extracts geometric features for the estimation of tumor size. It is seen that the shape, location, and size of a tumor are significant factors in the estimation of prognosis. The experimental methods are conducted to test the efficacy of the model, and the results of the simulation show that the proposed method achieves a reduced error rate with increased accuracy than other methods. [ABSTRACT FROM AUTHOR]

The automatic segmentation of the tumor region from Magnetic Resonance cerebrum imageries is a difficult task in medical image analysis. Numerous techniques have been created with the goal of improving the segmentation effectiveness of the automated framework. As of late, Convolutional Neural Networks have accomplished better performance in various recognition tasks. In this paper, 2D-ConvNet with skull stripping (SS-2D ConvNet) based brain tumor segmentation technique have been presented. In the proposed method, initially, the input MRI images are preprocessed to reduce noise and skull stripped to correct the contrast and non-uniformity. It is further processed through the 2D-ConvNet for the segmentation of brain tumor. In particular, the proposed method has been compared with other existing methods, and it achieves better performances and yield precise segmentation with dice scores of 91%, accuracy of 89%, specificity of 98%, and sensitivity of 87%. [ABSTRACT FROM AUTHOR]

Deep learning is a useful technique for investigating the medicinal images. Glaucoma is a neurotic condition, dynamic neuro degeneration of the optic nerve, which leads visual impairment. It could be forestalled by an early detection of glaucoma and the regular screening with specialist for glaucoma diagnosis. Glaucoma is assessed by observing intra ocular pressure and optic Cup-Disc-Ratio (CDR). In this paper, novel mechanized glaucoma recognition has been performed by utilizing computer supported analysis from fundus images. The simulation outcomes are acquired by utilizing a Support Vector Machine based VGG-19 network architecture. The CDR threshold value of 0.41 has been used for glaucoma recognition. The fundus images which has the CDR greater than 0.41 is treated as glaucoma affected and less than 0.41 is non-glaucoma fundus images. The proposed glaucoma recognition system works with reasonable to obtain and generally utilized digital color fundus images. For the set of 175 fundus images a classification precision of 94% has been accomplished. [ABSTRACT FROM AUTHOR]