Search

High rated and active research in Ophthalmic field has paved the way for the detection of several retinal disorders which helps the ophthalmologist, in scheduling and executing timely treatment. There exist different imaging device for retinal examination in ophthalmology with varying degrees of resolution. The images obtained from such imaging devices contains noise which must be eliminated for producing accurate results. This paper mainly concentrates on using boosted anisotropic diffusion filter (BADF) which outperforms the existing anisotropic diffusion filter and is compared with different filters to authenticate the performance. Various performance measures are taken into considerations which are mean square error, structural similarity index, peak signal to noise ratio and signal to noise ratio. The proposed work is tested for 20 images (10 abnormal BRAO from clinical database and 10 normal images). This paper clearly concludes that BADF helps the radiologist in accurate retinal examination and thereby reducing the risk factors. [ABSTRACT FROM AUTHOR]

Medical image detection and classification play an important role in medical research. Tumour detection is a process of crucial importance in oncology. The aim of this paper is to devise an approach for efficient image enhancement, tumour detection, and classification on computed tomographic lung images. Three different application-related methods on computed tomography (CT) images have been designed and implemented in this work. The first method, which was based on image quality, enhances the performance of the medical images. Generally, the CT images are very sensitive to noise and are difficult to handle. Proper care may be taken by introducing some preprocessing algorithms like enhancement algorithms and filters. According to this, an image enhancement algorithm, Wavelet Shrinkage adaptive histogram Equalization (WSAHE), with anisotropic diffusion filter (ADF) was introduced to improve the contrast of the CT images and denoising. In the second method Seed Region growing with Random walk segmentation algorithm (SRGWRWS) is proposed for lung tumour segmentation. In the third method GLCM features, FOS features, structural features, and combinational features are calculated from the segmented lung images. After segmentation, the tumour classification is done by Multi-class support vector machine (MCSVM) and Descend RUSBOOST classifiers. Here, MCSVM classifier was used to find whether the input CT tumour image is suspicious, benign or malignant. Overall accuracy of 92% is obtained using Descend RUSBOOST classifier with GLCM features, FOS features, structural features, combinational features and overall accuracy of 97% is obtained using MCSVM classifier with GLCM feature in MATLAB 2017a software. [ABSTRACT FROM AUTHOR]