Then, only cysts are enhanced using CNN and a newly defined function. The construction of Generalized Motion Patterns (GMP) helps to the selective enhancement of cysts. This process is performed by a Convolutional Neural Network (CNN). 8 a cyst segmentation method is proposed working based on the selective enhancement of cysts. The main approaches are artificial intelligence, graph theory, level set and hybrid methods. It is possible to categorize the existing works according to the approaches utilized for the mentioned purpose. Table 1 presents a summary of existing research works for cyst identification and segmentation. Thus, to propose new methods for automatically processing of OCT images is of considerable importance 1, 2, 3, 4. OCT images captured from each patient include a large volume of information the interpretation of which is a time-consuming and difficult process. OCT is a non-invasive technology which can provide important information from retinal layers for ophthalmologists. Optical Coherence Tomography (OCT) is a comparatively new modality designed for imaging from light-scattering organs like retina. Therefore, the identification of the cysts in such images is of significant importance to control the progressive trend of diseases 1, 2. These cysts can have different sizes and shapes which make the process of detection and segmentation difficult. The formation of cysts between or inside retinal layers is from the most important manifestations of such diseases. Age-related Macular Degeneration (AMD) and Diabetic Macular Edema (DME) are from salient retinal diseases which may damage retina and even lead to blindness. In some important retinal diseases, the properties of layers change or some abnormalities are formed between or inside layers. Retina is a layered and light-scattering structure that each layer has its own characteristics. One of the most important organs of body is retina. The evaluation results show the improved performance of HMM in terms of accuracy. The features extracted in the first phase are used as observation vectors to estimate the HMM parameters. It is shown that the feature with the best discriminating power is the feature extracted by AlexNet. In the first phase, a number of features are extracted which are Harris, KAZE, HOG, SURF, FAST, Min-Eigen and feature extracted by deep AlexNet. Since the existence of cyst in an OCT B-scan depends on the existence of cyst in the previous B-scans, HMM is an appropriate tool for modelling this process. In fact, the existence of cyst in the image can be considered as a hidden state. In the proposed method, a Hidden Markov Model (HMM) is used for mathematically modelling the existence of cyst. In this paper, a new method is proposed for the rapid detection of cystic OCT B-scans. Therefore, the identification of cysts in the retinal layers is of great importance. In the salient diseases of retina, cysts are formed in retinal layers. Optical Coherence Tomography (OCT) is a useful imaging modality facilitating the capturing process from retinal layers.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |