| Abstrakt: |
Diabetic retinopathy (DR) is an impediment of diabetes mellitus, which if not treated early may result in complete loss of vision, even without any preemptive symptoms. DR is caused by high level of glucose in the blood, causing alterations in the microvasculature of retina. However, early screening of diabetic patients through retinal fundus imaging, along with proper diagnosis and treatment can control the prevalence of DR complications. Manual inspection of pathological changes in retinal fundus images is an extremely challenging and tedious task. Therefore, computer-aided diagnosis (CAD) system is an efficient and effective method for early detection of DR and can greatly assist the ophthalmologists. CAD system encompasses DR detection and severity grading that includes detection, classification, localization and segmentation of lesions from the fundus images. Significant contributions have been made in DR severity grading using conventional image processing approaches using hand-engineered features and traditional machine-learning (ML) techniques. In the recent years, significant development of deep learning (DL) methods alleviated by the advancement of hardware computation power and efficient learning algorithms, has triumphed over the traditional ML methods in DR detection and grading tasks. Many researchers have employed the established as well as customized DL models in different DR image repositories and reported their findings. In this paper, we conduct a detailed review of the recent state-of-the-art contributions in the field of DL based DR classification by explaining their methodologies and highlighting their advantages and limitations. A detailed comparative study based on certain statistical parameters has also been conducted to quantitatively evaluate the methods, models and preprocessing techniques. In addition, the challenges in designing an efficient, accurate and robust deep-learning model for DR classification are explored in details to help the future research in this field. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink