Diabetic retinopathy through retinal image analysis: A review

Abstract

In this paper, the recent advancement in the Digital Image Processing Aspects in the Diabetic Retinopathy (DR) were been discussed. The major approaches in DR are categorized into four classes namely Preprocessing, Optic Disk Detection, Blood Vessel Extraction and supervised classification. The optic disk, blood vessels and exudates gives more analytical details about the retinal image, segmentation of those features are very important. Further these approaches are classified into finer classes based on the methodologies accomplished in the respective schemes. The details of the database those used for testing the proposed algorithms is also illustrated in this paper. The details of performance metrics such as accuracy, sensitivity, specificity, precision, recall and F-measure are also discussed through their mathematical expressions.

Classification of spinal curvature types using radiography images: deep learning versus classical methods

“…Researchers and physicians have been considering deep neural networks as an automated machine learning system in recent years since they have the advantage of automatic feature extraction, which helps diagnose and classify diseases in medicine (Szegedy et al 2015 , 2016 ). Studies have been reported in the articles (Pratt et al 2016 ; Shuangling Wang et al 2015 ), diagnoses of diabetic retinopathy (DR) or ocular diabetes (Giancardo et al 2012 ; Niemeijer et al 2009 ; Rahim et al 2016 ; Reddy et al 2018 ; Vo and Verma 2016 ), in (Tajbakhsh et al 2015b ; Zhang et al 2016 ) diagnoses polyps during colonoscopy, in (Tajbakhsh et al 2015a ) correctly diagnoses Pulmonary embolism in CT scan images, in (Zheng et al 2015 ) classify lung diseases, in (Rajinikanth et al 2022 ) lung pneumonitis is diagnosed with the InceptionV3 network (Rajinikanth et al 2022 ) demonstrated the lung segmentation performance of the U-Net scheme with a one-fold and two-fold training process. Experimental verification of the proposed scheme is conducted by segmenting the lung section from chest X-rays in (Nagi et al 2022 ).…”