Diabetic Retinopathy

As a weakly supervised learning technique, neural network (NN) has shown an advantage over supervised learning methods for automatic detection of diabetic retinopathy (DR): only the image-level annotation is needed to achieve both detections of DR images and DR lesions, making more graded and de-identified retinal images available for learning. However, the performance of existing studies on this technique is limited by the use of handcrafted features. We propose a NN method for DR detection, which jointly learns features and classifiers from data and achieves a significant improvement on detecting DR images and their inside lesions. Specifically, a pre-trained neural network is adapted to achieve the patch-level DR estimation, and then global aggregation is used to make the classification of DR images.

Autorentext

Dr. Shafiulla Basha Shaik, Assistenzprofessor, Y.S.R. Engg. College der Yogi Vemana Universität, Proddatur. Y.S.R (Dist), Andhra Pradesh, Indien - 516360, mit über 15 Jahren Lehrerfahrung, hat einen M.Tech in Elektronik und Kommunikationstechnik von der JNTU, Hyderabad, und einen Doktortitel in Biomedizinischer Bildverarbeitung von der Yogi Vemana Universität.