Diabetic retinopathy classification using C4.5

Title: Diabetic retinopathy classification using C4.5
Creator: Park, Mira; Summons, Peter
Relation: Knowledge Management and Acquisition for Intelligent Systems (PKAW 2018). Proceedings of 15th Pacific Rim Knowledge Acquisition Workshop (PKAW 2018) (Nanjing, China 28-29 August, 2018) p. 90-101
Publisher Link: http://dx.doi.org/10.1007/978-3-319-97289-3_7
Publisher: Springer
Resource Type: conference paper
Date: 2018
Description: Early detection of diabetic retinopathy (DR) can prevent blindness and improve the quality of life. Practical detection requires a cost-effective screening over a large population. The presence of Microaneurysms (MAs) in a retinal image is the earliest sign of DR. This paper presents an efficient method to automatically detect MAs in a retinal image. The method is based on an advanced wavelet transform and the C4.5 algorithm (a categorization algorithm to distinguish DR and non-DR cases). It uses both the green and red channel data in RGB retinal images for detection of small sized MAs and obtains image feature parameters from the input image. A system was developed to implement the proposed method that displayed a sensitivity of 0.92 and a precision of 0.82.
Subject: diabetic retinopathy; microaneurysms; c4.5; automatic detection
Identifier: http://hdl.handle.net/1959.13/1445529
Identifier: uon:42603
Identifier: ISBN:9783319972886
Language: eng
Reviewed

		Thumbnail	File	Description	Size	Format