Secondary Observer System for Detection of Microaneurysms in Fundus Images Using Texture Descriptors

Abstract

The increase of diabetic retinopathy patients and diabetic mellitus worldwide yields lot of challenges to ophthalmologists in the screening of diabetic retinopathy. Different signs of diabetic retinopathy were identified in retinal images taken through fundus photography. Among these stages, the early stage of diabetic retinopathy termed as microaneurysms plays a vital role in diabetic retinopathy patients. To assist the ophthalmologists, and to avoid vision loss among diabetic retinopathy patients, a computer-aided diagnosis is essential that can be used as a second opinion while screening diabetic retinopathy. On this vision, a new methodology is proposed to detect the microaneurysms and non-microaneurysms through the stages of image pre-processing, candidate extraction, feature extraction, and classification. The feature extractor, generalized rotational invariant local binary pattern, contributes in extracting the texture-based features of microaneurysms. As a result, our proposed system achieved a free-response receiver operating characteristic score of 0.421 with Retinopathy Online Challenge database.

Keywords: Diabetic retinopathy; Fundus image; Local binary pattern; Microaneurysms; Optic disc.

Fig. 1

Fundus image showing various stages of DR

Fig. 2

Flow diagram of the proposed method in detection of MAs

Fig. 3

Steps in pre-processing (FOV at 45° images are shown in the first row, and ROI portion is given in the second row) a original image, b luminosity correction, c contrast enhancement, d color equalization

Fig. 4

Optic disc removal a detection of OD, b segmentation of OD

Fig. 5

Process in candidate extraction. a Contrast enhancement. b Threshold image

Fig. 6

Circular symmetric set for different P, R

Fig. 7

Histogram distribution pattern of a MAs b Non-MAs

Fig. 8

a Ground truth image. b MA detected image (detected lesions are marked in green circles)

Fig. 9

FROC curves using LBP and GRILBP methods

Fig. 10

ROC curve of MA detection