Scale-space curvature detection of retinal exudates with a dynamic threshold (original) (raw)

Curvature detection and segmentation of retinal exudates

2012

In this paper, a segmentation method of the retinal images exudates is proposed. First, pixels that belong to exudates are located using the scale-space extrinsic curvature. These candidate points, are used together with the mean curvature to select possible exudates patches. True exudates are selected using the local maxima blob response through dynamical threshold, which will represent the final segmentation. The proposed scheme is tested with a retinal images public database. The ROC curve is used to validate the final performance, which shows a normalized area under the curve of 96.39%, with a confidence level of 0.8. In that case the sensitivity is 97.07%, the specificity is 99.90% and the accuracy is 99.83%. A final comparison with recent methods is also presented.

Automatic Detection of Exudates in Retinal Fundus Images using Differential Morphological Profile

2013

This paper presents an automatic method for exudate detection from colour fundus images based on Differential Morphological Profile (DMP).The detection of exudates is important for the identification of eye diseases such as diabetic retinopathy. The method involves of three main phases. In the first phase, pre processing tasks like Gaussian smoothing and contrast enhancement is done. In the second phase, DMP is applied on the pre-processed image. The image obtained from DMP contains highlighted bright regions consisting of exudates and optic disc. In the next phase, feature extraction based on location of optic disc, shape index and area is done to obtain actual exudates. The performance of the proposed method is evaluated by applying it on the DIARETDB1 database. The specificity, sensitivity and PPV of the proposed method were compared with two other methods. The results show that the proposed method gives better results than the other conventional methods. Keyword- DMP, Exudates, ...

Exudate Identification in Retinal Fundus Images Using Precise Textural Verifications

One of the most salient diseases of retina is Diabetic Retinopathy which may lead to irreparable damages to eye vision in the advanced phases. Hard Exudates (HE) are bright lesions appeared in retinal fundus images of DR patients. Thus, the detection of HEs is an important task preventing the progress of DR. However, the detection of HEs is a challenging process due to their different appearance features. In this paper, an automatic method for the identification of HEs with various sizes and shapes is proposed. The method works based on a pixel-wise approach. It considers several semi-circular regions around each pixel. For each semi-circular region, the intensity changes around several directions and non-necessarily equal radiuses are computed. All pixels for which several semi-circular regions include considerable intensity changes are considered as the pixels located in HEs. In order to reduce false positives, an optic disc localization method is proposed in the post-processing p...