Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images

Abstract

Aim: To recognise automatically the main components of the fundus on digital colour images.

Methods: The main features of a fundus retinal image were defined as the optic disc, fovea, and blood vessels. Methods are described for their automatic recognition and location. 112 retinal images were preprocessed via adaptive, local, contrast enhancement. The optic discs were located by identifying the area with the highest variation in intensity of adjacent pixels. Blood vessels were identified by means of a multilayer perceptron neural net, for which the inputs were derived from a principal component analysis (PCA) of the image and edge detection of the first component of PCA. The foveas were identified using matching correlation together with characteristics typical of a fovea-for example, darkest area in the neighbourhood of the optic disc. The main components of the image were identified by an experienced ophthalmologist for comparison with computerised methods.

Results: The sensitivity and specificity of the recognition of each retinal main component was as follows: 99.1% and 99.1% for the optic disc; 83.3% and 91.0% for blood vessels; 80.4% and 99.1% for the fovea.

Conclusions: In this study the optic disc, blood vessels, and fovea were accurately detected. The identification of the normal components of the retinal image will aid the future detection of diseases in these regions. In diabetic retinopathy, for example, an image could be analysed for retinopathy with reference to sight threatening complications such as disc neovascularisation, vascular changes, or foveal exudation.

Figure 1

Digital colour retinal image.

Figure 2

Retinal image after preprocessing by local colour contrast enhancement.

Figure 3

The variance image of Figure 2.

Figure 4

An example of the data input to the net, of size 2 × 10 × 10 pixels. In this example, the pattern was classified as vessel.

Figure 5

Classification of the image Figure 2 into vessels/non-vessels.

Figure 6

The classified image after post-processing to remove small regions.

Figure 7

The results of automatic recognition of the main components of the fundus from a digital fundus colour image.

Figure 8

A sample of images showing the results of the recognition of the main components from digital fundus colour images.

Figure 9

Example of patch of size 20 × 20 pixels used to measure the accuracy of vessels recognition.