Automatic optic disc detection in colour fundus images by means of multispectral analysis and information content
M. Elena Martinez-Perez1,3, Nicholas Witt2, Kim H. Parker2, Alun D. Hughes3,4 and Simon M. A. Thom3
1 Department of Computer Science, Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autónoma de México, 04510 CDMX, México
2 Department of Bioengineering, Imperial College, London, United Kingdom
3 National Heart & Lung Institute, Imperial College, London, United Kingdom
4 Institute of Cardiovascular Sciences, University College London, United Kingdom
Abstract
The optic disc (OD) in retinal fundus images is widely used as a reference in computer-based systems for the measurement of the severity of retinal disease. A number of algorithms have been published in the past 5 years to locate and measure the OD in digital fundus images. Our proposed algorithm, automatically i) uses the three channels (RGB) of the digital colour image to locate the region of interest (ROI) where the OD lies, ii) measures the Shannon information content per channel in the ROI, to decide which channel is most appropriate for searching for the OD centre using the circular Hough transform. A series of evaluations were undertaken to test our hypothesis that using the three channels gives a better performance than a single channel. Three different databases were used for evaluation purposes with a total of 2371 colour images giving a misdetection error of 3% in the localisation of the centre of the OD. We find that the area determined by our algorithm which assumes that the OD is circular, is similar to that found by other algorithms that detected the shape of the OD. Five metrics were measured for comparison with other recent studies. Combining the two databases where expert delineation of the OD is available, (1240 images) the average results for our multispectral (MS) algorithm are: TPR=0.879, FPR=0.003, Accuracy=0.994, Overlap=80.6% and Dice index=0.878.
Keywords
optic disc detection; visual multispectral imaging; information content; retinal images
Paper Status:
Submitted to PeerJ, December 2018.
Source Code:
The code and 10 sample images can be downloaded here [Code and images 48MB]