A Novel Adaptive Deformable Model for Automated Optic Disc and Cup Segmentation to Aid Glaucoma Diagnosis

Abstract

This paper proposes a novel Adaptive Region-based Edge Smoothing Model (ARESM) for automatic boundary detection of optic disc and cup to aid automatic glaucoma diagnosis. The novelty of our approach consists of two aspects: 1) automatic detection of initial optimum object boundary based on a Region Classification Model (RCM) in a pixel-level multidimensional feature space; 2) an Adaptive Edge Smoothing Update model (AESU) of contour points (e.g. misclassified or irregular points) based on iterative force field calculations with contours obtained from the RCM by minimising energy function (an approach that does not require predefined geometric templates to guide auto-segmentation). Such an approach provides robustness in capturing a range of variations and shapes. We have conducted a comprehensive comparison between our approach and the state-of-the-art existing deformable models and validated it with publicly available datasets. The experimental evaluation shows that the proposed approach significantly outperforms existing methods. The generality of the proposed approach will enable segmentation and detection of other object boundaries and provide added value in the field of medical image processing and analysis.

Keywords: Computer-aided retinal disease diagnosis; Glaucoma; Machine learning; Medical image processing and analysis.

Fig. 1

Comparison of CDR in a normal image and b glaucoma image. The glaucoma image has higher CDR

Fig. 2

Different meridians of Cup to Disk Ratio (CDR) measurement

Fig. 3

Block diagram of adaptive region-based edge smoothing model

Fig. 4

Contour profile sampling steps to determine the disc boundary in this challenging optic nerve photo due to extensive PPA with a Mean shape initialisation, b Sampling the search line (red) normal to the contour point. Each sample on the search line has its subline samples. c Determination of optimal sample on the search line

Fig. 5

An example of optic disc segmentation by our proposed algorithm with a example image from a disc with extensive cupping and peripapillary atrophy , b output after optic disc region search by the RCM and c output after optic disc shape edge update

Fig. 6

The procedure of adaptive edge smoothing update with a optimum contour from the RCM, b best feature map for determination of optic disc edge, c Edge map after convolving b with DoG filter, d force field of (c), e contour update towards maximum force and f final disc contour

Fig. 7

The overview of optic disc segmentation based on the proposed approach

Fig. 8

Determination of distance map (b) after optic disc segmentation as mentioned (a). The distance map shows higher pixel values near the centre indicating the higher chances of the pixel to be the part of optic cup

Fig. 9

The overview of optic cup segmentation based on the proposed approach

Fig. 10

Comparison of the individual classification performance with and without vasculature removal for optic disc and optic cup. The result shows that the vasculature removal has higher individual classification performance

Fig. 11

Results of feature selection procedures for optic disc (OD) and optic cup (OC)

Fig. 12

Classification zones for a optic disc and b optic cup. The classification of optic disc has been performed between inside and outside of optic disc whereas classification for optic cup has been performed between inside of optic cup and optic disc rim

Fig. 13

Examples of Optic Disc Segmentation Results with a Original Image b Clinical Annotations, c ARESM (our proposed approach), d ASM, e ACM and f Chan-Vese (C-V). The Dice Coefficient of each method compared to ground truth has been shown above each visual result

Fig. 14

Examples of Optic Cup Segmentation Results with a Original Image b Clinical Annotations, c ARESM (our proposed approach), d ASM, e ACM and f Chan-Vese (C-V). The Dice Coefficient of each method compared to ground truth has been shown above each visual result

Fig. 15

Comparison of classification performance between the clinical manual CDR and the automatic CDRs with the first row a, b and c represents the results on set 1 (N vs G) and second row represents the results on set 2 (N vs (G + S)). The first column ((a) and (d)) represent the results calculated on vertical CDR whereas the second and third column represent the results on horizontal CDR and the area CDR respectively