Optic disk is one of the main components on retina. It is an indicator of various ophthalmic pathologies. This paper presents a novel algorithm to segment the optic disk, based on snake model. The proposed method improves and extends original snake technique in two aspects: clustering and smoothing update. The contour first deforms to the location with the minimal energy, and then self-separates into edge-point group or uncertain-point group by means of weighted k-means algorithm. The contour points are finally updated by variable updating sample numbers. These modifications directly solve the blood vessel problem, which has not been effectively solved in the earlier work on disk boundary detection up to now. The comparative results on the 100 testing images shown that the proposed method achieves better success rate (94%) when compared to those obtained by GVF-snake (12%) and modified ASM method (82%)

Bright lesions in the form of exudates and cotton wool spots while dark lesions consisting of hemorrhages are main evidences of background diabetic retinopathy that require early detection and precise classification. Based on different properties of bright lesions and dark lesions, bottom-up and top-down strategies are applied respectively to cope with the main difficulties in lesions detection such as inhomogeneous illumination. In bright lesion detection, a three-stage, bottom-up approach is applied. After local contrast enhancement preprocessing stage, two-step Improved Fuzzy C-Means is applied in Luv color space to segment candidate bright lesion areas. Finally, a hierarchical SVM classification structure is applied to classify bright non-lesion areas, exudates and cotton wool spots. In hemorrhage detection, a top-down strategy is adopted. The hemorrhages are located in the ROI firstly by calculating the evidence value of every pixel using SVM. Then their boundaries can be accurately segmented in the post-processing stage.

Hemorrhages are main evidences of background diabetic retinopathy and early detection is essential for an effective treatment. In this paper, a top-down strategy is applied to detect hemorrhages. After color normalization preprocessing stage, an evidence value for every pixel is calculated by SVM. The SVM classifier uses features extracted by combined 2DPCA instead of explicit image features as the input vector. After locating the hemorrhages in the ROI, the boundaries of the hemorrhages can be accurately segmented by the post-processing stage. The paper demonstrates a new implementation of various techniques on the problem and shows the improvement it offers over the others. Combined 2DPCA is proposed and virtual SVM is applied to achieve the higher accuracy of classification.

In this work, we propose a perceptual model based technique for embedding patient information in a medical image. The distortions in the diagnostic information-content, which will arise due to data embedding, can be controlled using a Perceptual Quality Measure (PQM). A Perceptual Quality Distortion Measure (PQDM) has been defined to measure the visible distortions between the original image and the processed image. The PQDM increases with the increase in the quantity of data embedded into the image. However it has been shown that the PQDM has different values when the same quantity of data is embedded into different regions inside the image, whereas the peak signal to noise ratio (PSNR) is only dependent on the quantity of embedded-data and does not show any change when the same quantity of data is embedded at different regions in the image. Quantification of correlation between PQDM and the loss in diagnostic information in medical images could play the key role for further work in this research area.

Bright lesions, including exudates and cotton wool spots, are the main symptoms in diabetic retinopathy. Early detection and classification of such evidence is essential for an effective treatment. A three-stage approach is applied to detect and classify bright lesions. After a local contrast enhancement preprocessing stage, two-step improved fuzzy C-means is applied in Luv color space to segment candidate bright-lesion areas. The results are shown to be effective in dealing with the inhomogeneous illumination of the fundus images while reducing the influence of noise. Finally, a hierarchical support vector machine (SVM) classification structure is successfully applied to classify bright non-lesion areas, exudates and cotton wool spots.

A new approach to automatically extract the main features in color fundus images is proposed. The optic disk is localized by principal component analysis (PCA) and its shape is detected by a modified active shape model (ASM). Exudates are extracted by the combined region growing and edge detection. A fundus coordinate system is further set up based on fovea localization to provide a better description of the features in fundus images. The success rates achieved are 99%, 94%, and 100% for disk localization, disk boundary detection, and fovea localization respectively. The sensitivity and specificity for exudate detection are 100% and 71%. The success of the proposed algorithms can be attributed to utilization of the model-based methods.

Existing medical image acquisition, storage, retrieval, and diagnosis procedure currently practiced in clinics or hospitals can be further enhanced by incorporating the ever increasingly powerful Internet technologies. In this paper, a concept of online database for remote access to medical image database is presented along with the design methodologies and system implementation based on eye images. The online database supports basic operation of storage and retrieval of eye images through the web and additionally utilizes the Internet platform to provide wider access, more information coverage, and more reliable image data storage and retrieval at lower cost.

An approach to abnormality detection from colour fundus images for an automated mass screening system is proposed in this paper, which uses the object-based colour difference image. Four colour models, viz. RGB, Luv, Lab and HVC, are evaluated based on hand-labelled feature maps, and Luv and Lab are selected for computing the colour difference because of their good performances in object classification. The object-based colour difference images of bright objects (e.g. exudates) and dark objects (e.g. haemorrhages and blood vessels) are obtained respectively according to the 2D histogram distribution on the L-u plane, and then a watershed transform is performed on the colour difference image to extract object candidates. A pre-thresholding and a post-verification procedure are performed to deal with the over-segmentation problem of the watershed transform.

On the research work leading to automatic analysis of retinal fundus images, the knowledge of the optic disk location is essential, and a new method to locate the optic disk automatically is proposed. The candidate regions are first determined by clustering the brightest pixels in the intensity image. Principal component analysis (PCA) is then applied to these candidate regions. The minimum distance between the original retinal image and its projection onto "disk space" is located as the center of the optic disk. The algorithm has been tested and compared with another commonly used method and the results show that the method proposed here can provide more acceptable automatic location of the optic disk.