Jacob Scharcanski

Segmentation of the optic disk in color eye fundus images using an adaptive morphological approach

The identification of some important retinal anatomical regions is a prerequisite for the computer aided diagnosis of several retinal diseases. In this paper, we propose a new adaptive method for the automatic segmentation of the optic disk in digital color fundus images, using mathematical morphology. The proposed method has been designed to be robust under varying illumination and image acquisition conditions, common in eye fundus imaging. Our experimental results based on two publicly available eye fundus image databases are encouraging, and indicate that our approach potentially can achieve a better performance than other known methods proposed in the literature. Using the DRIVE database (which consists of 40 retinal images), our method achieves a success rate of 100% in the correct location of the optic disk, with 41.47% of mean overlap. In the DIARETDB1 database (which consists of 89 retinal images), the optic disk is correctly located in 97.75% of the images, with a mean overlap of 43.65%.

A coarse-to-fine strategy for automatically detecting exudates in color eye fundus images

The detection of exudates is a prerequisite for detecting and grading severe retinal lesions, like the diabetic macular edema. In this work, we present a new method based on mathematical morphology for detecting exudates in color eye fundus images. A preliminary evaluation of the proposed method performance on a known public database, namely DIARETDB1, indicates that it can achieve an average sensitivity of 70.48%, and an average specificity of 98.84%. Comparing to other recent automatic methods available in the literature, our proposed approach potentially can obtain better exudate detection results in terms of sensitivity and specificity.

Automated prescreening of pigmented skin lesions using standard cameras

This paper describes a new method for classifying pigmented skin lesions as benign or malignant. The skin lesion images are acquired with standard cameras, and our method can be used in telemedicine by non-specialists. Each acquired image undergoes a sequence of processing steps, namely: (1) preprocessing, where shading effects are attenuated; (2) segmentation, where a 3-channel image representation is generated and later used to distinguish between lesion and healthy skin areas; (3) feature extraction, where a quantitative representation for the lesion area is generated; and (4) lesion classification, producing an estimate if the lesion is benign or malignant (melanoma). Our method was tested on two publicly available datasets of pigmented skin lesion images. The preliminary experimental results are promising, and suggest that our method can achieve a classification accuracy of 96.71%, which is significantly better than the accuracy of comparable methods available in the literature.

Adaptive image denoising using scale and space consistency

This paper proposes a new method for image denoising with edge preservation, based on image multiresolution decomposition by a redundant wavelet transform. In our approach, edges are implicitly located and preserved in the wavelet domain, whilst image noise is filtered out. At each resolution level, the image edges are estimated by gradient magnitudes (obtained from the wavelet coefficients), which are modeled probabilistically, and a shrinkage function is assembled based on the model obtained. Joint use of space and scale consistency is applied for better preservation of edges. The shrinkage functions are combined to preserve edges that appear simultaneously at several resolutions, and geometric constraints are applied to preserve edges that are not isolated. The proposed technique produces a filtered version of the original image, where homogeneous regions appear separated by well-defined edges. Possible applications include image presegmentation, and image denoising.

Denoising and enhancing digital mammographic images for visual screening

Dense regions in digital mammographic images are usually noisy and have low contrast, and their visual screening is difficult. This paper describes a new method for mammographic image noise suppression and enhancement, which can be effective particularly for screening image dense regions. Initially, the image is preprocessed to improve its local contrast and the discrimination of subtle details. Next, image noise suppression and edge enhancement are performed based on the wavelet transform. At each resolution, coefficients associated with noise are modelled by Gaussian random variables; coefficients associated with edges are modelled by Generalized Laplacian random variables, and a shrinkage function is assembled based on posterior probabilities. The shrinkage functions at consecutive scales are combined, and then applied to the wavelets coefficients. Given a resolution of analysis, the image denoising process is adaptive (i.e. does not require further parameter adjustments), and the selection of a gain factor provides the desired detail enhancement. The enhancement function was designed to avoid introducing artifacts in the enhancement process, which is essential in mammographic image analysis. Our preliminary results indicate that our method allows to enhance local contrast, and detect microcalcifications and other suspicious structures in situations where their detection would be difficult otherwise. Compared to other approaches, our method requires less parameter adjustments by the user.

Robust watershed segmentation using wavelets

The use of watersheds in image segmentation relies mostly on a good estimation of image gradients. However, background noise tends to produce spurious gradients, causing over-segmentation and degrading the result of the watershed transform. Also, low-contrast edges generate small magnitude gradients, causing distinct regions to be erroneously merged. In this paper, a new technique is presented to improve the robustness of the segmentation using watersheds, which attenuates the over-segmentation problem. A redundant wavelet transform is used to de-noise the image, enhance edges in multiple resolutions, and obtain an enhanced version of image gradients. Then, the watershed transform is applied to the obtained gradient image, and the segmented regions that do not satisfy specific criteria are removed or merged. Applications of our segmentation approach to noisy and/or blurred images are discussed, emphasizing a case study in fingerprint segmentation.

Automatic Skin Lesion Segmentation via Iterative Stochastic Region Merging

An automatic method for segmenting skin lesions in conventional macroscopic images is presented. The images are acquired with conventional cameras, without the use of a dermoscope. Automatic segmentation of skin lesions from macroscopic images is a very challenging problem due to factors such as illumination variations, irregular structural and color variations, the presence of hair, as well as the occurrence of multiple unhealthy skin regions. To address these factors, a novel iterative stochastic region-merging approach is employed to segment the regions corresponding to skin lesions from the macroscopic images, where stochastic region merging is initialized first on a pixel level, and subsequently on a region level until convergence. A region merging likelihood function based on the regional statistics is introduced to determine the merger of regions in a stochastic manner. Experimental results show that the proposed system achieves overall segmentation error of under 10% for skin lesions in macroscopic images, which is lower than that achieved by existing methods.

Fovea center detection based on the retina anatomy and mathematical morphology

In this work, we present a new fovea center detection method for color eye fundus images. This method is based on known anatomical constraints on the relative locations of retina structures, and mathematical morphology. The detection of this anatomical feature is a prerequisite for the computer aided diagnosis of several retinal diseases, such as Diabetic Macular Edema. The proposed method is adaptive to local illumination changes, and it is robust to local disturbances introduced by pathologies in digital color eye fundus images (e.g. exudates). Our experimental results using the DRIVE image database indicate that our method is able to detect the fovea center in 37 out of 37 images (i.e. with a success rate of 100%). Using the DIARETDB1 database, our method was able to detect the fovea center in 92.13% of all tested cases (i.e. in 82 out of 89 images). These results indicate that our approach potentially can achieve a better performance than comparable methods proposed in the literature.

A morphologic two-stage approach for automated optic disk detection in color eye fundus images

A new adaptive morphological method for the automatic detection of the optic disk in digital color eye fundus images is presented in this paper. This method has been designed to detect the optic disk center and the optic disk rim. In our experiments with the DRIVE and DIARETDB1 databases, the proposed method was able to detect the optic disk center with 100% and 97.75% of accuracy, respectively. We considered correct all automatically detected optic disk location that is within the borders of the optic disk marked manually. Using our proposed method, the rim of the optic disk was detected in all images of the DRIVE database with average sensitivity and specificity of 83.54% and 99.81%, respectively, and on the DIARETDB1 database with average sensitivity and specificity of 92.51% and 99.76%, respectively.

Shading attenuation in human skin color images

This paper presents a new automatic method to significantly attenuate the color degradation due to shading in color images of the human skin. Shading is caused by illumination variation across the scene due to changes in local surface orientation, lighting conditions, and other factors. Our approach is to estimate the illumination variation by modeling it with a quadric function, and then relight the skin pixels with a simple operation. Therefore, the subsequent color skin image processing and analysis is simplified in several applications. We illustrate our approach in two typical color imaging problems involving human skin, namely: (a) pigmented skin lesion segmentation, and (b) face detection. Our preliminary experimental results show that our shading attenuation approach helps reducing the complexity of the color image analysis problem in these applications.