Mouloud Adel

Detection of the foveal avascular zone on retinal angiograms using Markov random fields

This paper deals with the segmentation of the Foveal Avascular Zone (FAZ) in digital retinal angiograms. Retinal angiography is used for detection and progression in some eye pathologies. The proposed method consists of two-stages: Singular Value Decomposition (SVD) and FAZ segmentation using Markov Random Fields (MRF). The obtained results demonstrate that the method is encouraging as a first approach for location and evolution of FAZ in retinal images.

Semi-automated detection of the foveal avascular zone in fluorescein angiograms in diabetes mellitus.

Background:u2002 The foveal avascular zone (FAZ) is known to enlarge in diabetic retinopathy. In a preliminary study, the authors applied a region growing algorithm to fluorescein angiograms to detect the FAZ in a semi‐automated fashion.

Mathematical morphology in computerized analysis of angiograms in age-related macular degeneration.

This paper deals with image processing of numerical retinal angiograms in order to facilitate diagnosis and follow-up in age-related macular degeneration (AMD) which is currently the main cause of blindness in industrialized countries. A computerized scheme using principally mathematical morphology operators is proposed for detecting and counting drusen, which are precursor lesions of the ocular fundus. In order to check the feasibility of this approach, results relative to 58 retinal images are compared with those given by three retinal specialists independently. From manual counting measures it is found that interobserver correlation coefficients lie in the range 0.71-0.78. On the other hand, a correlation coefficient of 0.89 is obtained when the average of the three expert countings is compared with the drusen number given by the computerized method. This coefficient is improved from 0.89 to 0.93 by processing only frames captured immediately after the appearance of a dye consecutive to intravenous sodium fluorescein injection. Compared to the manual analysis which is, among other things, tedious and time consuming, the computerized analysis is both quicker and more objective. Validation by the practitioner is however necessary, given possible detection errors. The proposed computerized scheme for detecting and counting drusen may be easily automated and so should prove useful in clinical studies which involve high volume analysis of retinal angiograms.

Statistical segmentation of regions of interest on a mammographic image

This paper deals with segmentation of breast anatomical regions, pectoral muscle, fatty and fibroglandular regions, using a Bayesian approach. This work is a part of a computer aided diagnosis project aiming at evaluating breast cancer risk and its association with characteristics (density, texture, etc.) of regions of interest on digitized mammograms. Novelty in this paper consists in applying and adapting Markov random field for detecting breast anatomical regions on digitized mammograms whereas most of previous works were focused on masses and microcalcifications. The developed method was tested on 50 digitized mammograms of the mini-MIAS database. Computer segmentation is compared to manual one made by a radiologist. A good agreement is obtained on 68% of the mini-MIAS mammographic image database used in this study. Given obtained segmentation results, the proposed method could be considered as a satisfying first approach for segmenting regions of interest in a breast.

Filtering noise on mammographic phantom images using local contrast modification functions

This paper deals with filtering signal-dependent noise on digitized mammographic phantom images using a direct contrast modification method. First, a local contrast is computed for each pixel depending on the statistical properties of its neighbourhood. An optimal modification contrast function is then applied. This function is found by solving an optimisation problem using the mean squared error as a criterion. At last the enhanced pixel value is calculated using an inverse local contrast method. Simulated images containing objects similar to those observed in the phantom are built with different contrast and Signal to Noise Ratio (SNR) levels. Noise reduction results obtained are then compared to those of classical noise filtering methods. This comparison shows that the developed method gives better results. Evaluation was also done on real phantom images with the help of radiologists. Good results obtained lead us to consider the developed method as a good preprocessing step for quality control in mammographic facilities using image processing techniques.

Statistical-based linear vessel structure detection in medical images

Linear structures such as blood vessels in medical images are important features for computer-aided diagnosis and follow-up of many diseases. In this letter a new tracking-based segmentation method is proposed to detect blood vessels in retinal angiorams. Bayesian segmentation with the Maximum a posteriori (MAP) Probability criterion is used for that purpose. First promising results are presented and discussed.

Region-based brain selection and classification on pet images for Alzheimer's disease computer aided diagnosis

Positron Emission Tomography (PET) is a 3-D functional imaging modality which help physicians to diagnose neurodegenerative diseases like Alzheimers Disease (AD). Computer-aided detection and diagnosis, based on medical imaging techniques is of importance for a quantitative evaluation. A novel method of ranking the effectiveness of brain regions to separate AD from healthy brains images is presented. Brain images are first mapped into 116 anatomical regions of interest. The first four moments and the entropy of the histograms of these regions are computed. Receiver Operating Characteristics curves are then used to rank the ability of regions to separate PET brain images. Twenty one selected regions are input to both Support Vector Machine and Random Forest classifiers and evaluation is done on 142 brain PET images. Classification results are better than those obtained when using the whole 116 initial regions or when inputting the whole brain voxels. In addition, an important computational time reduction was obtained.

Spatial and spectral dependance co-occurrence method for multi-spectral image texture classification

This paper deals with the development of a new texture analysis method based on both spatial and spectral information for texture classification purposes. The idea of the Spatial and Spectral Gray Level Dependence Method (SSGLDM) is to extend the concept of spatial gray level dependence method by assuming texture joint information between spectral bands. In addition, new texture features measurement related to (SSGLDM) which define the image properties have been also proposed. Extensive experiments have been carried out on many multi-spectral images for use in prostate cancer diagnosis and quantitative results showed the efficiency of this method compared to the Gray Level Co-occurrence Matrix (GLCM). The results indicate a significant improvement in classification accuracy.

Array Processing Approach for Object Segmentation in Images

Thanks to a specific formalism for signal generation, it is possible to transpose an image processing problem to an array processing problem. For straight line characterization, the existing method subspace-based line detection (SLIDE) works on virtual signals generated on a linear antenna. In this paper we propose to retrieve circular and nearly circular contours in images. We propose a novel method for radius estimation, and we extend the estimation of circles to the retrieval of circular-like distorted contours. For this purpose we develop a new model for virtual signal generation: we simulate a circular antenna, so that a high resolution method can be employed for radius estimation. An application to biomedical imaging is proposed.