Claude Tameze

Empirical Analysis of Libs Images for Ovarian Cancer Detection

To develop a way to detect early epithelial ovarian cancer we expose blood samples to a laser. Using Laser induced breakdown spectroscopy, (LIBS) plasma images of the blood samples are generated and analyzed. In this paper we compare the images from blood specimens of cancer free mice to those of transgenic mice; that is, mice that are currently developing epithelial ovarian cancer and are approximately the same age as the disease free mice. Our ultimate goal is to look for changes in the shape and edges of the image that might indicate the presence of cancer. To analyze the images we use a nonlinear diffusion filter for enhancement of relevant image edges and removal of noise and irrelevant texture.

Aircraft identification by unions of ISAR images

We offer an algorithm that can identify aircraft categories from Inverse Synthetic Aperture Radar (ISAR) images that use both the radar reflection pulse shape, which includes the duration or size of the radar pulse that is reflected, and the Doppler shifts of different parts of the aircraft caused by rotational motions of the aircraft as it maneuvers. We investigated the practicality of determining which of seven different aircraft categories a radar return indicates. The object of this research is to very quickly tell from an ISAR return how an aircraft compares to the seven different categories where the aircraft is in any position of a prescribed holding pattern. We propose a new method in which we compare each ISAR image to unions of images of the different aircraft categories. This method gave us results that are superior to the results we obtained in [8].

Algorithmic Quantification of Skull Bone Density

It is estimated that over 200 million people worldwide experience a decrease in bone strength associated with osteoporosis. This causes increased susceptibility to fracture which represents one of the critical challenges of aging population. Therefore, novel approaches in assessing overall bone integrity are introduced. These approaches included the use of micro CT scan of skull bone images of mouse which allow to study a new mouse model with gap junction protein mutation, and compare normal and diseased animals. We propose skull bone detection algorithm capable of successfully detecting skull bone density. The proposed method has two functions: visual and numerical. Visual function is expressed through detection and indication of the potential bone tissue by marking it in a different color and distinguishing it from the background. Numerical function enables quantification of the amount of detected skull bone by calculating its numerical content equivalent.

Noise resistant algorithm for radar images recognition and classification

We propose a novel algorithm for automatic aircraft classification. The proposed method makes numerical equivalents to shape, size and other aircraft features as critical criteria to constitute the algorithm for their correct classification. This method uses Inverse Synthetic Aperture Radar (ISAR) aircraft images that are making maneuvers that introduce aircraft rotation relative to the radar station. By means of analyzing the shape of the radar pulse and Doppler shifts that are caused by rotation of the aircraft, an image of the aircraft shape can be constructed. We computer simulated five different categories of ISAR images. We tested the proposed classification algorithm on these five categories and on two more categories taken from the Internet. One aircraft model is simulated and the other one is a real sequence with much added noise. All seven different aircraft models are flying a holding pattern. We investigated where in the holding patterns ISAR reflections made it possible to identify each category of aircraft. Our experimental results demonstrate that in most parts of the holding pattern the category of the aircraft can be successfully identified. The performed tests show that the proposed algorithm appears to be noise resistant.

Combined nonlinear inverse diffusion filter and triangle method used for noise removal from polygonal shapes

A two step procedure for removing noise from polygonal shapes is presented here. The first step is the removal of vertices by linear and different nonlinear inverse diffusion filters. In the second step we apply the triangle method which identifies least dominant vertices from the polygon obtained from the first stage. Those vertices whose adjacent sides form triangles of the smallest area are defined as least dominant and most likely to be noise. A thorough testing of this method on the shapes typical in video images demonstrates that it successfully removes noise vertices while it preserves dominant ones.

Noise removal from polygonal shapes using combined inverse diffusion filter and triangle method

We introduce a method for de-noising, segmenting and measuring similarity of shapes. The proposed method consists of two techniques. First we use an inverse diffusion filter for enhancement of relevant polygonal vertices and removal of noise and irrelevant edges. Second we apply a technique that removes the vertices that form the triangles with the smallest areas. In a thorough experimental evaluation, the combined method shows successful noise suppression while preserving dominant vertices present in the input shape.

Empirical Analysis of Blood Plasma LIBS Images Using the Nonlinear Diffusion Method

In an attempt to develop a method of early epithelial ovarian cancer detection we apply a laser to blood samples. With laser induced breakdown spectroscopy, (LIBS), plasma state images of blood samples are prepared and analyzed. We apply an improved nonlinear diffusion filter in order to enhance relevant image edges and to remove noise and irrelevant texture. We hope to identify differences in the shapes of these images by which we can detect the earliest stages of ovarian cancer.

Programmed Neuron Cells' Morphology Multiphase Assessment

Alzheimers represents progressively increasing healthcare problems especially in aging population affecting memory, overall thinking process and general behavior. Symptoms usually develop slowly and get worse over time. Alzheimers disease accounts for 60 to 80 percent of dementia cases. It is caused by abnormal deposits of proteins that form amyloid plaques and tau tangles throughout the brain, and once- healthy neurons stop functioning, lose connections with other neurons, and die. They manifest neurodegeneration. Therefore, we propose neuron morphology algorithm that automatically routinely distinguishes healthy from degenerated neurons. This algorithm derives numerical indicators that represent abnormalities in neuron morphology examination.

EXUDATES DETECTION AND CLASSIFICATION ALGORITHM OF DIABETIC PATIENTS' RETINA IMAGES

The chronic hyperglycemia of diabetes is associated with long-term damage, dysfunction, and failure of different organs, especially the eyes, kidneys, nerves, heart and blood vessels. The regular examination of diabetic patients can potentially reduce the risk of vision impairment and in the last instance blindness. Early diabetic retinopathy detection enables application of laser therapy treatment in order to prevent or delay loss of vision. The diagnostics and detection of diabetic retinopathy is performed by specialized ophthalmologists manually and represents expensive procedure. Automatic exudates detection and retina images classification would be helpful for reducing diabetic retinopathy screening costs and encouraging regular examinations. We proposed the automated algorithm that applies mathematical modeling which enables light intensity levels emphasis, easier exudates detection, efficient and correct classification of retina images. The proposed algorithm is robust to various appearance changes of retinal fundus images which are usually processed in clinical environments.

Empirical analysis of LIBS images using the nonlinear diffusion method

We are investigating the use of the laser induced breakdown spectroscopy, (LIBS), on blood samples of mice to detect the earliest stages of epithelial ovarian cancer (EOC). A laser changes a blood samples to plasma state and the images produced thereby are analyzed. By comparing LIBS images of blood from EOC positive mice to those of cancer free mice, our goal is to identify differences by which we can detect those in early EOC stages. We apply an improved nonlinear diffusion filter to enhance relevant image edges and to remove noise and irrelevant texture.