Dimitris Maroulis

Computer-aided tumor detection in endoscopic video using color wavelet features

We present an approach to the detection of tumors in colonoscopic video. It is based on a new color feature extraction scheme to represent the different regions in the frame sequence. This scheme is built on the wavelet decomposition. The features named as color wavelet covariance (CWC) are based on the covariances of second-order textural measures and an optimum subset of them is proposed after the application of a selection algorithm. The proposed approach is supported by a linear discriminant analysis (LDA) procedure for the characterization of the image regions along the video frames. The whole methodology has been applied on real data sets of color colonoscopic videos. The performance in the detection of abnormal colonic regions corresponding to adenomatous polyps has been estimated high, reaching 97% specificity and 90% sensitivity.

Fuzzy Local Binary Patterns for Ultrasound Texture Characterization

B-scan ultrasound provides a non-invasive low-cost imaging solution to primary care diagnostics. The inherent speckle noise in the images produced by this technique introduces uncertainty in the representation of their textural characteristics. To cope with the uncertainty, we propose a novel fuzzy feature extraction method to encode local texture. The proposed method extends the Local Binary Pattern (LBP) approach by incorporating fuzzy logic in the representation of local patterns of texture in ultrasound images. Fuzzification allows a Fuzzy Local Binary Pattern (FLBP) to contribute to more than a single bin in the distribution of the LBP values used as a feature vector. The proposed FLBP approach was experimentally evaluated for supervised classification of nodular and normal samples from thyroid ultrasound images. The results validate its effectiveness over LBP and other common feature extraction methods.

A shock associated (SA) radio event and related phenomena observed from the base of the solar corona to 1 AU

We present for the rst time an almost com- plete frequency coverage of a Shock Associated (SA) radio event and related phenomena observed on May 6, 1996 at 9:27 UT. It is observed from the base of the solar corona up to almost 1 Astronomical Unit (AU) from the Sun by the following radio astronomical instruments: the Ond rejov spectrometer operating between 4.5 GHz and 1 GHz (radi- ation produced near the chromosphere); the Thermopyles Artemis-IV spectrograph operating between 600 MHz and 110 MHz (distance range about 1.1-1.4R from sun center); the Nan cay Decameter Array operating between 75 and 25 MHz (distance range about 1.4-2 R); and the RAD2 and RAD1 radio receivers on the WIND spacecraft covering the range from 14 MHz to about 20 kHz (distance range be- tween 3 R and about 1 AU). Observations at the Nan cay Decameter Array clearly show that the SA event starts from a coronal type II radio burst which traces the progression of a shock wave through the corona above 1.8 R-2 R from the sun center. This SA event has no associated radio emis- sion in the decimetric-metric range, thus there is no evidence for electron injection in the low/middle corona. The SA event enigma: What does SA stand for? Type II and type III solar radio bursts result from the interaction of a disturbing agent {a beam of energetic elec- trons or a shock wave{ with the ambient plasma (Wild and Smerd, 1972). Radiation is produced near the fundamen- tal of the local plasma frequency f p (kHz) =9 n 1 = 2 e (cm 3 ) and/or its second harmonic through various plasma mech- anisms (see e.g. Robinson, 1997). The observed frequency can be converted into an altitude in the corona, assuming a density model and the radiated mode. Dierent frequency drifts reflect dierent velocities along the density gradient in the corona and interplanetary medium, helping us to charac- terize the nature of the exciter: 0.05-0.3c electron beam for

An Original Genetic Approach to the Fully Automatic Gridding of Microarray Images

Gridding microarray images remains, at present, a major bottleneck. It requires human intervention which causes variations of the gene expression results. In this paper, an original and fully automatic approach for accurately locating a distorted grid structure in a microarray image is presented. The gridding process is expressed as an optimization problem which is solved by using a genetic algorithm (GA). The GA determines the line-segments constituting the grid structure. The proposed method has been compared with existing software tools as well as with a recently published technique. For this purpose, several real and artificial microarray images containing more than one million spots have been used. The outcome has shown that the accuracy of the proposed method achieves the high value of 94% and it outperforms the existing approaches. It is also noise-resistant and yields excellent results even under adverse conditions such as arbitrary grid rotations, and the appearance of various spot sizes.

LBP-guided active contours

This paper investigates novel LBP-guided active contour approaches to texture segmentation. The local binary pattern (LBP) operator is well suited for texture representation, combining efficiency and effectiveness for a variety of applications. In this light, two LBP-guided active contours have been formulated, namely the scalar-LBP active contour (s-LAC) and the vector-LBP active contour (v-LAC). These active contours combine the advantages of both the LBP texture representation and the vector-valued active contour without edges model, and result in high quality texture segmentation. s-LAC avoids the iterative calculation of active contour equation terms derived from textural feature vectors and enables efficient, high quality texture segmentation. v-LAC evolves utilizing regional information encoded by means of LBP feature vectors. It involves more complex computations than s-LAC but it can achieve higher segmentation quality. The computational cost involved in the application of v-LAC can be reduced if it is preceded by the application of s-LAC. The experimental evaluation of the proposed approaches demonstrates their segmentation performance on a variety of standard images of natural textures and scenes.

M3G: Maximum Margin Microarray Gridding

BackgroundComplementary DNA (cDNA) microarrays are a well established technology for studying gene expression. A microarray image is obtained by laser scanning a hybridized cDNA microarray, which consists of thousands of spots representing chains of cDNA sequences, arranged in a two-dimensional array. The separation of the spots into distinct cells is widely known as microarray image gridding.MethodsIn this paper we propose M3G, a novel method for automatic gridding of cDNA microarray images based on the maximization of the margin between the rows and the columns of the spots. Initially the microarray image rotation is estimated and then a pre-processing algorithm is applied for a rough spot detection. In order to diminish the effect of artefacts, only a subset of the detected spots is selected by matching the distribution of the spot sizes to the normal distribution. Then, a set of grid lines is placed on the image in order to separate each pair of consecutive rows and columns of the selected spots. The optimal positioning of the lines is determined by maximizing the margin between these rows and columns by using a maximum margin linear classifier, effectively facilitating the localization of the spots.ResultsThe experimental evaluation was based on a reference set of microarray images containing more than two million spots in total. The results show that M3G outperforms state of the art methods, demonstrating robustness in the presence of noise and artefacts. More than 98% of the spots reside completely inside their respective grid cells, whereas the mean distance between the spot center and the grid cell center is 1.2 pixels.ConclusionsThe proposed method performs highly accurate gridding in the presence of noise and artefacts, while taking into account the input image rotation. Thus, it provides the potential of achieving perfect gridding for the vast majority of the spots.

Unsupervised 2D gel electrophoresis image segmentation based on active contours

This work introduces a novel active contour-based scheme for unsupervised segmentation of protein spots in two-dimensional gel electrophoresis (2D-GE) images. The proposed segmentation scheme is the first to exploit the attractive properties of the active contour formulation in order to cope with crucial issues in 2D-GE image analysis, including the presence of noise, streaks, multiplets and faint spots. In addition, it is unsupervised, providing an alternate to the laborious, error-prone process of manual editing, which is required in state-of-the-art 2D-GE image analysis software packages. It is based on the formation of a spot-targeted level-set surface, as well as of morphologically-derived active contour energy terms, used to guide active contour initialization and evolution, respectively. The experimental results on real and synthetic 2D-GE images demonstrate that the proposed scheme results in more plausible spot boundaries and outperforms all commercial software packages in terms of segmentation quality.

TND: A Thyroid Nodule Detection System for Analysis of Ultrasound Images and Videos

In this paper, we present a computer-aided-diagnosis (CAD) system prototype, named TND (Thyroid Nodule Detector), for the detection of nodular tissue in ultrasound (US) thyroid images and videos acquired during thyroid US examinations. The proposed system incorporates an original methodology that involves a novel algorithm for automatic definition of the boundaries of the thyroid gland, and a novel approach for the extraction of noise resilient image features effectively representing the textural and the echogenic properties of the thyroid tissue. Through extensive experimental evaluation on real thyroid US data, its accuracy in thyroid nodule detection has been estimated to exceed 95%. These results attest to the feasibility of the clinical application of TND, for the provision of a second more objective opinion to the radiologists by exploiting image evidences.

Unsupervised SVM-based gridding for DNA microarray images

This paper presents a novel method for unsupervised DNA microarray gridding based on support vector machines (SVMs). Each spot is a small region on the microarray surface where chains of known DNA sequences are attached. The goal of microarray gridding is the separation of the spots into distinct cells. The positions of the spots on a DNA microarray image are first detected using image analysis operations and then a set of soft-margin linear SVM classifiers is used to estimate the optimal layout of the grid lines in the image. Each grid line is the separating line produced by one of the SVM classifiers, which maximizes the margin between two consecutive rows or columns of spots. The classifiers are trained using the spot locations as training vectors. The proposed method was evaluated on reference microarray images containing more than two million spots in total. The results illustrate its robustness in the presence of artifacts, noise and weakly expressed spots, as well as image rotation. The comparison to state of the art methods for microarray gridding reveals the superior performance of the proposed method. In 96.4% of the cases, the spots reside completely inside their respective grid cells.

Tumor recognition in endoscopic video images using artificial neural network architectures

The paper focuses on a scheme for automated tumor recognition using images acquired during endoscopic sessions. The proposed recognition system is based on multilayer feed forward neural networks (MFNNs) and uses texture information encoded with corresponding statistical measures that are fed as input to the MFNN. Experiments were performed for recognition of different types of tumors in various images and also a number of sequentially acquired frames. The recognition of a polypoid tumor of the colon in the original image, which were used for training was very high. The trained network was also able to satisfactorily recognize the tumor in a sequence of video frames. The results of the proposed approach were very promising and it seems that it can be efficiently applied for tumor recognition.