Lena Costaridou

Atlas-Based Segmentation of Degenerated Lumbar Intervertebral Discs From MR Images of the Spine

Intervertebral disc degeneration is an age-associated condition related to chronic back pain, while its consequences are responsible for over 90% of spine surgical procedures. In clinical practice, MRI is the modality of reference for diagnosing disc degeneration. In this study, we worked toward 2-D semiautomatic segmentation of both normal and degenerated lumbar intervertebral discs from T2-weighted midsagittal MR images of the spine. This task is challenged by partial volume effects and overlapping gray-level values between neighboring tissue classes. To overcome these problems three variations of atlas-based segmentation using a probabilistic atlas of the intervertebral disc were developed and their accuracies were quantitatively evaluated against manually segmented data. The best overall performance, when considering the tradeoff between segmentation accuracy and time efficiency, was accomplished by the atlas-robust-fuzzy c-means approach, which combines prior anatomical knowledge by means of a rigidly registered probabilistic disc atlas with fuzzy clustering techniques incorporating smoothness constraints. The dice similarity indexes of this method were 91.6% for normal and 87.2% for degenerated discs. Research in progress utilizes the proposed approach as part of a computer-aided diagnosis system for quantification and characterization of disc degeneration severity. Moreover, this approach could be exploited in computer-assisted spine surgery.

Improvement of microcalcification cluster detection in mammography utilizing image enhancement techniques

In this work, the effect of an image enhancement processing stage and the parameter tuning of a computer-aided detection (CAD) system for the detection of microcalcifications in mammograms is assessed. Five (5) image enhancement algorithms were tested introducing the contrast-limited adaptive histogram equalization (CLAHE), the local range modification (LRM) and the redundant discrete wavelet (RDW) linear stretching and shrinkage algorithms. CAD tuning optimization was targeted to the percentage of the most contrasted pixels and the size of the minimum detectable object which could satisfactorily represent a microcalcification. The highest performance in two mammographic datasets, were achieved for LRM (A(Z)=0.932) and the wavelet-based linear stretching (A(Z)=0.926) methodology.

A wavelet-based spatially adaptive method for mammographic contrast enhancement.

A method aimed at minimizing image noise while optimizing contrast of image features is presented. The method is generic and it is based on local modification of multiscale gradient magnitude values provided by the redundant dyadic wavelet transform. Denoising is accomplished by a spatially adaptive thresholding strategy, taking into account local signal and noise standard deviation. Noise standard deviation is estimated from the background of the mammogram. Contrast enhancement is accomplished by applying a local linear mapping operator on denoised wavelet magnitude values. The operator normalizes local gradient magnitude maxima to the global maximum of the first scale magnitude subimage. Coefficient mapping is controlled by a local gain limit parameter. The processed image is derived by reconstruction from the modified wavelet coefficients. The method is demonstrated with a simulated image with added Gaussian noise, while an initial quantitative performance evaluation using 22 images from the DDSM database was performed. Enhancement was applied globally to each mammogram, using the same local gain limit value. Quantitative contrast and noise metrics were used to evaluate the quality of processed image regions containing verified lesions. Results suggest that the method offers significantly improved performance over conventional and previously reported global wavelet contrast enhancement methods. The average contrast improvement, noise amplification and contrast-to-noise ratio improvement indices were measured as 9.04, 4.86 and 3.04, respectively. In addition, in a pilot preference study, the proposed method demonstrated the highest ranking, among the methods compared. The method was implemented in C++ and integrated into a medical image visualization tool.

Breast Cancer Diagnosis: Analyzing Texture of Tissue Surrounding Microcalcifications

The current study investigates texture properties of the tissue surrounding microcalcification (MC) clusters on mammograms for breast cancer diagnosis. The case sample analyzed consists of 85 dense mammographic images, originating from the digital database for screening mammography. mammograms analyzed contain 100 subtle MC clusters (46 benign and 54 malignant). The tissue surrounding MCs is defined on original and wavelet decomposed images, based on a redundant discrete wavelet transform. Gray-level texture and wavelet coefficient texture features at three decomposition levels are extracted from surrounding tissue regions of interest (ST-ROIs). Specifically, gray-level first-order statistics, gray-level cooccurrence matrices features, and Lawspsila texture energy measures are extracted from original image ST-ROIs. Wavelet coefficient first-order statistics and wavelet coefficient cooccurrence matrices features are extracted from subimages ST-ROIs. The ability of each feature set in differentiating malignant from benign tissue is investigated using a probabilistic neural network. Classification outputs of most discriminating feature sets are combined using a majority voting rule. The proposed combined scheme achieved an area under receiver operating characteristic curve (Az) of 0.989. Results suggest that MCspsila ST texture analysis can contribute to computer-aided diagnosis of breast cancer.

Assessing heterogeneity of lesion enhancement kinetics in dynamic contrast-enhanced MRI for breast cancer diagnosis

The current study investigates the feasibility of using texture analysis to quantify the heterogeneity of lesion enhancement kinetics in order to discriminate malignant from benign breast lesions. A total of 82 biopsy-proven breast lesions (51 malignant, 31 benign), originating from 74 women subjected to dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) were analysed. Pixel-wise analysis of DCE-MRI lesion data was performed to generate initial enhancement, post-initial enhancement and signal enhancement ratio (SER) parametric maps; these maps were subsequently subjected to co-occurrence matrix texture analysis. The discriminating ability of texture features extracted from each parametric map was investigated using a least-squares minimum distance classifier and further compared with the discriminating ability of the same texture features extracted from the first post-contrast frame. Selected texture features extracted from the SER map achieved an area under receiver operating characteristic curve of 0.922 +/- 0.029, a performance similar to post-initial enhancement map features (0.906 +/- 0.032) and statistically significantly higher than for initial enhancement map (0.767 +/- 0.053) and first post-contrast frame (0.756 +/- 0.060) features. Quantifying the heterogeneity of parametric maps that reflect lesion washout properties could contribute to the computer-aided diagnosis of breast lesions in DCE-MRI.

Texture-Based Identification and Characterization of Interstitial Pneumonia Patterns in Lung Multidetector CT

Identification and characterization of diffuse parenchyma lung disease (DPLD) patterns challenges computer-aided schemes in computed tomography (CT) lung analysis. In this study, an automated scheme for volumetric quantification of interstitial pneumonia (IP) patterns, a subset of DPLD, is presented, utilizing a multidetector CT (MDCT) dataset. Initially, lung-field segmentation is achieved by 3-D automated gray-level thresholding combined with an edge-highlighting wavelet preprocessing step, followed by a texture-based border refinement step. The vessel tree volume is identified and removed from lung field, resulting in lung parenchyma (LP) volume. Following, identification and characterization of IP patterns is formulated as a three-class pattern classification of LP into normal, ground glass, and reticular patterns, by means of k-nearest neighbor voxel classification, exploiting 3-D cooccurrence features. Performance of the proposed scheme in indentifying and characterizing ground glass and reticular patterns was evaluated by means of volume overlap (ground glass: 0.734 ± 0.057, reticular: 0.815 ± 0.037), true-positive fraction (ground glass: 0.638 ± 0.055, reticular: 0.942 ± 0.023) and false-positive fraction (ground glass: 0.361 ± 0.027, reticular: 0.147 ± 0.032) on five MDCT scans.

Texture classification‐based segmentation of lung affected by interstitial pneumonia in high‐resolution CT

Accurate and automated lung field (LF) segmentation in high-resolution computed tomography (HRCT) is highly challenged by the presence of pathologies affecting lung borders, also affecting the performance of computer-aided diagnosis (CAD) schemes. In this work, a two-dimensional LF segmentation algorithm adapted to interstitial pneumonia (IP) patterns is presented. The algorithm employs k-means clustering followed by a filling operation to obtain an initial LF order estimate. The final LF border is obtained by an iterative support vector machine neighborhood labeling of border pixels based on gray level and wavelet coefficient statistics features. A second feature set based on gray level averaging and gradient features was also investigated to evaluate its effect on segmentation performance of the proposed method. The proposed method is evaluated on a dataset of 22 HRCT cases spanning a range of IP patterns such as ground glass, reticular, and honeycombing. The accuracy of the method is assessed using area overlap and shape differentiation metrics (d(mean), d(rms), and d(max)), by comparing automatically derived lung borders to manually traced ones, and further compared to a gray level thresholding-based (GLT-based) method. Accuracy of the methods evaluated is also compared to interobserver variability. The proposed method incorporating gray level and wavelet coefficient statistics demonstrated the highest segmentation accuracy, averaged over left and right LFs (overlap=0.954, d(mean)=1.080 mm, d(rms)=1.407 mm, and d(max)=4.944 mm), which is statistically significant (two-tailed students t test for paired data, p<0.0083) with respect to all metrics considered as compared to the proposed method incorporating gray level averaging and gradient features (overlap=0.918, d(mean)=2.354 mm, d(rms)=3.711 mm, and d(max)=14.412 mm) and the GLT-based method (overlap=0.897, d(mean)=3.618 mm, d(rms)=5.007 mm, and d(max)=16.893 mm). The performance of the three segmentation methods, although decreased as IP pattern severity level (mild, moderate, and severe) was increased, did not demonstrate statistically significant difference (two-tailed students t test for unpaired data, p>0.0167 for all metrics considered). Finally, the accuracy of the proposed method, based on gray level and wavelet coefficient statistics ranges within interobserver variability. The proposed segmentation method could be used as an initial stage of a CAD scheme for IP patterns.

Medical image analysis methods

Computer-Aided Diagnosis of Breast Cancer, H. Chan, B. Sahiner, N. Petrick, L. Hadjiiski, and S. Paquerault Medical Image Processing and Analysis for CAD Systems, A. Papadopoulos, M. Plissiti, and D. Fotiadis Texture and Morphological Analysis of Ultrasound Images of the Carotid Plaque for the Assessment of Stroke,C.Christodoulou, C. Pattichis, E. Kyriacou, M. Pattichis, M. Pantziaris, and A. Nikolaides Biomedical Image Classification Methods and Techniques, V. Ruiz and S. Nasuto Texture Characterization Using Autoregressive Models with Application to Medical Imaging, S. Lee and T. Stathaki Locally Adaptive Wavelet Contrast Enhancement,L.Costaridou, P. Sakellaropoulos, S. Skiadopoulos, and G. Panayiotakis Three-Dimensional Multiscale Watershed Segmentation of MR Images, I. Pratikakis, H.Sahli, and J. Cornelis A MRF-Based Approach for the Measurement of Skin Thickness in Mammography,A. Katartzis, H. Sahli, J. Cornelis, L. Costaridou, and G. Panayiotakis Landmark-Based Registration of Medical Image Data,J. Ruiz-Alzola, E. Suarez-Santana, C. Alberola-Lopez and C. Westin Graph-Based Analysis of Amino Acid Sequences, L. da Fontura Costa Estimation of Human Cortical Connectivity with Multimodal Integration of fMRI and High-Resolution EEG,L. Astolfi, F. Cincotti, D. Mattia, B. He, S. Salinari, and F. Babiloni Evaluation Strategies for Medical Image Analysis and Processing Methodologies, M. Kallergi

Modeling quantum and structure noise of phosphors used in medical X-ray imaging detectors

The noise properties of granular phosphors used in X-ray imaging detectors are studied in terms of a noise transfer function, NTF. This study is performed in high-exposure conditions where the contribution of structure noise to total screen noise is considerable. An analytical model, based on the cascaded linear systems methodology presented in the literature, is developed. This model takes into account the quantum noise and structure noise. Furthermore, it considers the effect of the K X-rays reabsorption on the phosphor material and the effect of screen thickness on the NTF. The model was validated against experimental results obtained by a set of Zn2SiO4:Mn phosphor screens prepared by sedimentation. The model may be used to evaluate the effect of screen thickness and the effect of the characteristic Xrays on NTF in high-exposure conditions where structure noise is considerable. r 2002 Elsevier Science B.V. All rights reserved.

Suitability of new anode materials in mammography: Dose and subject contrast considerations using Monte Carlo simulation

Mammography is the technique with the highest sensitivity and specificity, for the early detection of nonpalpable lesions associated with breast cancer. As screening mammography refers to asymptomatic women, the task of optimization between the image quality and the radiation dose is critical. A way toward optimization could be the introduction of new anode materials. A method for producing the x-ray spectra of different anode/filter combinations is proposed. The performance of several mammographic spectra, produced by both existing and theoretical anode materials, is evaluated, with respect to their dose and subject contrast characteristics, using a Monte Carlo simulation. The mammographic performance is evaluated utilizing a properly designed mathematical phantom with embedded inhomogeneities, irradiated with different spectra, based on combinations of conventional and new (Ru, Ag) anode materials, with several filters (Mo, Rh, Ru, Ag, Nb, Al). An earlier developed and validated Monte Carlo model, for deriving both image and dose characteristics in mammography, was utilized and overall performance results were derived in terms of subject contrast to dose ratio and squared subject contrast to dose ratio. Results demonstrate that soft spectra, mainly produced from Mo, Rh, and Ru anodes and filtered with k-edge filters, provide increased subject contrast for inhomogeneities of both small size, simulating microcalcifications and low density, simulating masses. The harder spectra (W and Ag anode) come short in the discrimination task but demonstrate improved performance when considering the dose delivered to the breast tissue. As far as the overall performance is concerned, new theoretical spectra demonstrate a noticeable good performance that is similar, and in some cases better compared to commonly used systems, stressing the possibility of introducing new materials in mammographic practice as a possible contribution to its optimization task. In the overall optimization task in terms of subject contrast to dose ratio, tube voltage was found to have a minor effect, while with respect to the filter material, a lesion specific performance was noticed, with Al filtered spectra showing improved characteristics in case of the inhomogeneities simulating microcalcifications, while softer k-edge filtered spectra are more suitable for the discrimination of inhomogeneities simulating masses.