Javad Alirezaie

Neural network based segmentation of magnetic resonance images of the brain

The potential of artificial neural networks (ANNs) for the classification and segmentation of magnetic resonance (MR) images of the human brain is investigated. In this study, we present the application of a Learning Vector Quantization (LVQ) Artificial Neural Network (ANN) for the multispectral supervised classification of MR images. We have modified the LVQ for better and more accurate classification. We have compared the results using LVQ ANN versus back-propagation ANN. This comparison shows that, unlike back-propagation ANN, our method is insensitive to the gray-level variation of MR images between different slices. It shows that tissue segmentation using LVQ ANN also performs better and faster than that using back-propagation ANN.

Automatic segmentation of cerebral MR images using artificial neural networks

The authors present an unsupervised clustering technique for multispectral segmentation of magnetic resonance (MR) images of the human brain. Their scheme utilizes the Self Organizing Feature Map (SOFM) artificial neural network for feature mapping and generates a set of codebook vectors. By extending the network with an additional layer the map will be classified and each tissue class will be labeled. An algorithm has been developed for extracting the cerebrum from the head scan prior to the segmentation. Extracting the cerebrum is performed by stripping away the skull pixels from the T2 image. Three tissue types of the brain: white matter, gray matter and cerebral spinal fluid (CSF) are segmented accurately. To compare the results with other conventional approaches the authors applied the c-means algorithm to the problem.

Development of a Nanoparticle-Labeled Microfluidic Immunoassay for Detection of Pathogenic Microorganisms

ABSTRACT The light-scattering properties of submicroscopic metal particles ranging from 40 to 120 nm in diameter have recently been investigated. These particles scatter incident white light to generate monochromatic light, which can be seen either by the naked eye or by dark-field microscopy. The nanoparticles are well suited for detection in microchannel-based immunoassays. The goal of the present study was to detect Helicobacter pylori- and Escherichia coli O157:H7-specific antigens with biotinylated polyclonal antibodies. Gold particles (diameter, 80 nm) functionalized with a secondary antibiotin antibody were then used as the readout. A dark-field stereomicroscope was used for particle visualization in poly(dimethylsiloxane) microchannels. A colorimetric quantification scheme was developed for the detection of the visual color changes resulting from immune reactions in the microchannels. The microchannel immunoassays reliably detected H. pylori and E. coli O157:H7 antigens in quantities on the order of 10 ng, which provides a sensitivity of detection comparable to those of conventional dot blot assays. In addition, the nanoparticles within the microchannels can be stored for at least 8 months without a loss of signal intensity. This strategy provides a means for the detection of nanoparticles in microchannels without the use of sophisticated equipment. In addition, the approach has the potential for use for further miniaturization of immunoassays and can be used for long-term archiving of immunoassays.

Automatic lung segmentation in CT images using watershed transform

The preprocessing step of most computer-aided diagnosis (CAD) systems for identifying the lung diseases is lung segmentation. We present a novel lung segmentation technique based on watershed transform, which is fast and accurate. Lung region is precisely marked with internal and external markers. The markers are combined with the gradient image of the original data and watershed transform is applied on the combined data to find the lung borders. Rolling ball filter is used to smooth the contour and fill the cavities while preserving the original borders. The proposed method eliminates the tasks of finding an optimal threshold and separating the attached left and right lungs, which are two common practices in most lung segmentation methods and require a significant amount of time. We have applied our new approach on several pulmonary CT images and the results reveal the speed, robustness and accuracy of this method.

Colony size measurement of the yeast gene deletion strains for functional genomics.

BackgroundNumerous functional genomics approaches have been developed to study the model organism yeast, Saccharomyces cerevisiae, with the aim of systematically understanding the biology of the cell. Some of these techniques are based on yeast growth differences under different conditions, such as those generated by gene mutations, chemicals or both. Manual inspection of the yeast colonies that are grown under different conditions is often used as a method to detect such growth differences.ResultsHere, we developed a computerized image analysis system called Growth Detector (GD), to automatically acquire quantitative and comparative information for yeast colony growth. GD offers great convenience and accuracy over the currently used manual growth measurement method. It distinguishes true yeast colonies in a digital image and provides an accurate coordinate oriented map of the colony areas. Some post-processing calculations are also conducted. Using GD, we successfully detected a genetic linkage between the molecular activity of the plant-derived antifungal compound berberine and gene expression components, among other cellular processes. A novel association for the yeast mek1 gene with DNA damage repair was also identified by GD and confirmed by a plasmid repair assay. The results demonstrate the usefulness of GD for yeast functional genomics research.ConclusionGD offers significant improvement over the manual inspection method to detect relative yeast colony size differences. The speed and accuracy associated with GD makes it an ideal choice for large-scale functional genomics investigations.

Block-wise 2D kernel PCA/LDA for face recognition

Direct extension of (2D) matrix-based linear subspace algorithms to kernel-induced feature space is computationally intractable and also fails to exploit local characteristics of input data. In this letter, we develop a 2D generalized framework which integrates the concept of kernel machines with 2D principal component analysis (PCA) and 2D linear discriminant analysis (LDA). In order to remedy the mentioned drawbacks, we propose a block-wise approach based on the assumption that data is multi-modally distributed in so-called block manifolds. Proposed methods, namely block-wise 2D kernel PCA (B2D-KPCA) and block-wise 2D generalized discriminant analysis (B2D-GDA), attempt to find local nonlinear subspace projections in each block manifold or alternatively search for linear subspace projections in kernel space associated with each blockset. Experimental results on ORL face database attests to the reliability of the proposed block-wise approach compared with related published methods.

Endocardial boundary extraction in left ventricular echocardiographic images using fast and adaptive B-spline snake algorithm

PurposeA fast and robust algorithm was developed for automatic segmentation of the left ventricular endocardial boundary in echocardiographic images. The method was applied to calculate left ventricular volume and ejection fraction estimation.MethodsA fast adaptive B-spline snake algorithm that resolves the computational concerns of conventional active contours and avoids computationally expensive optimizations was developed. A combination of external forces, adaptive node insertion, and multiresolution strategy was incorporated in the proposed algorithm. Boundary extraction with area and volume estimation in left ventricular echocardiographic images was implemented using the B-spline snake algorithm. The method was implemented in MATLAB and 50 medical images were used to evaluate the algorithm performance. Experimental validation was done using a database of echocardiographic images that had been manually evaluated by experts.ResultsComparison of methods demonstrates significant improvement over conventional algorithms using the adaptive B-spline technique. Moreover, our method reached a reasonable agreement with the results obtained manually by experts. The accuracy of boundary detection was calculated with Dice’s coefficient equation (91.13%), and the average computational time was 1.24 s in a PC implementation.ConclusionIn sum, the proposed method achieves satisfactory results with low computational complexity. This algorithm provides a robust and feasible technique for echocardiographic image segmentation. Suggestions for future improvements of the method are provided.

Computer simulation for segmentation of lung nodules in CT images

Automated lung nodule detection through computed tomography (CT) image segmentation is a new and exciting research area of medical image processing. We are currently developing a nodule detection system. For the testing stage we have developed a method to insert simulated lung nodules into CT images. The simulated nodules can be used to produce corner cases to provide a better test environment for the segmentation technique than would be available through clinical data. The synthetic lung nodules produced by this program are based on a 2D Gaussian structure. This is modeled on the study of the structure of real lung nodules. We have also developed a lung segmentation technique, which is the first stage of our nodule detection system. The lungs are segmented using a combination of thresholding, morphology, 3D region growing, and volume analysis

Use of dynamic CT in acute respiratory distress syndrome (ARDS) with comparison of positive and negative pressure ventilation

Negative pressure ventilation via an external device (‘iron lung’) has the potential to provide better oxygenation with reduced barotrauma in patients with ARDS. This study was designed to see if oxygenation differences between positive and negative ventilation could be explained by CT. Six anaesthetized rabbits had ARDS induced by repeated saline lavage. Rabbits were ventilated with positive pressure ventilation (PPV) and negative pressure ventilation (NPV) in turn. Dynamic CT images were acquired over the respiratory cycle. A computer-aided method was used to segment the lung and calculate the range of CT densities within each slice. Volumes of ventilated lung and atelectatic lung were measured over the respiratory cycle. NPV was associated with an increased percentage of ventilated lung and decreased percentage of atelectatic lung. The most significant differences in ventilation and atelectasis were seen at mid-inspiration and mid-expiration (ventilated lung NPV = 61%, ventilated lung PPV = 47%, p < 0.001; atelectatic lung NPV = 10%, atelectatic lung PPV 19%, p < 0.001). Aeration differences were not significant at end-inspiration. Dynamic CT can show differences in lung aeration between positive and negative ventilation in ARDS. These differences would not be appreciated if only static breath-hold CT was used.

Automatic Segmentation of Abnormal Lung Parenchyma Utilizing Wavelet Transform

Since several lung diseases are diagnosed based on the patterns of lung tissue in medical images, texture segmentation is an essential part of the most computer aided diagnosis (CAD) systems. In this paper a novel composite method is proposed to segment the abnormality in lung tissue in pediatric CT images. The proposed approach is based on wavelet transform and intensity similarities. Our focus is on the honeycomb texture in lung tissue. After segmenting lung regions, wavelet transform is applied to decompose the image. The vertical subimage of lung is thresholded to extract high resolution areas. Then the regions with low pixel intensities are kept and grown to segment the honeycomb regions. The proposed method has been tested on 91 pediatric chest CT images containing healthy and unhealthy lung images. Statistical analysis shows the sensitivity of 100% along with the specificity of 94.44%.