Segmentation and intensity estimation for microarray images with saturated pixels

An automated method for gridding and clustering-based segmentation of cDNA microarray images

In this paper we present a dynamic texture based motion segmentation approach to address the challenging problem of heart localization and segmentation in 4D spatio-temporal cardiac images. Our approach introduces time-dependent dynamic constraints into model-based segmentation, and it has the advantage of producing segmentation results that are both spatially and temporally consistent. Compared to previous methods that segment cardiac contours, our method offers the following advantages: 1) the heart can be quickly localized in 4D cardiac images with distinct dynamic signatures; 2) heart dynamics are learned online and adaptively by analyzing the dynamic texture from the video sequence of a cardiac cycle and then incorporated in the segmentation process; and 3) the proposed dynamic features can be easily integrated with model-based segmentation methods. We illustrate our framework through combining the new dynamic constraints with active contour models, and demonstrate its performance on sequences of 4D MRI and tagged MRI images of the heart. We also validate the accuracy of the segmentation results by comparing with ground truth marked by experts

Background/Objectives: This study presents an external and internal prior guided patch based filter for minimizing Gaussian noise in complementary deoxyribonucleic acid (cDNA) microarray images. Methods/Statistical analysis: The proposed denoising filter is capable of taking into consideration both external and internal prior. It employs combined prior guided patch based denoising considering various distance based patch-matching methods. Findings: Experimental results demonstrate that the combined prior guided patch based filter outperforms the existing well-known filters in minimizing noise of cDNA microarray images. The outcome of the proposed scheme found to offer better peak signalto-noise ratio and structural similarity index in contrast to existing filtering techniques. Effectiveness of the proposed denoising method is also assessed by estimating the spot intensities of cDNA microarray image that reflects the effect of noise reduction in the image. Application/Improvements: Minimization of noise is a crucial step of cDNA microarray image processing and it aids in microarray analysis by extracting valid and good quality gene expression measurements. Keywords: Denoising, External Prior, Internal Prior, K- nearest Neighbor, Microarray Image, Singular Value Decomposition

BackgroundImage analysis is the first crucial step to obtain reliable results from microarray experiments. First, areas in the image belonging to single spots have to be identified. Then, those target areas have to be partitioned into foreground and background. Finally, two scalar values for the intensities have to be extracted. These goals have been tackled either by spot shape methods or intensity histogram methods, but it would be desirable to have hybrid algorithms which combine the advantages of both approaches.ResultsA new robust and adaptive histogram type method is pixel clustering, which has been successfully applied for detecting and quantifying microarray spots. This paper demonstrates how the spot shape can be effectively integrated in this approach. Based on the clustering results, a bivalence mask is constructed. It estimates the expected spot shape and is used to filter the data, improving the results of the cluster algorithm. The quality measure 'stability' is defined and evaluated on a real data set. The improved clustering method is compared with the established Spot software on a data set with replicates.ConclusionThe new method presents a successful hybrid microarray image analysis solution. It incorporates both shape and histogram features and is specifically adapted to deal with typical microarray image characteristics. As a consequence of the filtering step pixels are divided into three groups, namely foreground, background and deletions. This allows a separate treatment of artifacts and their elimination from the further analysis.

Developing a robust method for liver segmentation from magnetic resonance images is a challenging task because of the similar intensity values between adjacent organs, the geometrically complex liver structure, and injection of contrast media. Most importantly, a high anatomical variability of a healthy or diseased liver is a major challenge in defining the exact boundaries of the liver. Several artifacts of pulsation, motion, and partial volume effects are also among the variety of factors that make automatic liver segmentation difficult. In this paper, we present an overview of liver segmentation methods in magnetic resonance images and show comparative results of seven different pseudo-3D liver segmentation approaches chosen from deterministic (K-means-based), probabilistic (Gaussian model-based), supervised neural network (multilayer perceptron-based), and deformable model-based (level set) segmentation methods. The results of quantitative and qualitative analyses using sensitivity, specificity, and accuracy metrics show that the multilayer perceptron-based approach and a level set-based approach, both of which use distance regularization terms and signed pressure force function, are the most successful methods for liver segmentation from spectral presaturation inversion recovery (SPIR) images. However, the multilayer perceptron-based segmentation method has a higher computational cost. The automatic method using the distance regularized level set evolution with signed pressure force function avoids the sensitivity of a user-defined initial contour for each slice, gives the most efficient results for liver segmentation after the preprocessing steps, and also requires less computational time.

The utility and shortcomings of near-real-time ocean surface vector wind retrievals from the NASA Quick Scatterometer (QuikSCAT) in operational forecast and analysis activities at the National Hurricane Center (NHC) are described. The use of QuikSCAT data in tropical cyclone (TC) analysis and forecasting for center location/identification, intensity (maximum sustained wind) estimation, and analysis of outer wind radii is presented, along with shortcomings of the data due to the effects of rain contamination and wind direction uncertainties. Automated QuikSCAT solutions in TCs often fail to show a closed circulation, and those that do are often biased to the southwest of the NHC best-track position. QuikSCAT winds show the greatest skill in TC intensity estimation in moderate to strong tropical storms. In tropical depressions, a positive bias in QuikSCAT winds is seen due to enhanced backscatter by rain, while in major hurricanes rain attenuation, resolution, and signal saturation result in a large negative bias in QuikSCAT intensity estimates. QuikSCAT wind data help overcome the large surface data void in the analysis and forecast area of NHC’s Tropical Analysis and Forecast Branch (TAFB). These data have resulted in improved analyses of surface features, better definition of high wind areas, and improved forecasts of high-wind events. The development of a climatology of gap wind events in the Gulf of Tehuantepec has been possible due to QuikSCAT wind data in a largely data-void region. The shortcomings of ocean surface vector winds from QuikSCAT in the operational environment at NHC are described, along with requirements for future ocean surface vector wind missions. These include improvements in the timeliness and quality of the data, increasing the wind speed range over which the data are reliable, and decreasing the impact of rain to allow for accurate retrievals in all-weather conditions.

We employ right-censored Poisson point process models to develop maximum-likelihood procedures for estimating the time of arrival of transient optical signals subject to saturation distortion. The Poisson intensity is modeled as a template with an unknown scaling factor with additive background counts. Using Monte Carlo simulations, we explore the performance of different algorithms as a function of signal magnitude and saturation threshold. In particular, we characterize the benefit our procedures have over algorithms that are unaware of the censoring.

Objective The muscles of mastication play a major role in the orodigestive system as the principal motive force for the mandible. An algorithm for segmenting these muscles from magnetic resonance (MR) images was developed and tested. Materials and methods Anatomical information about the muscles of mastication in MR images is used to obtain the spatial relationships relating the muscle region of interest (ROI) and head ROI. A model-based technique that involves the spatial relationships between head and muscle ROIs as well as muscle templates is developed. In the segmentation stage, the muscle ROI is derived from the model. Within the muscle ROI, anisotropic diffusion is applied to smooth the texture, followed by thresholding to exclude bone and fat. The muscle template and morphological operators are employed to obtain an initial estimate of the muscle boundary, which then serves as the input contour to the gradient vector flow snake that iterates to the final segmentation. Results The method was applied to segmentation of the masseter, lateral pterygoid and medial pterygoid in 75 images. The overlap indices (κ) achieved are 91.4, 92.1 and 91.2%, respectively. Conclusion A model-based method for segmenting the muscles of mastication from MR images was developed and tested. The results show good agreement between manual and automatic segmentations.

A spot-adaptive compound clustering-enhancement-segmentation (CES) scheme was developed for the quantification of gene expression levels in microarray images. The CES-scheme employed 1/griding, for locating spot-regions, 2/Fuzzy C-means clustering, for segmenting spots from background, 3/ background noise estimation and spot's center localization, 4/emphasizing of spot's outline by the CLAHE image enhancement technique, 5/segmentation by the SRG algorithm, using information from step 3, and 6/microarray spot intensity extraction. Extracted intensities by the CES-Scheme were compared against those obtained by the MAGIC TOOL's SRG. Kullback-Liebler metric's values for the CES-Scheme were on average double than MAGIC TOOL's, with differences ranging from 1.45bits to 2.77bits in 7 cDNA images. Coefficient-of-Variation results showed significantly higher reproducibility (p<0.001) for the CES-Scheme in quantifying gene expression levels. Processing times for 1024×1024 16-bit microarray images containing 6400 spots were 300 and 487 seconds for the CES-Scheme and MAGIC TOOL respectively.

Renal cortical scintigraphy is a well-established functional imaging technique for visual analysis of radiopharmaceutical tracer distribution. However, the visual evaluation is subjective, causing interobserver variability, especially in a quantifiable number of scars. The purpose of this study was to develop new computerized methods in renal cortical scintigraphy image interpretation, particularly addressing activity distribution and cortex continuity (scars). The proposed methods involve preprocessing stages of model-based automatic kidney segmentation using active-shape model and image normalization (transforming each kidney image into a standardized image vector). For our previous computer-aided diagnosis scheme, two new image-based features [localized activity drop and principal component analysis (PCA)] were defined. Their performance was evaluated and compared with our previous scheme by using free-response receiver operating characteristic that is in terms of sensitivity (true-positive fraction) and the mean number of false positives (FPs) per image. Clinical tests were conducted in 297 patients (231 normal and 66 abnormal). The PCA-based image feature presented the best scar detection performance, followed by the localized activity drop feature. Both schemes were found to be superior to our previous computer-aided diagnosis scheme. In the PCA-based scheme, for sensitivity of 0.90 (76/84), the mean number of FPs was measured as 4.52 (1343/297). For another setting with reduced sensitivity of 0.79 (66/84), the mean number of FPs improved to 1.21 (360/297). Finally, a decision fusion scheme using 'majority voting' was also proposed, the sensitivity and mean number of FPs of which were measured as 0.83 (70/84) and 1.90 (563/297), respectively. The proposed methods have potential to provide effective second-reader information to nuclear medicine specialists in finding scar regions. Possible ways to improve the FP rate were also proposed.

This review explores the use of machine learning (ML) techniques for detecting pests and diseases in crops, which is a significant challenge in agriculture, leading to substantial yield losses worldwide. This study focuses on the integration of ML models, particularly Convolutional Neural Networks (CNNs), which have shown promise in accurately identifying and classifying plant diseases from images. By analyzing studies published from 2019 to 2024, this work summarizes the common methodologies involving stages of data acquisition, preprocessing, segmentation, feature extraction, and prediction to develop robust ML models. The findings indicate that the incorporation of advanced image processing and ML algorithms significantly enhances disease detection capabilities, leading to the early and precise diagnosis of crop ailments. This can not only improve crop yield and quality but also reduce the dependency on chemical pesticides, contributing to more sustainable agricultural practices. Future research should focus on enhancing the robustness of these models to varying environmental conditions and expanding the datasets to include a wider variety of crops and diseases. CNN-based models, particularly specialized architectures like ResNet, are the most widely used in the studies reviewed, making up 42.36% of all models, with ResNet alone contributing 7.65%. This highlights ResNet’s appeal for tasks that demand deep architectures and sophisticated feature extraction. Additionally, SVM models account for 9.41% of the models examined. The prominence of both ResNet and MobileNet reflects a trend toward architectures with residual connections for deeper networks, alongside efficiency-focused designs like MobileNet, which are well-suited for mobile and edge applications.

In real time continuous activity recognition systems, utilization of a data segmentation stage increases the dependency of success ratio on the size of activity set as well as activity type, duration and sensor sampling rate. In this study, we analyzed if iterative K-Nearest Neighbour based knowledge discovery performed on acceleration data can substitute for the segmentation stage to reduce these dependencies for hand oriented activities. To this end, we compared peak frequency and wavelet entropy feature extraction schemes for the recognition of open-pill-box, put-pill-in-mouth, drink and put-glass-back actions which constitute as a whole "medication intake" activity. We evaluated the performance of these schemes on incomplete data, resulting from the iterative process. According to our findings, peak frequency outperforms wavelet entropy in terms of Intra-Class-Correlation (ICC) metric which is an indication for better adaptation to variation in activity type with incompleteness mitigation problem. Our work points out that a more proficient iterative classification algorithm is required for attaining higher adaptability to the diversification of actions that stem from the incompleteness problem.

We suggest that silver nanocube (AgNC) aggregates within cylindrical pores (PAM–AgNC) can be employed as efficient nanostructures for highly efficient, robust, tunable, and reusable surface-enhanced Raman scattering (SERS) substrates for trace level organic vapor detection which is a challenging task in chemical detection. We demonstrate the ability to tune both the detection limit and the onset of signal saturation of the substrate by switching the adsorption behavior of AgNCs between highly aggregated and more disperse by varying the number of adsorption-mediating polyelectrolyte bilayers on the pore walls of the membrane. The different AgNC distributions show large differences in the trace vapor detection limit of the common Raman marker benzenethiol (BT) and a widely used explosive binder N-methyl-4-nitroaniline (MNA), demonstrating the importance of the large electromagnetic field enhancement associated with AgNC coupling. The SERS substrate with highly aggregated AgNCs within the cylindrical pores allows for consistent trace detection of mid ppb (∼500) for BT analyte, and a record limit of detection of low ppb (∼3) for MNA vapors with an estimated achievable limit of detection of approximately 600 ppt. The dispersed AgNC aggregates do not saturate at higher ppb concentrations, providing an avenue to distinguish between higher ppb concentrations and increase the effective range of the SERS substrate design. A comparison between the AgNC substrate and an electroless deposition substrate with silver quasi-nanospheres (PAM–AgNS) also demonstrates a higher SERS activity, and better detection limit, by the nanocube aggregates. This is supported by FDTD electromagnetic simulations that suggest that the higher integrated electromagnetic field intensity of the hot spots and the large specific interfacial areas impart greatly improved SERS for the AgNCs. Moreover, we demonstrated that the AgNC substrate can be reused multiple times without significant loss of SERS activity which opens up new avenues for in-field monitoring.

An algorithm for extracting individual signs of a person’s gait according to the data of a mobile phone accelerometer is considered. The developed algorithm includes the stage of data segmentation, correlation selection of motion patterns, and data clustering procedures. By selecting noisy segments, the quality of data clustering and the extraction of individual features is improved. The results of the algorithm work allow us to refine the existing models of changes in human motor behavior in personalized medicine and security systems. The article also discusses the features of data segmentation and the influence of external factors on the measurement results.

Detection of a cancer in a lung through image processing with SVM classification is processed in this research paper. The research could facilitate the detection of a cancer in desired output. The author considered a computer tomography (CT) image of a lung as an input data set which further processed by segmentation of that image. Here water segmentation is proposed on an input image to improve the quality from the image. Once the segmentation of an image is done the author used the SVM classification to train segmented data set to get an accurate reading of lung cancer detection. In every stage of classification image segmentation is done separately. For classification purpose, SVM binary classifier is used to show a higher accuracy in a detection of a lung cancer. The author has makes use of a confusion matrix to determine the predicted groups in group and group hat respectively.KeywordsDetection of lung cancerCT scan image processingWatershed segmentationSVM classifier