Automated Protein Subcellular Localization Based on Local Invariant Features

To understand the function of the encoded proteins, we need to be able to know the subcellular location of a protein. The most common method used for determining subcellular location is fluorescence microscopy which allows subcellular localizations to be imaged in high throughput. Image feature calculation has proven invaluable in the automated analysis of cellular images. This article proposes a novel method named LDPs for feature extraction based on invariant of translation and rotation from given images, the nature which is to count the local difference features of images, and the difference features are given by calculating the D-value between the gray value of the central pixel c and the gray values of eight pixels in the neighborhood. The novel method is tested on two image sets, the first set is which fluorescently tagged protein was endogenously expressed in 10 sebcellular locations, and the second set is which protein was transfected in 11 locations. A SVM was trained and tested for each image set and classification accuracies of 96.7 and 92.3 % were obtained on the endogenous and transfected sets respectively.     

Evaluation of DNA and nuclear protein features for their use in describing normal and malignant endometrium

Different feature sets (geometric, densitometric, and textural) derived from DNA and nuclear protein staining were evaluated for their use in describing atrophic, secretory, and proliferative endometrium, and well-differentiated stage I and moderately differentiated stage I adenocarcinomas of the endometrium. It was found that the pattern of significant differences among these groups varied between feature sets, while remaining consistent within a set of features. The DNA density and run-length features were not very effective in describing group mean differences, whereas the co-occurrence features revealed significant differences among most groups. The protein run-length features were the only ones that consistently showed a difference between proliferative endometrium and well-differentiated adenocarcinomas. Analyses repeated on only cells in the G0/G1 DNA region improved the differentiation between moderately differentiated adenocarcinomas and the other groups. It was concluded that the use of DNA and nuclear protein texture features are effective in describing group differences that cannot be described by DNA content only.     

Rough-Fuzzy Clustering and Unsupervised Feature Selection for Wavelet Based MR Image Segmentation

Image segmentation is an indispensable process in the visualization of human tissues, particularly during clinical analysis of brain magnetic resonance (MR) images. For many human experts, manual segmentation is a difficult and time consuming task, which makes an automated brain MR image segmentation method desirable. In this regard, this paper presents a new segmentation method for brain MR images, integrating judiciously the merits of rough-fuzzy computing and multiresolution image analysis technique. The proposed method assumes that the major brain tissues, namely, gray matter, white matter, and cerebrospinal fluid from the MR images are considered to have different textural properties. The dyadic wavelet analysis is used to extract the scale-space feature vector for each pixel, while the rough-fuzzy clustering is used to address the uncertainty problem of brain MR image segmentation. An unsupervised feature selection method is introduced, based on maximum relevance-maximum significance criterion, to select relevant and significant textural features for segmentation problem, while the mathematical morphology based skull stripping preprocessing step is proposed to remove the non-cerebral tissues like skull. The performance of the proposed method, along with a comparison with related approaches, is demonstrated on a set of synthetic and real brain MR images using standard validity indices.     

Combinatorial use of mRNA and two-dimensional electrophoresis expression data to choose relevant features for mass spectrometric identification

It is only recently that quantitative studies of differential proteome analysis (DPA) have become possible. In this paper the issues involved in quantitative DPA are discussed and novel tools to select features for identification by mass spectrometry (MS) are described. The problem of comparing two sets of gels on a global level is explored as well as how to find specific protein features that differentiate two sets of two-dimensional electrophoresis gels. The concept of a 'virtual' gel, derived from gene expression data, is introduced. The virtual gel enables the co-analysis of data from gene and protein expression. We discuss the value of such an approach, and consider what new information can be gained by using gene and protein expression together. These tools are illustrated by analysis of data from tandem gene and protein expression experiments. Features that are highlighted by the above methods are putative candidates for MS identification. Tools are described that integrate the process of feature selection, cutting, and MS analysis.     

Learning protein multi-view features in complex space

Protein attribute prediction from primary sequences is an important task and how to extract discriminative features is one of the most crucial aspects. Because single-view feature cannot reflect all the information of a protein, fusing multi-view features is considered as a promising route to improve prediction accuracy. In this paper, we propose a novel framework for protein multi-view feature fusion: first, features from different views are parallely combined to form complex feature vectors; Then, we extend the classic principal component analysis to the generalized principle component analysis for further feature extraction from the parallely combined complex features, which lie in a complex space. Finally, the extracted features are used for prediction. Experimental results on different benchmark datasets and machine learning algorithms demonstrate that parallel strategy outperforms the traditional serial approach and is particularly helpful for extracting the core information buried among multi-view feature sets. A web server for protein structural class prediction based on the proposed method (COMSPA) is freely available for academic use at: http://www.csbio.sjtu.edu.cn/bioinf/COMSPA/.     

Textural analysis in the diagnosis of benign and malignant breast cells

OBJECTIVE: To study the discriminatory capacity of textural variables to classify the nuclei of breast tumor cells as benign or malignant, using a statistical approach. STUDY DESIGN: Image analysis techniques were used to automatically segment nuclei of cells obtained by fine needle aspiration and Papanicolaou stained. The sample comprised 95 cases of malignant lesions and 47 cases of benign lesions (approximately 25 nuclei per case), and 27 textural variables were measured. Two methods were used to analyze the data: classification and regression trees (CART) and discriminant analysis. RESULTS: The variance in gray levels was the most decisive variable in the CART analysis, correctly classifying 57% and 97% of benign and malignant cases, respectively. Discriminant analysis yielded the best results, correctly classifying 79% and 85% of benign and malignant cases, respectively. CONCLUSION: The classifier obtained by a statistical approach to the textural analysis of Papanicolaou-stained nuclei did not prove useful for diagnostic discrimination. Staining techniques that are not chromatin specific are highly variable, and other features have proven more effective with this type of staining.     

Sleep apnoea detection from ECG using features extracted from reconstructed phase space and frequency domain

Sleep apnoea is a very common sleep disorder which is able to cause symptoms such as daytime sleepiness, irritability and poor concentration. This paper presents a combinational feature extraction approach based on some nonlinear features extracted from Electro Cardio Graph (ECG) Reconstructed Phase Space (RPS) and usually used frequency domain features for detection of sleep apnoea. Here 6 nonlinear features extracted from ECG RPS are combined with 3 frequency based features to reconstruct final feature set. The nonlinear features consist of Detrended Fluctuation Analysis (DFA), Correlation Dimensions (CD), 3 Large Lyapunov Exponents (LLEs) and Spectral Entropy (SE). The final proposed feature set show about 94.8% accuracy over the Physionet sleep apnoea dataset using a kernel based SVM classifier. This research also proves that using non-linear analysis to detect sleep apnoea can potentially improve the classification accuracy of apnoea detection system.     

Simulation Studies as Designed Experiments: The Comparison of Penalized Regression Models in the “Large p,Small n” Setting

New algorithms are continuously proposed in computational biology. Performance evaluation of novel methods is important in practice. Nonetheless, the field experiences a lack of rigorous methodology aimed to systematically and objectively evaluate competing approaches. Simulation studies are frequently used to show that a particular method outperforms another. Often times, however, simulation studies are not well designed, and it is hard to characterize the particular conditions under which different methods perform better. In this paper we propose the adoption of well established techniques in the design of computer and physical experiments for developing effective simulation studies. By following best practices in planning of experiments we are better able to understand the strengths and weaknesses of competing algorithms leading to more informed decisions about which method to use for a particular task. We illustrate the application of our proposed simulation framework with a detailed comparison of the ridge-regression, lasso and elastic-net algorithms in a large scale study investigating the effects on predictive performance of sample size, number of features, true model sparsity, signal-to-noise ratio, and feature correlation, in situations where the number of covariates is usually much larger than sample size. Analysis of data sets containing tens of thousands of features but only a few hundred samples is nowadays routine in computational biology, where “omics” features such as gene expression, copy number variation and sequence data are frequently used in the predictive modeling of complex phenotypes such as anticancer drug response. The penalized regression approaches investigated in this study are popular choices in this setting and our simulations corroborate well established results concerning the conditions under which each one of these methods is expected to perform best while providing several novel insights.     

Predicting Future Morphological Changes of Lesions from Radiotracer Uptake in 18F-FDG-PET Images

We introduce a novel computational framework to enable automated identification of texture and shape features of lesions on ¹⁸F-FDG-PET images through a graph-based image segmentation method. The proposed framework predicts future morphological changes of lesions with high accuracy. The presented methodology has several benefits over conventional qualitative and semi-quantitative methods, due to its fully quantitative nature and high accuracy in each step of (i) detection, (ii) segmentation, and (iii) feature extraction. To evaluate our proposed computational framework, thirty patients received 2 ¹⁸F-FDG-PET scans (60 scans total), at two different time points. Metastatic papillary renal cell carcinoma, cerebellar hemongioblastoma, non-small cell lung cancer, neurofibroma, lymphomatoid granulomatosis, lung neoplasm, neuroendocrine tumor, soft tissue thoracic mass, nonnecrotizing granulomatous inflammation, renal cell carcinoma with papillary and cystic features, diffuse large B-cell lymphoma, metastatic alveolar soft part sarcoma, and small cell lung cancer were included in this analysis. The radiotracer accumulation in patients'' scans was automatically detected and segmented by the proposed segmentation algorithm. Delineated regions were used to extract shape and textural features, with the proposed adaptive feature extraction framework, as well as standardized uptake values (SUV) of uptake regions, to conduct a broad quantitative analysis. Evaluation of segmentation results indicates that our proposed segmentation algorithm has a mean dice similarity coefficient of 85.75±1.75%. We found that 28 of 68 extracted imaging features were correlated well with SUV_max (p<0.05), and some of the textural features (such as entropy and maximum probability) were superior in predicting morphological changes of radiotracer uptake regions longitudinally, compared to single intensity feature such as SUV_max. We also found that integrating textural features with SUV measurements significantly improves the prediction accuracy of morphological changes (Spearman correlation coefficient = 0.8715, p<2e-16).     

A Comparative Approach for MI-Based EEG Signals Classification Using Energy,Power and Entropy

ObjectiveThe initial principal task of a Brain-Computer Interfacing (BCI) research is to extract the best feature set from a raw EEG (Electroencephalogram) signal so that it can be used for the classification of two or multiple different events. The main goal of the paper is to develop a comparative analysis among different feature extraction techniques and classification algorithms.Materials and methodsIn this present investigation, four different methodologies have been adopted to classify the recorded MI (motor imagery) EEG signal, and their comparative study has been reported. Haar Wavelet Energy (HWE), Band Power, Cross-correlation, and Spectral Entropy (SE) based Cross-correlation feature extraction techniques have been considered to obtain the necessary features set from the raw EEG signals. Four different machine learning algorithms, viz. LDA (Linear Discriminant Analysis), QDA (Quadratic Discriminant Analysis), Naïve Bayes, and Decision Tree, have been used to classify the features.ResultsThe best average classification accuracies are 92.50%, 93.12%, 72.26%, and 98.71% using the four methods. Further, these results have been compared with some recent existing methods.ConclusionThe comparative results indicate a significant accuracy level performance improvement of the proposed methods with respect to the existing one. Hence, this presented work can guide to select the best feature extraction method and the classifier algorithm for MI-based EEG signals.     

Integrating Dimension Reduction and Out-of-Sample Extension in Automated Classification of Ex Vivo Human Patellar Cartilage on Phase Contrast X-Ray Computed Tomography

Phase contrast X-ray computed tomography (PCI-CT) has been demonstrated as a novel imaging technique that can visualize human cartilage with high spatial resolution and soft tissue contrast. Different textural approaches have been previously investigated for characterizing chondrocyte organization on PCI-CT to enable classification of healthy and osteoarthritic cartilage. However, the large size of feature sets extracted in such studies motivates an investigation into algorithmic feature reduction for computing efficient feature representations without compromising their discriminatory power. For this purpose, geometrical feature sets derived from the scaling index method (SIM) were extracted from 1392 volumes of interest (VOI) annotated on PCI-CT images of ex vivo human patellar cartilage specimens. The extracted feature sets were subject to linear and non-linear dimension reduction techniques as well as feature selection based on evaluation of mutual information criteria. The reduced feature set was subsequently used in a machine learning task with support vector regression to classify VOIs as healthy or osteoarthritic; classification performance was evaluated using the area under the receiver-operating characteristic (ROC) curve (AUC). Our results show that the classification performance achieved by 9-D SIM-derived geometric feature sets (AUC: 0.96 ± 0.02) can be maintained with 2-D representations computed from both dimension reduction and feature selection (AUC values as high as 0.97 ± 0.02). Thus, such feature reduction techniques can offer a high degree of compaction to large feature sets extracted from PCI-CT images while maintaining their ability to characterize the underlying chondrocyte patterns.     

Quantifying biofilm structure using image analysis

We have developed and implemented methods of extracting morphological features from images of biofilms in order to quantify the characteristics of the inherent heterogeneity. This is a first step towards quantifying the relationship between biofilm heterogeneity and the underlying processes, such as mass-transport dynamics, substrate concentrations, and species variations. We have examined two categories of features, areal, which quantify the relative magnitude of the heterogeneity and textural, which quantify the microscale structure of the heterogeneous elements. The feature set is not exhaustive and has been restricted to two-dimensional images to this point. Included in this paper are the methods used to extract the structural information and the algorithms used to quantify the data. The features discussed are porosity, fractal dimension, diffusional length, angular second moment, inverse difference moment and textural entropy. We have found that some features are better predictors of biofilm behavior than others and we discuss possible future directions for research in this area.     

Computer-based malignancy grading of astrocytomas employing a support vector machine classifier, the WHO grading system and the regular hematoxylin-eosin diagnostic staining procedure

OBJECTIVE: To investigate and develop an automated technique for astrocytoma malignancy grading compatible with the clinical routine. STUDY DESIGN: One hundred forty biopsies of astrocytomas were collected from 2 hospitals. The degree of tumor malignancy was defined as low or high according to the World Health Organization grading system. From each biopsy, images were digitized and segmented to isolate nuclei from background tissue. Morphologic and textural nuclear features were quantified to encode tumor malignancy. Each case was represented by a 40-dimensional feature vector. An exhaustive search procedure in feature space was utilized to determine the best feature combination that resulted in the smallest classification error. Low and high grade tumors were discriminated using support vector machines (SVMs). To evaluate the system performance, all available data were split randomly into training and test sets. RESULTS: The best vector combination consisted of 3 textural and 2 morphologic features. Low and high grade cases were discriminated with an accuracy of 90.7% and 88.9%, respectively, using an SVM classifier with polynomial kernel of degree 2. CONCLUSION: The proposed methodology was based on standards that are common in daily clinical practice and might be used in parallel with conventional grading as a second-opinion tool to reduce subjectivity in the classification of astrocytomas.     

Class prediction and discovery using gene microarray and proteomics mass spectroscopy data: curses,caveats, cautions

MOTIVATION: Two practical realities constrain the analysis of microarray data, mass spectra from proteomics, and biomedical infrared or magnetic resonance spectra. One is the 'curse of dimensionality': the number of features characterizing these data is in the thousands or tens of thousands. The other is the 'curse of dataset sparsity': the number of samples is limited. The consequences of these two curses are far-reaching when such data are used to classify the presence or absence of disease. RESULTS: Using very simple classifiers, we show for several publicly available microarray and proteomics datasets how these curses influence classification outcomes. In particular, even if the sample per feature ratio is increased to the recommended 5-10 by feature extraction/reduction methods, dataset sparsity can render any classification result statistically suspect. In addition, several 'optimal' feature sets are typically identifiable for sparse datasets, all producing perfect classification results, both for the training and independent validation sets. This non-uniqueness leads to interpretational difficulties and casts doubt on the biological relevance of any of these 'optimal' feature sets. We suggest an approach to assess the relative quality of apparently equally good classifiers.     

Image analysis combined with quantitative cytochemistry

Summary This paper describes the application of image analysis combined with a quantitative staining method for the analysis of cervical specimens. The image analysis is carried out with the Leyden Television Analysis System, LEYTAS, of which two versions are described. LEYTAS-1 as well as LEYTAS-2 have both been designed with a high degree of flexibility and interaction facilities. A much wider range of image analysis programs is however, possible with LEYTAS-2, enabling many applications. LEYTAS-1, the earlier version, consists of a Leitz microscope with automated functions, a TV camera, the Texture Analysis System (TAS, Leitz), a four-bit grey value memory and a minicomputer (PDP 11/23). Using this instrumentation 1,500 cervical smears prepared from cell suspensions and stained with acriflavin-Feulgen-Sits have been analysed in a completely automated procedure. Image transformations working in parallel on entire fields, have been used for cell selection and artefact rejection. Resulting alarms, consisting of selected single cells and non-rejected artefacts are stored in the grey value memory, which is displayed on a TV monitor. This option allows visual interaction after the machine diagnosis has been made. The machine diagnosis was correct in 320 out 321 specimens with a severe dysplasia or more serious lesion. The false positive rate in 561 morphologically negative specimens (normal and inflammation) was 16% (machine diagnosis). Visual interaction by subtracting the visually recognized false alarms from the total number of alarms reduces the false positive rate to 11%. In LEYTAS-2, which is based on LEYTAS-1 studies, the microscope is equipped with a new type of objective, enabling the analysis of microscope fields, which are four times as large as in LEYTAS-1. The image analysis part consists of the Modular Image Analysis Computer (MIAC, Leitz) and for alarm storage an eight-bit grey value processor is used. Comparison with LEYTAS-1 shows that cell selection capacities are similar and that the speed is four times higher.In honour of Prof. P. van Duijn     

High-resolution color video cytophotometry

Comparison was made between cytophotometric measurements obtained using two data acquisition systems, one a microphotometer and the other a rapid video camera system, to ascertain whether the degradation of data with the faster video acquisition system still results in recorded images of sufficient quality to permit computer discrimination between cells of very similar appearance. Normal-appearing intermediate cells from cases with normal cytology and those from patients with dysplasia or malignant disease, as well as the subvisual markers within these cells that have rendered them capable of cytophotometric discrimination, were used for the study. Comparison of the data recorded by the two systems indicates that the diagnostic information is preserved in the change-over to a full-field, video-rate scanning system, with differences in the data caused primarily by differences in the spectral response of the two systems. This was reflected in the substantial differences observed in the color-related features and the lesser differences seen in the textural features, while the morphometric features (outline and shape) were virtually unaffected. The differences were primarily expressed on a cell-to-cell basis; in sets of about 300 cells, which would be used in patient-to-patient comparisons, the feature values showed remarkable consistency between the two systems.     

LEDPatNet19: Automated Emotion Recognition Model based on Nonlinear LED Pattern Feature Extraction Function using EEG Signals

Electroencephalography (EEG) signals collected from human brains have generally been used to diagnose diseases. Moreover, EEG signals can be used in several areas such as emotion recognition, driving fatigue detection. This work presents a new emotion recognition model by using EEG signals. The primary aim of this model is to present a highly accurate emotion recognition framework by using both a hand-crafted feature generation and a deep classifier. The presented framework uses a multilevel fused feature generation network. This network has three primary phases, which are tunable Q-factor wavelet transform (TQWT), statistical feature generation, and nonlinear textural feature generation phases. TQWT is applied to the EEG data for decomposing signals into different sub-bands and create a multilevel feature generation network. In the nonlinear feature generation, an S-box of the LED block cipher is utilized to create a pattern, which is named as Led-Pattern. Moreover, statistical feature extraction is processed using the widely used statistical moments. The proposed LED pattern and statistical feature extraction functions are applied to 18 TQWT sub-bands and an original EEG signal. Therefore, the proposed hand-crafted learning model is named LEDPatNet19. To select the most informative features, ReliefF and iterative Chi2 (RFIChi2) feature selector is deployed. The proposed model has been developed on the two EEG emotion datasets, which are GAMEEMO and DREAMER datasets. Our proposed hand-crafted learning network achieved 94.58%, 92.86%, and 94.44% classification accuracies for arousal, dominance, and valance cases of the DREAMER dataset. Furthermore, the best classification accuracy of the proposed model for the GAMEEMO dataset is equal to 99.29%. These results clearly illustrate the success of the proposed LEDPatNet19.