Xian Du

Automated Diagnosis of Glaucoma Using Texture and Higher Order Spectra Features

Glaucoma is the second leading cause of blindness worldwide. It is a disease in which fluid pressure in the eye increases continuously, damaging the optic nerve and causing vision loss. Computational decision support systems for the early detection of glaucoma can help prevent this complication. The retinal optic nerve fiber layer can be assessed using optical coherence tomography, scanning laser polarimetry, and Heidelberg retina tomography scanning methods. In this paper, we present a novel method for glaucoma detection using a combination of texture and higher order spectra (HOS) features from digital fundus images. Support vector machine, sequential minimal optimization, naive Bayesian, and random-forest classifiers are used to perform supervised classification. Our results demonstrate that the texture and HOS features after z-score normalization and feature selection, and when combined with a random-forest classifier, performs better than the other classifiers and correctly identifies the glaucoma images with an accuracy of more than 91%. The impact of feature ranking and normalization is also studied to improve results. Our proposed novel features are clinically significant and can be used to detect glaucoma accurately.

Classification of Epilepsy Using High-Order Spectra Features and Principle Component Analysis

The classification of epileptic electroencephalogram (EEG) signals is challenging because of high nonlinearity, high dimensionality, and hidden states in EEG recordings. The detection of the preictal state is difficult due to its similarity to the ictal state. We present a framework for using principal components analysis (PCA) and a classification method for improving the detection rate of epileptic classes. To unearth the nonlinearity and high dimensionality in epileptic signals, we extract principal component features using PCA on the 15 high-order spectra (HOS) features extracted from the EEG data. We evaluate eight classifiers in the framework using true positive (TP) rate and area under curve (AUC) of receiver operating characteristics (ROC). We show that a simple logistic regression model achieves the highest TP rate for class “preictal” at 97.5% and the TP rate on average at 96.8% with PCA variance percentages selected at 100%, which also achieves the most AUC at 99.5%.

Segmentation of fluorescence microscopy cell images using unsupervised mining.

The accurate measurement of cell and nuclei contours are critical for the sensitive and specific detection of changes in normal cells in several medical informatics disciplines. Within microscopy, this task is facilitated using fluorescence cell stains, and segmentation is often the first step in such approaches. Due to the complex nature of cell issues and problems inherent to microscopy, unsupervised mining approaches of clustering can be incorporated in the segmentation of cells. In this study, we have developed and evaluated the performance of multiple unsupervised data mining techniques in cell image segmentation. We adapt four distinctive, yet complementary, methods for unsupervised learning, including those based on k-means clustering, EM, Otsu’s threshold, and GMAC. Validation measures are defined, and the performance of the techniques is evaluated both quantitatively and qualitatively using synthetic and recently published real data. Experimental results demonstrate that k-means, Otsu’s threshold, and GMAC perform similarly, and have more precise segmentation results than EM. We report that EM has higher recall values and lower precision results from under-segmentation due to its Gaussian model assumption. We also demonstrate that these methods need spatial information to segment complex real cell images with a high degree of efficacy, as expected in many medical informatics applications.

NOVEL CLASSIFICATION OF CORONARY ARTERY DISEASE USING HEART RATE VARIABILITY ANALYSIS

Coronary artery disease (CAD) is a leading cause of death worldwide. Heart rate variability (HRV) has been proven to be a non-invasive marker of the autonomic modulation of the heart. Nonlinear analyses of HRV signals have shown that the HRV is reduced significantly in patients with CAD. Therefore, in this work, we extracted nonlinear features from the HRV signals using the following techniques: recurrence plots (RP), Poincare plots, and detrended fluctuation analysis (DFA). We also extracted three types of entropy, namely, Shannon entropy (ShanEn), approximation entropy (ApEn), and sample entropy (SampEn). These features were subjected to principal component analysis (PCA). The significant principal components were evaluated using eight classification techniques, and the performances of these techniques were evaluated to determine which presented the highest accuracy in classifying normal and CAD classes. We observed that the multilayer perceptron (MLP) method resulted in the highest classification accuracy (89.5%) using our proposed technique.

Cancer prognosis using support vector regression in imaging modality.

The proposed techniques investigate the strength of support vector regression (SVR) in cancer prognosis using imaging features. Cancer image features were extracted from patients and recorded into censored data. To employ censored data for prognosis, SVR methods are needed to be adapted to uncertain targets. The effectiveness of two principle breast features, tumor size and lymph node status, was demonstrated by the combination of sampling and feature selection methods. In sampling, breast data were stratified according to tumor size and lymph node status. Three types of feature selection methods comprised of no selection, individual feature selection, and feature subset forward selection, were employed. The prognosis results were evaluated by comparative study using the following performance metrics: concordance index (CI) and Brier score (BS). Cox regression was employed to compare the results. The support vector regression method (SVCR) performs similarly to Cox regression in three feature selection methods and better than Cox regression in non-feature selection methods measured by CI and BS. Feature selection methods can improve the performance of Cox regression measured by CI. Among all cross validation results, stratified sampling of tumor size achieves the best regression results for both feature selection and non-feature selection methods. The SVCR regression results, perform better than Cox regression when the techniques are used with either CI or BS. The best CI value in the validation results is 0.6845. The best CI value corresponds to the best BS value 0.2065, which were obtained in the combination of SVCR, individual feature selection, and stratified sampling of the number of positive lymph nodes. In addition, we also observe that SVCR performs more consistently than Cox regression in all prognosis studies. The feature selection method does not have a significant impact on the metric values, especially on CI. We conclude that the combinational methods of SVCR, feature selection, and sampling can improve cancer prognosis, but more significant features may further enhance cancer prognosis accuracy.

Concentric circle scanning system for large-area and high-precision imaging

Large-area manufacturing surfaces containing micro- and nano-scale features and large-view biomedical targets motivate the development of large-area, high-resolution and high-speed imaging systems. Compared to constant linear velocity scans and raster scans, constant angular velocity scans can significantly attenuate transient behavior while increasing the speed of imaging. In this paper, we theoretically analyze and evaluate the speed, acceleration and jerks of concentric circular trajectory sampling (CCTS). We then present a CCTS imaging system that demonstrates less vibration and lower mapping errors than raster scanning for creating a Cartesian composite image, while maintaining comparably fast scanning speed for large scanning area.

Concentric circular trajectory sampling for super-resolution and image mosaicing

Ubiquitous applications in diverse fields motivate large-area sampling, super-resolution (SR) and image mosaicing. However, conventional translational sampling has drawbacks including laterally constrained variations between samples. Meanwhile, existing rotational sampling methods do not consider the uniformity of sampling points in Cartesian coordinates, resulting in additional distortion errors in sampled images. We design a novel optimized concentric circular trajectory sampling (OCCTS) method to acquire image information uniformly at fast sampling speeds. The sampling method allows multiple low-resolution images for conventional SR algorithms to be acquired by adding small variations in the angular dimension. Experimental results demonstrate that OCCTS can beat comparable CCTS methods that lack optimized sampling densities by reducing sampling time by more than 11.5% while maintaining 50% distortion error reduction. The SR quality of OCCTS has at least 5.2% fewer distortion errors than the comparable CCTS methods. This paper is the first, to the best of our knowledge, to present an OCCTS method for SR and image mosaicing.

3-D knee cartilage segmentation using a smoothing B-Spline active surface

We present an adaptive solution for guinea pig knee cartilage segmentation using a 3-D smoothing B-Spline active surface. An adaptive parametric combination of edge-based forces and balloon force solves the problem of capture range of external forces. The comparison between the results of the experiments using this method and previous 3-D validated snake segmentation shows that the accuracy and robustness are improved.

Controlled angular and radial scanning for super resolution concentric circular imaging

Poor motion estimation and subsequent registration are detrimental to super-resolution (SR). In this paper, we present a camera sampling method for achieving SR in concentric circular trajectory sampling (CCTS). Using this method, we can precisely control regular radial and angular shifts in CCTS. SR techniques can be subsequently applied ring by ring in radial and angular dimensions. Not only does the proposed camera sampling method eliminate the transient behavior and increases the sampling speed in CCTS, it also preserves the SR accuracy. Our experimental results demonstrate that our approach can accurately discriminate SR pixels from blurry images.

Salient frame extraction using support vector regression and motion features

We present a new support vector regression (SVR) algorithm to extract salient frames from videos. We use optical flow to describe motion in frames and an adaptive SVR to identify the abrupt change of content in frame sequences. We show that the proposed algorithm is computationally simple and effective in detecting salient frames in video sequences.